Merge pull request 'Push kkkmrtvotrsu' (#77) from push-kkkmrtvotrsu into main

Reviewed-on: #77
This commit was merged in pull request #77.
This commit is contained in:
coissac committed 2026-10-13 07:54:48 +00:00
commit 2232628e58
147 files changed
+6963 -8255

No files matched your search

+1
View File
@@ -44,3 +44,4 @@ biblio
*.parstree *.parstree
*.ckp.gz *.ckp.gz
*.model *.model
scripts/__pycache__/mk_wiki.cpython-314.pyc
+1 -1
View File
@@ -1119,7 +1119,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1370,7 +1370,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1128,7 +1128,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1130,7 +1130,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1140,7 +1140,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
File diff suppressed because it is too large. Load diff
@@ -1265,7 +1265,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1485,8 +1485,9 @@ this pipeline.</p>
by <code>verify_presence</code>/<code>verify_merge_presence</code>, which only check index by <code>verify_presence</code>/<code>verify_merge_presence</code>, which only check index
<em>content</em> against the <code>.npz</code> truth, never the query API.</li> <em>content</em> against the <code>.npz</code> truth, never the query API.</li>
<li><code>pack --sparse</code> produces a presence-matrix format documented (see <li><code>pack --sparse</code> produces a presence-matrix format documented (see
<a href="../../architecture/siblings/">siblings.md</a>) as faster for single-row <a href="../obicompactvec/">obicompactvec.md</a>, "Sparse matrix formats") as faster
access (query) and slower for column-oriented access (phylo <code>--metric</code>). for single-row access (query) and slower for column-oriented access
(phylo <code>--metric</code>).
<code>global_index_presence/</code> built by <code>merge_presence.sh</code> is always packed <code>global_index_presence/</code> built by <code>merge_presence.sh</code> is always packed
dense (packing is a stage inside <code>merge</code>, not a separate <code>pack</code> dense (packing is a stage inside <code>merge</code>, not a separate <code>pack</code>
invocation) — there was no dense/sparse regression check.</li> invocation) — there was no dense/sparse regression check.</li>
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -579,7 +579,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1265,7 +1265,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1388,7 +1388,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1265,7 +1265,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+2 -2
View File
@@ -1504,7 +1504,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -2208,7 +2208,7 @@
<span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">sub_matrix</span><span class="p">(</span><span class="o">&amp;</span><span class="bp">self</span><span class="p">,</span><span class="w"> </span><span class="n">slots</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="p">[</span><span class="kt">usize</span><span class="p">])</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nb">Vec</span><span class="o">&lt;</span><span class="nb">Vec</span><span class="o">&lt;</span><span class="kt">bool</span><span class="o">&gt;&gt;</span> <span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">sub_matrix</span><span class="p">(</span><span class="o">&amp;</span><span class="bp">self</span><span class="p">,</span><span class="w"> </span><span class="n">slots</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="p">[</span><span class="kt">usize</span><span class="p">])</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nb">Vec</span><span class="o">&lt;</span><span class="nb">Vec</span><span class="o">&lt;</span><span class="kt">bool</span><span class="o">&gt;&gt;</span>
<span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">fill_sub_matrix</span><span class="p">(</span><span class="o">&amp;</span><span class="bp">self</span><span class="p">,</span><span class="w"> </span><span class="n">slots</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="p">[</span><span class="kt">usize</span><span class="p">],</span><span class="w"> </span><span class="n">out</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">mut</span><span class="w"> </span><span class="p">[</span><span class="nb">Vec</span><span class="o">&lt;</span><span class="kt">bool</span><span class="o">&gt;</span><span class="p">])</span> <span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">fill_sub_matrix</span><span class="p">(</span><span class="o">&amp;</span><span class="bp">self</span><span class="p">,</span><span class="w"> </span><span class="n">slots</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="p">[</span><span class="kt">usize</span><span class="p">],</span><span class="w"> </span><span class="n">out</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">mut</span><span class="w"> </span><span class="p">[</span><span class="nb">Vec</span><span class="o">&lt;</span><span class="kt">bool</span><span class="o">&gt;</span><span class="p">])</span>
</code></pre></div> </code></pre></div>
<p>Column-first to match the on-disk column-major layout. <code>fill_sub_matrix</code> sorts <code>slots</code> once, then calls each column's <code>fill_batch</code> in turn — no redundant per-column sort. On <code>PersistentSparseBitMatrix</code> (k-mer-major, no column method) this degrades to a row-by-row decode; see <a href="../../architecture/siblings/">siblings.md</a>.</p> <p>Column-first to match the on-disk column-major layout. <code>fill_sub_matrix</code> sorts <code>slots</code> once, then calls each column's <code>fill_batch</code> in turn — no redundant per-column sort. On <code>PersistentSparseBitMatrix</code> (k-mer-major, no column method) this goes through <code>nonzero_iter</code> instead, decoding one row at a time; see <a href="../obicompactvec/">obicompactvec.md</a>, "Sparse matrix formats".</p>
<hr /> <hr />
<h2 id="layeredstores-and-aggregation-traits">LayeredStore\&lt;S&gt; and aggregation traits</h2> <h2 id="layeredstores-and-aggregation-traits">LayeredStore\&lt;S&gt; and aggregation traits</h2>
<p><code>LayeredStore&lt;S&gt;</code> is a generic aggregation wrapper over <code>Vec&lt;S&gt;</code>. It propagates three traits from <code>obicompactvec::traits</code> up the hierarchy via blanket impls:</p> <p><code>LayeredStore&lt;S&gt;</code> is a generic aggregation wrapper over <code>Vec&lt;S&gt;</code>. It propagates three traits from <code>obicompactvec::traits</code> up the hierarchy via blanket impls:</p>
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1348,7 +1348,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1332,7 +1332,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1343,7 +1343,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+219 -3
View File
@@ -494,7 +494,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -632,6 +632,46 @@
</a> </a>
</li> </li>
<li class="md-nav__item"> <li class="md-nav__item">
<a class="md-nav__link" href="#sparse-matrix-formats">
<span class="md-ellipsis">
Sparse matrix formats
</span>
</a>
<nav aria-label="Sparse matrix formats" class="md-nav">
<ul class="md-nav__list">
<li class="md-nav__item">
<a class="md-nav__link" href="#persistentsparsebitmatrix">
<span class="md-ellipsis">
PersistentSparseBitMatrix
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#nonzero_iter-the-one-traversal-per-format">
<span class="md-ellipsis">
nonzero_iter — the one traversal per format
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#persistentsparsecompactintmatrix">
<span class="md-ellipsis">
PersistentSparseCompactIntMatrix
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#aggregation-traits-matrix-level"> <a class="md-nav__link" href="#aggregation-traits-matrix-level">
<span class="md-ellipsis"> <span class="md-ellipsis">
@@ -1191,7 +1231,7 @@ Pass 1 — byte max, SIMD-vectorizable, O(n)
<tr> <tr>
<td><code>Sparse</code></td> <td><code>Sparse</code></td>
<td>bit: <code>sparse_meta.json</code> + PFIV/Elias-Fano component files, row-major. Int: same support files (built on <code>PersistentSparseBitMatrix</code> internally) plus <code>singleton_values.pciv</code>/<code>multi_values.pciv</code>/<code>multi_offsets</code> for the per-row, non-deduplicated values</td> <td>bit: <code>sparse_meta.json</code> + PFIV/Elias-Fano component files, row-major. Int: same support files (built on <code>PersistentSparseBitMatrix</code> internally) plus <code>singleton_values.pciv</code>/<code>multi_values.pciv</code>/<code>multi_offsets</code> for the per-row, non-deduplicated values</td>
<td><code>pack --sparse</code>; see <a href="../../architecture/siblings/">siblings.md</a> for the sparse-vs-dense access-pattern trade-off</td> <td><code>pack --sparse</code>; see "Sparse matrix formats" below for the sparse-vs-dense access-pattern trade-off</td>
</tr> </tr>
<tr> <tr>
<td><code>Implicit</code> (bit only)</td> <td><code>Implicit</code> (bit only)</td>
@@ -1201,7 +1241,6 @@ Pass 1 — byte max, SIMD-vectorizable, O(n)
</tbody> </tbody>
</table> </table>
<p><code>PersistentBitMatrix::open(layer_dir)</code> auto-detects the variant, in order: <code>matrix.pbmx</code> → Packed, <code>presence/meta.json</code> → Columnar, <code>presence/sparse_meta.json</code> → Sparse, <code>layer_meta.json</code> (no presence dir at all) → Implicit. <code>PersistentCompactIntMatrix::open(layer_dir)</code> mirrors the same priority order minus <code>Implicit</code> (there's no implicit count matrix — counts always have at least one on-disk column): <code>matrix.pcmx</code> → Packed, <code>counts/meta.json</code> → Columnar, <code>counts/singleton_values.pciv</code> → Sparse. <code>col_view</code>/<code>col</code>/<code>sub_matrix</code> panic on <code>Sparse</code>/<code>Implicit</code> where the operation has no direct-slice equivalent (Sparse is k-mer-major, not column-major; Implicit has no backing storage) — callers needing per-column data on those variants go through <code>row</code>/<code>fill_row</code>.</p> <p><code>PersistentBitMatrix::open(layer_dir)</code> auto-detects the variant, in order: <code>matrix.pbmx</code> → Packed, <code>presence/meta.json</code> → Columnar, <code>presence/sparse_meta.json</code> → Sparse, <code>layer_meta.json</code> (no presence dir at all) → Implicit. <code>PersistentCompactIntMatrix::open(layer_dir)</code> mirrors the same priority order minus <code>Implicit</code> (there's no implicit count matrix — counts always have at least one on-disk column): <code>matrix.pcmx</code> → Packed, <code>counts/meta.json</code> → Columnar, <code>counts/singleton_values.pciv</code> → Sparse. <code>col_view</code>/<code>col</code>/<code>sub_matrix</code> panic on <code>Sparse</code>/<code>Implicit</code> where the operation has no direct-slice equivalent (Sparse is k-mer-major, not column-major; Implicit has no backing storage) — callers needing per-column data on those variants go through <code>row</code>/<code>fill_row</code>.</p>
<p>Unlike the bit side, <code>PersistentSparseCompactIntMatrix</code>'s values are <em>not</em> deduplicated across rows — two rows can share the same non-zero column set (same <code>dict_id</code> in the shared support) while carrying different counts — so its <code>CountPartials</code> impl can't reuse the support's dict-multiplicity shortcut the way <code>BitPartials for PersistentSparseBitMatrix</code> does. It still avoids the naive <code>O(n_cols² × n)</code> column-pair scan via a single row-major pass (<code>row_major_pairwise</code> in <code>sparse_intmatrix.rs</code>), reconstructing the squared-difference formulas (<code>euclidean</code>/<code>relfreq_euclidean</code>/<code>hellinger</code>) from per-column marginals via <code>Σ(a-b)² = Σa²+Σb²-2Σab</code> — see <a href="../../architecture/siblings/">siblings.md</a>'s "<code>PersistentCompactIntMatrix::Sparse</code> — implemented" entry for the full derivation.</p>
<p><code>col_view(c)</code> returns the appropriate view directly:</p> <p><code>col_view(c)</code> returns the appropriate view directly:</p>
<div class="highlight"><pre><span></span><code><span class="c1">// PersistentBitMatrix</span> <div class="highlight"><pre><span></span><code><span class="c1">// PersistentBitMatrix</span>
<span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">col_view</span><span class="p">(</span><span class="o">&amp;</span><span class="bp">self</span><span class="p">,</span><span class="w"> </span><span class="n">c</span><span class="p">:</span><span class="w"> </span><span class="kt">usize</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">BitSliceView</span><span class="o">&lt;'</span><span class="nb">_</span><span class="o">&gt;</span> <span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">col_view</span><span class="p">(</span><span class="o">&amp;</span><span class="bp">self</span><span class="p">,</span><span class="w"> </span><span class="n">c</span><span class="p">:</span><span class="w"> </span><span class="kt">usize</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">BitSliceView</span><span class="o">&lt;'</span><span class="nb">_</span><span class="o">&gt;</span>
@@ -1212,6 +1251,183 @@ Pass 1 — byte max, SIMD-vectorizable, O(n)
<p>No wrapper enums (<code>BitColView</code>, <code>IntColView</code>): the caller receives a <code>Copy</code> view struct immediately usable with any view method or bulk builder method.</p> <p>No wrapper enums (<code>BitColView</code>, <code>IntColView</code>): the caller receives a <code>Copy</code> view struct immediately usable with any view method or bulk builder method.</p>
<p><code>pack_compact_int_matrix</code> and <code>pack_bit_matrix</code> convert columnar → packed format.</p> <p><code>pack_compact_int_matrix</code> and <code>pack_bit_matrix</code> convert columnar → packed format.</p>
<hr/> <hr/>
<h2 id="sparse-matrix-formats">Sparse matrix formats</h2>
<p>Motivated by real k-mer-family data being extremely row-sparse (most rows —
k-mers — present in only a handful of genome columns out of dozens to
thousands): a row-major, deduplicated alternative to the dense column-major
formats above, built once per layer like the rest of the pipeline (never the
whole multi-billion-row index at once). Implements the exact-duplicate
special case of Alanko, Bille, Gørtz, Navarro, Puglisi, "Compact Data
Structures for Collections of Sets" (2025,
<code>biblio/Alanko et al. - Compact Data Structures for Collections of
Sets.pdf</code>) — a plain dedup dictionary, not their full subset-containment
hierarchy.</p>
<h3 id="persistentsparsebitmatrix"><code>PersistentSparseBitMatrix</code></h3>
<p>Four mmap-backed on-disk components: an <code>is_multi</code> rank-capable flag per row
(singleton vs. multi-genome), a fixed-bit-width array for singleton rows
(genome index directly, <code>ceil(log2(n_cols))</code> bits), a separate fixed-width
array for multi-genome rows (<code>dict_id</code>, <code>ceil(log2(n_distinct_multi_sets))</code>
bits — kept apart from the singleton array because <code>n_distinct_multi_sets</code>
can be large in absolute terms even when multi-genome rows are a small
<em>fraction</em> of all rows, and a shared array would force every row, singletons
included, to pay the wider width), and a deduplicated dictionary of distinct
multi-genome sets (Elias-Fano-encoded byte offsets + a varint-encoded values
blob). Supporting primitives: <code>PersistentFixedIntVec</code> (arbitrary,
runtime-parameterised bit width, width <code>0</code> included — needed once an
<code>EliasFano</code> reopen bug surfaced, see below), <code>PersistentRankSelectBitVec</code>
(rank1/rank0/select1 on top of the crate's existing <code>count_ones</code>, via
<code>common_traits::SelectInWord</code>), <code>EliasFano</code> (composes the two). <code>BinaryMatrix</code>
(<code>n</code>, <code>n_cols</code>, <code>row</code>/<code>fill_row</code>, <code>fill_sub_matrix</code>, <code>count_ones</code>) is the
trait unifying dense and sparse at the call sites that need both
interchangeably; column-oriented methods (<code>col</code>, <code>col_view</code>, the
<code>partial_*_dist_matrix</code> family) stay dense-only — <code>Sparse</code>/<code>Implicit</code> panic
there (see the <code>PersistentBitMatrix::open</code> note above).</p>
<p>Measured on real data (one layer, 30.2M rows, 91 genomes):</p>
<table>
<thead>
<tr>
<th></th>
<th>dense</th>
<th>sparse</th>
<th>ratio</th>
</tr>
</thead>
<tbody>
<tr>
<td>on-disk size</td>
<td>328.1MB</td>
<td>43.7MB</td>
<td><strong>7.5x</strong> smaller</td>
</tr>
<tr>
<td>build time / peak RSS</td>
<td>—</td>
<td>4.26s / 628MB</td>
<td>per-layer, in-memory construction</td>
</tr>
<tr>
<td>row access, sequential (2M reads)</td>
<td>43ns/row</td>
<td>32ns/row</td>
<td>sparse faster (smaller structure, better cache fit)</td>
</tr>
<tr>
<td>row access, random (2M reads)</td>
<td>409ns/row</td>
<td>85ns/row</td>
<td>sparse <strong>~4.8x faster</strong> — the <code>--shannon</code>/family-lookup access shape</td>
</tr>
<tr>
<td>column access, one full column (30.2M rows)</td>
<td>11.5ms</td>
<td>993ms</td>
<td>sparse <strong>86x slower</strong> — no native column method, every read decodes a full row to keep one bit</td>
</tr>
</tbody>
</table>
<p>The row-access wins (compactness was the stated design goal, not speed) come
from dense's genome-major layout scattering a single row read across a much
bigger file — costlier than sparse's rank/select/varint decode once the file
is this much smaller. Column access is the flip side of the same layout
choice; <code>nonzero_iter</code> (below) is what removes it from the hot path that
actually matters (<code>query</code>).</p>
<p>Two reopen-correctness bugs, now fixed at the source: (1) <code>EliasFano::open</code>
re-derived its low-bits width from the persisted low-vector's own width
byte; the width-<code>0</code> case was built with a dummy 1-bit placeholder (the
builder used to reject true width <code>0</code>), silently doubling every reopened
value. Fixed by making <code>PersistentFixedIntVec</code> genuinely support width <code>0</code>
(no storage, <code>get</code> always <code>0</code>). (2) An empty row (cardinality 0) used to be
recorded as a singleton at genome <code>0</code>, indistinguishable on read-back from a
<em>real</em> singleton at genome <code>0</code>. Fixed by routing cardinality-0 rows through
the dictionary path (a genuine empty entry).</p>
<p>Still deferred: full Alanko et al. subset-hierarchy compression (only the
exact-duplicate case is built), a sparse <code>PersistentCompactIntMatrix</code>
variant beyond what's described below, BRWT-style column-correlation
exploitation, and a row-major rewrite of
<code>partial_jaccard_dist_matrix</code>/<code>partial_hamming_dist_matrix</code>/etc. as a
per-row co-occurrence accumulation (<code>O(Σ_rows k̄²)</code>) so <code>obikindex</code>'s
<code>--metric</code> distance-matrix path stops paying the column-access penalty on
<code>Sparse</code> — needs its own design pass (how it plugs into
<code>BitPartials</code>/<code>ColumnWeights</code> so both matrix types keep serving <code>--metric</code>),
not just "port the loop".</p>
<h3 id="nonzero_iter-the-one-traversal-per-format"><code>nonzero_iter</code> — the one traversal per format</h3>
<p><code>fn nonzero_iter&lt;'a&gt;(&amp;'a self, slots: &amp;'a [usize]) -&gt; Box&lt;dyn Iterator&lt;Item = (usize, usize, u32)&gt; + 'a&gt;</code>
(item: index into <code>slots</code>, column, value) is the single foundational
per-format traversal primitive every consumer builds on — <code>fill_sub_matrix</code>
and a <code>for_each</code>-style callback are both trivial, free consumers of it
(<code>.for_each(f)</code> is <code>Iterator::for_each</code>; <code>fill_sub_matrix</code> drains the
iterator and scatters into <code>out[][]</code>), instead of two independently
hand-maintained traversals that can silently diverge. <code>Box&lt;dyn Iterator&gt;</code>,
not a bare <code>impl Iterator</code>: <code>Columnar</code>/<code>Packed</code>/<code>Sparse</code>/<code>Implicit</code> are
genuinely different concrete types and the method isn't on a
dyn-compatible trait (<code>BinaryMatrix</code> is used as <code>dyn BinaryMatrix</code>
elsewhere, and RPITIT methods aren't dyn-compatible) — one <code>Box</code> per
<code>nonzero_iter</code> call, not per cell.</p>
<p>Per-format implementation: <code>PersistentSparseBitMatrix</code> decodes natively,
buffered one row at a time (<code>std::iter::from_fn</code> over the existing
<code>for_each_genome_in_row</code>, no <code>n_cols</code>-wide allocation ever). <code>Columnar</code>/
<code>Packed</code> loop columns, collecting each column's hits via
<code>BitSliceView::nonzero_among_sorted</code>/<code>IntSliceView::nonzero_among_sorted</code>
(a <code>filter</code>/<code>filter_map</code> over the vector-level <code>get()</code>, no new state
machine — <code>std</code>'s own <code>Filter</code> iterator already is one) into one <code>Vec</code> via
<code>.extend()</code> (not <code>flat_map</code>: a <code>flat_map</code> closure can't lazily return
something borrowing its own captured sort permutation across separate calls
without either boxing per-column or fighting the borrow checker — eager
collection sidesteps it at zero extra cost, since <code>fill_sub_matrix</code> already
fully materialises anyway). <code>Implicit</code> is trivial (<code>slots.iter().map(|&amp;i| (i, 0, 1))</code>).</p>
<p>This closed a real dispatch bug by construction, not by patching it:
<code>PersistentBitMatrix::fill_sub_matrix</code>/<code>sub_matrix</code> used to reimplement a
naive per-<code>(column, slot)</code> loop instead of delegating to
<code>PersistentSparseBitMatrix</code>'s own efficient native method for <code>Self::Sparse</code>
— two hand-written traversals for the same format, free to drift apart, and
they had (<code>obikphylo</code>'s own cache layer had independently built a parallel
enum wrapper that <em>did</em> dispatch correctly, evidence the bug was worked
around rather than fixed at the source). With <code>fill_sub_matrix</code>/<code>sub_matrix</code>
rewritten to drain <code>nonzero_iter</code>, there is only one traversal per format
left to get right. <code>KmerPartition::query_partition_with</code>
(<code>obikindex/src/partition/query_layer.rs</code>) — previously column-major
(<code>for g { for slot { col_value } }</code>, which for <code>Sparse</code> rebuilt a full row
per single cell touched, O(hits × n_cols) instead of O(hits) — the original
motivation for this primitive) — now issues one <code>layer.nonzero_iter(&amp;slot_list)</code>
call per layer, format-agnostic. Dense/sparse query performance parity
confirmed on real data (previously sparse 30-50% slower than dense,
reproducibly; now within ~1-3% either way — noise level).</p>
<h3 id="persistentsparsecompactintmatrix"><code>PersistentSparseCompactIntMatrix</code></h3>
<p>The count-matrix analogue, built on <code>PersistentSparseBitMatrix</code> as its
"which columns are non-zero" support, values <strong>not</strong> deduplicated (unlike
the bit side, two rows can share the same non-zero column set — same
<code>dict_id</code> — while carrying different counts, so the dict-multiplicity
shortcut <code>BitPartials for PersistentSparseBitMatrix</code> uses doesn't carry
over). <code>CountPartials</code> here: a single row-major pass (<code>row_major_pairwise</code>
in <code>sparse_intmatrix.rs</code>, decodes each row once via
<code>for_each_cell_in_row</code>, nests over that row's own co-present columns) —
<code>O(Σ k̄²)</code> over populated rows, avoiding the naive <code>O(n_cols² × n)</code>
column-pair rescan. <code>min(a,b)</code>-based kernels (<code>bray</code>, <code>relfreq_bray</code>) need
no correction — they vanish when either side is absent. <code>a·b</code> and <code>√(a·b)</code>
kernels (<code>euclidean</code>/<code>relfreq_euclidean</code>/<code>hellinger</code>) do need one, since
<code>(a-0)² = a² ≠ 0</code> unlike the <code>min</code>-based formulas — reconstructed from
per-column marginals via <code>Σ(a-b)² = Σa²+Σb²-2Σab</code>.
<code>threshold_jaccard(1)</code> shortcuts to <code>BitPartials::partial_jaccard</code>
(threshold 1 is exactly presence); <code>threshold_jaccard(0)</code> is closed-form
(every <code>u32</code> is <code>≥ 0</code>).</p>
<p>Wiring the <code>threshold==1</code> shortcut surfaced two pre-existing formula bugs in
<code>BitPartials for PersistentSparseBitMatrix</code> (present since that type's own
introduction, never caught because no test had compared <code>Sparse</code>'s raw
<code>partial_*</code> output against dense on real data — only the diagonal-blind
<code>jaccard_dist_matrix</code>/<code>hamming_dist_matrix</code> finalisations were tested),
fixed at the source:</p>
<ol>
<li><code>partial_jaccard</code>'s diagonal used to be <code>(0, 2×col_weights[i])</code> instead
of a genuine self-comparison <code>(col_weights[i], col_weights[i])</code> —
<code>col_weights_and_pair_counts</code>'s <code>inter</code> never pairs a column with itself
by construction, so the diagonal needs its own case.</li>
<li><code>partial_hamming</code>'s off-diagonal formula itself was wrong: it computed
<code>total - union</code> (rows where <em>neither</em> column is present) instead of the
actual Hamming distance <code>col_weights[i] + col_weights[j] - 2×inter[i,j]</code>
(symmetric-difference size) — the two only coincide when
<code>col_weights[i] + col_weights[j] == total</code>, which small/synthetic test
data can easily satisfy by accident.</li>
</ol>
<h2 id="aggregation-traits-matrix-level">Aggregation traits (matrix level)</h2> <h2 id="aggregation-traits-matrix-level">Aggregation traits (matrix level)</h2>
<h3 id="columnweights">ColumnWeights</h3> <h3 id="columnweights">ColumnWeights</h3>
<div class="highlight"><pre><span></span><code><span class="k">trait</span><span class="w"> </span><span class="n">ColumnWeights</span><span class="p">:</span><span class="w"> </span><span class="nb">Send</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="nb">Sync</span><span class="w"> </span><span class="p">{</span> <div class="highlight"><pre><span></span><code><span class="k">trait</span><span class="w"> </span><span class="n">ColumnWeights</span><span class="p">:</span><span class="w"> </span><span class="nb">Send</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="nb">Sync</span><span class="w"> </span><span class="p">{</span>
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1293,7 +1293,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1305,7 +1305,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1563,7 +1563,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1405,7 +1405,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1388,7 +1388,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1254,7 +1254,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1382,7 +1382,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1326,7 +1326,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1232,7 +1232,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -1354,7 +1354,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1228,7 +1228,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1314,7 +1314,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1227,7 +1227,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
Binary file not shown.
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1199,7 +1199,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1265,7 +1265,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+594 -4
View File
@@ -932,6 +932,17 @@
</span> </span>
</a> </a>
</li>
<li class="md-nav__item">
<a href="#automatic-estimation-gamma-shape-auto" class="md-nav__link">
<span class="md-ellipsis">
Automatic α estimation (--gamma-shape auto)
</span>
</a>
</li> </li>
<li class="md-nav__item"> <li class="md-nav__item">
@@ -943,6 +954,45 @@
</span> </span>
</a> </a>
</li>
<li class="md-nav__item">
<a href="#-estimation-literature-survey-and-design-discussion-2026-09-11" class="md-nav__link">
<span class="md-ellipsis">
α-estimation literature survey and design discussion (2026-09-11)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#sharing-one-sample-across-algorithms-sankoff-tnt-phyg-iqtree-snp-distance-implemented-2026-09-11" class="md-nav__link">
<span class="md-ellipsis">
Sharing one sample across algorithms (--sankoff/--tnt/--phyg/--iqtree + snp-* --distance) — implemented 2026-09-11
</span>
</a>
<nav class="md-nav" aria-label="Sharing one sample across algorithms (--sankoff/--tnt/--phyg/--iqtree + snp-* --distance) — implemented 2026-09-11">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#explicit-session-implemented-2026-09-12" class="md-nav__link">
<span class="md-ellipsis">
Explicit --session (implemented 2026-09-12)
</span>
</a>
</li>
</ul>
</nav>
</li> </li>
<li class="md-nav__item"> <li class="md-nav__item">
@@ -1691,7 +1741,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
@@ -2268,6 +2318,17 @@
</span> </span>
</a> </a>
</li>
<li class="md-nav__item">
<a href="#automatic-estimation-gamma-shape-auto" class="md-nav__link">
<span class="md-ellipsis">
Automatic α estimation (--gamma-shape auto)
</span>
</a>
</li> </li>
<li class="md-nav__item"> <li class="md-nav__item">
@@ -2279,6 +2340,45 @@
</span> </span>
</a> </a>
</li>
<li class="md-nav__item">
<a href="#-estimation-literature-survey-and-design-discussion-2026-09-11" class="md-nav__link">
<span class="md-ellipsis">
α-estimation literature survey and design discussion (2026-09-11)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#sharing-one-sample-across-algorithms-sankoff-tnt-phyg-iqtree-snp-distance-implemented-2026-09-11" class="md-nav__link">
<span class="md-ellipsis">
Sharing one sample across algorithms (--sankoff/--tnt/--phyg/--iqtree + snp-* --distance) — implemented 2026-09-11
</span>
</a>
<nav class="md-nav" aria-label="Sharing one sample across algorithms (--sankoff/--tnt/--phyg/--iqtree + snp-* --distance) — implemented 2026-09-11">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#explicit-session-implemented-2026-09-12" class="md-nav__link">
<span class="md-ellipsis">
Explicit --session (implemented 2026-09-12)
</span>
</a>
</li>
</ul>
</nav>
</li> </li>
<li class="md-nav__item"> <li class="md-nav__item">
@@ -4476,9 +4576,75 @@ F84/TN93 and is included below. <code>snp-</code> prefix on every CLI value.</p>
<p><strong><code>+Γ</code> rate-heterogeneity modifier, applicable to <code>snp-jc</code>, <code>snp-k2p</code>, <p><strong><code>+Γ</code> rate-heterogeneity modifier, applicable to <code>snp-jc</code>, <code>snp-k2p</code>,
<code>snp-k81</code>, <code>snp-t92</code>, <code>snp-f84</code>, <code>snp-hky85</code>, <code>snp-tn93</code></strong> (not <code>snp-raw</code>, <code>snp-k81</code>, <code>snp-t92</code>, <code>snp-f84</code>, <code>snp-hky85</code>, <code>snp-tn93</code></strong> (not <code>snp-raw</code>,
nothing to correct; not <code>snp-logdet</code>, no standard gamma formulation) — same nothing to correct; not <code>snp-logdet</code>, no standard gamma formulation) — same
formula as the base correction, weighted by a shape parameter <code>α</code> supplied formula as the base correction, weighted by a shape parameter <code>α</code> either
by the user (<code>--gamma-shape &lt;alpha&gt;</code>), not estimated by ML. A modifier on supplied by the user (<code>--gamma-shape &lt;alpha&gt;</code>) or estimated from the data
existing values, not a separate enum arm per distance.</p> (<code>--gamma-shape auto</code>/<code>estimate</code>, method-of-moments — not ML; see
"Automatic α estimation" below). A modifier on existing values, not a
separate enum arm per distance.</p>
<h3 id="automatic-estimation-gamma-shape-auto">Automatic α estimation (<code>--gamma-shape auto</code>)</h3>
<p><strong>Correction (verified against the primary source, 2026-09-11):</strong> Jin &amp;
Nei (1990) itself (<em>"Limitations of the Evolutionary Parsimony Method of
Phylogenetic Analysis"</em>, Mol. Biol. Evol. 7(2):82–102 — the paper this
whole <code>+Γ</code> correction is cited from, confirmed algebraically to match this
codebase's <code>corrected_log</code>/<code>k2p</code> exactly against their eq. A4, general, and
A8, the <code>a = 1</code> case) contains <strong>no</strong> data-driven α-estimation procedure.
Their own recommendation (p. 98) is a fixed default: <em>"we suggest that the
gamma distance with a = 1 [eq. A8] be used. However, one may choose a
different gamma distance, estimating a from data. Wilson et al. (1989)
recently used a distance with a = 1/2 for restriction-site data of
mitochondrial DNA in hominoids."</em> — i.e. Jin &amp; Nei explicitly punt
data-driven estimation to a <em>different</em> paper (Wilson et al. 1989), not
read/verified here. The estimator below is therefore <strong>not</strong> "Jin &amp; Nei's
method" under any framing — that attribution (present in an earlier
revision of this section) was wrong, not just under-cited.</p>
<p><strong>Implemented</strong> (<code>PartitionDispersion</code>, <code>obikphylo/src/siblings/algorithms/pairwise.rs</code>)
as an independent method-of-moments estimator, unrelated to any specific
published procedure: pools substitution counts by <strong>partition</strong> rather
than by genome pair, during the same <code>reduce_pairwise</code> pass that builds
<code>PairwiseTally</code> (no second scan).</p>
<p>For partition <code>i</code>: <code>n_i</code> = substitutions pooled over every genome pair,
<code>L_i</code> = eligible loci pooled over every genome pair, <code>R_i = n_i / L_i</code>.
Modeling among-site rate heterogeneity the same way as the <code>+Γ</code> correction
itself (a <code>Gamma(α, α)</code>-distributed, mean-1, multiplicative rate shared by
every locus in a partition — the classical Poisson-Gamma/negative-binomial
mixture, the general identity behind gamma-rate-heterogeneity corrections,
also behind Uzzell &amp; Corbin's (1971) original observation that substitution
counts across sites/regions are over-dispersed relative to Poisson):</p>
<div class="arithmatex">\[
\mathbb{E}[R_i] = \mu \qquad \mathrm{Var}[R_i] = \frac{\mu}{L_i} + \frac{\mu^2}{\alpha}
\]</div>
<p>Weighting each partition's squared deviation by its own <code>L_i</code> cancels the
Poisson term before attributing what's left to <code>α</code>:</p>
<div class="arithmatex">\[
\hat\mu = \frac{\sum_i n_i}{\sum_i L_i} \qquad
V = \frac{\sum_i L_i (R_i-\hat\mu)^2}{\sum_i L_i} \qquad
\hat\alpha = \frac{\hat\mu^2}{V - \hat\mu/\bar L}
\]</div>
<p>where <code>\bar L</code> is the mean partition size. Returns "no estimate" (falls
back to the uncorrected formula, warns) when fewer than 2 partitions have
data, <code>\hat\mu \le 0</code>, or <code>V</code> doesn't exceed the Poisson floor
<code>\hat\mu/\bar L</code> — no detectable over-dispersion, <code>α</code> would be unbounded.</p>
<p><strong>Caveat, stated explicitly rather than left implicit</strong>: unlike every
closed-form correction in <code>snp_distance.rs</code> (each verified line-by-line
against <code>ape</code>'s <code>dist_dna.c</code>, and now also against Jin &amp; Nei 1990 directly
for the base <code>+Γ</code> formula), this estimator is derived from first
principles (the general Poisson-Gamma/negative-binomial identity) with no
primary-source procedure behind it at all — not Jin &amp; Nei's (confirmed
above), and Wilson et al. (1989), the paper they point to instead, hasn't
been read/verified either. Mathematically self-consistent (re-derived and
checked, not guessed), but a from-scratch method, not a literature
implementation. If <code>--gamma-shape</code> needs a value with a literature
pedigree rather than an estimated one, Jin &amp; Nei's own stated default,
<code>α = 1</code> (<code>--gamma-shape 1</code>), is the better-supported choice today.</p>
<p>Deliberately <strong>not</strong> gated by <code>--sankoff-ratio-ceiling</code> the way
<code>base_pair_tally</code> is (same precedent as <code>cardinality_tally</code> — see its own
doc comment): that filter excludes individual saturated <em>pairs</em> from a
composition estimate computed once at the very end, from the complete
<code>PairwiseTally</code>; the partition axis needed here only exists transiently,
one partition at a time, while <code>PairwiseTally</code> is still being built — long
before any pair's final SNP ratio (and thus its ratio_ceiling eligibility)
is known. <code>--exclude-genome</code> isn't applied either, matching
<code>reduce_pairwise</code>'s own raw per-pair fold.</p>
<p><strong>Implemented now: <code>snp-raw</code>, <code>snp-jc</code>, <code>snp-k2p</code>, <code>snp-k81</code>, <code>snp-f81</code>, <p><strong>Implemented now: <code>snp-raw</code>, <code>snp-jc</code>, <code>snp-k2p</code>, <code>snp-k81</code>, <code>snp-f81</code>,
<code>snp-t92</code>, <code>snp-tn93</code>, <code>snp-tv</code>, all with <code>+Γ</code> except <code>raw</code>/<code>tv</code></strong> — see <code>snp-t92</code>, <code>snp-tn93</code>, <code>snp-tv</code>, all with <code>+Γ</code> except <code>raw</code>/<code>tv</code></strong> — see
"Exact formulas" below. <code>snp-tajima-nei</code>, <code>snp-f84</code>, <code>snp-hky85</code>, "Exact formulas" below. <code>snp-tajima-nei</code>, <code>snp-f84</code>, <code>snp-hky85</code>,
@@ -4591,6 +4757,430 @@ special-casing K80). K81/T92/TN93's gamma branches follow the same
mechanical substitution but weren't independently checked against an mechanical substitution but weren't independently checked against an
<code>ape</code>-equivalent reference for those three specifically — flagged here, not <code>ape</code>-equivalent reference for those three specifically — flagged here, not
silently assumed correct.</p> silently assumed correct.</p>
<h3 id="-estimation-literature-survey-and-design-discussion-2026-09-11">α-estimation literature survey and design discussion (2026-09-11)</h3>
<p>Follow-up discussion after implementing <code>PartitionDispersion::estimate_alpha</code>
(previous section), triggered by the user pointing out that the literature
conflates two distinct problems: <em>estimating α from an alignment</em> versus
<em>using a given α in a Jin-Nei-style corrected distance</em>. Jin &amp; Nei (1990)
itself is squarely in the second camp — α is a user-supplied parameter
there, not something their paper estimates (confirmed by reading the paper
directly, see previous section). This section catalogs the actual
α-estimation literature and records which approaches were considered and
why each was or wasn't adopted.</p>
<p><strong>Bibliography</strong> (methodological papers, not exhaustive users of <code>+Γ</code>):</p>
<table>
<thead>
<tr>
<th>Method</th>
<th>Reference</th>
<th>Needs a tree?</th>
<th>Estimates "true" α or a task-specific one?</th>
<th>Cost</th>
</tr>
</thead>
<tbody>
<tr>
<td>ML, continuous Γ (foundational)</td>
<td><strong>Gu, Fu &amp; Li (1995)</strong>, MBE 12:546–557 — read in full</td>
<td>yes, topology fixed a priori</td>
<td>true α (+ θ jointly, invariant+Γ)</td>
<td>very high, ≤5–6 taxa in practice</td>
</tr>
<tr>
<td>ML, discrete Γ</td>
<td>Yang (1993/94), MBE 10:1396; JME 39:306</td>
<td>yes</td>
<td>true α</td>
<td>high</td>
</tr>
<tr>
<td>Parsimony-based ML on inferred changes</td>
<td>Yang &amp; Kumar (1996), MBE 13:650</td>
<td>yes, equal branch lengths assumed</td>
<td>true α, biased when branches unequal</td>
<td>low</td>
</tr>
<tr>
<td>Corrected substitutions/site → NB fit</td>
<td><strong>Gu &amp; Zhang (1997)</strong>, MBE 14:1106 — read in full</td>
<td>yes, + ancestral reconstruction</td>
<td>true α, close to ML accuracy</td>
<td>low (given a tree)</td>
</tr>
<tr>
<td>Topology-optimizing grid search</td>
<td><strong>Guindon &amp; Gascuel (2002)</strong>, MBE 19:534 — read in full</td>
<td>yes, but built <em>from</em> the candidate distances themselves (BIONJ)</td>
<td><strong>not</strong> true α — deliberately biased <em>upward</em> for topological accuracy</td>
<td>low–moderate (grid × tree build)</td>
</tr>
<tr>
<td>Free (non-parametric) rate distribution</td>
<td>Susko et al. (2003), Syst. Biol. 52:594</td>
<td>yes</td>
<td>tests the Γ assumption itself</td>
<td>high</td>
</tr>
<tr>
<td>Parsimony counts/site → NB fit</td>
<td><strong>Wakeley (1993)</strong>, JME 37:613 — read in full</td>
<td>yes, NJ tree + Fitch parsimony ancestral reconstruction</td>
<td>true α, biased <em>upward</em> by parsimony (conservative)</td>
<td>low (given a tree)</td>
</tr>
<tr>
<td>Poisson-Gamma/negative-binomial, foundational</td>
<td>Uzzell &amp; Corbin (1971), Science 172:1089 — <strong>not read</strong>, only seen via citations</td>
<td>unknown — likely also count-per-site/tree-based, unverified</td>
<td>true α (indirect, via NB overdispersion)</td>
<td>unknown</td>
</tr>
<tr>
<td>Bayesian posterior over α</td>
<td>BPP/MrBayes/BEAST2/RevBayes</td>
<td>yes</td>
<td>posterior, not point estimate</td>
<td>very high</td>
</tr>
</tbody>
</table>
<p><strong>Correction (2026-09-11, after reading Wakeley in full):</strong> an earlier
revision of this table filed Wakeley (1993) under "no tree needed" —
wrong. Wakeley's method: build a tree (neighbor-joining, Saitou &amp; Nei
1987, on the real mtDNA data; coalescent-simulated for the simulation
study), reconstruct ancestral states at internal nodes by Fitch (1971)
parsimony, count the <em>minimum</em> number of changes per site this implies,
then fit either a two-rate Poisson mixture or a gamma-distributed-rates
model (⟹ negative binomial, parameters by the methods of Cohen 1965 and
Johnson &amp; Kotz 1969) to the resulting per-site count distribution — the
same general "tree + ancestral reconstruction + per-site counts + NB fit"
shape as Gu &amp; Zhang (1997), just using raw parsimony counts directly
rather than Gu &amp; Zhang's multiple-hit-corrected <code>k̂</code>. Confirmed by
simulation (Wakeley's own Fig. 1) that parsimony underestimates both the
mean <em>and</em> (more severely) the variance of per-site change counts, which
biases <code>α</code> <strong>upward</strong> (toward apparent uniformity) — consistent with Gu &amp;
Zhang's own citation of Wakeley for exactly this bias, and with the
general "parsimony overestimates α" pattern noted throughout this
literature. Real hypervariable-region-1 mtDNA data gave <code>α̂ ≈ 0.44–0.60</code>
per data set, <code>0.47</code> combined — despite the conservative bias, still
solidly in the "strong heterogeneity" range, which is the paper's own
point: the method is biased but usefully conservative, not useless.</p>
<p><strong>Where <code>PartitionDispersion::estimate_alpha</code> actually sits</strong>: nowhere in
this table's tree-dependent rows. It shares only the <em>abstract
mathematical identity</em> (Poisson-Gamma mixture ⟹ negative binomial
over-dispersion) with Wakeley/Uzzell-Corbin/Gu&amp;Zhang, applied via a
genuinely different, tree-free and ancestral-reconstruction-free route:
pairwise genome-to-genome substitution counts pooled by <em>partition</em>
instead of per-site counts pooled across an alignment's columns after
ancestral state reconstruction. As far as this survey has established
(Uzzell &amp; Corbin not read, so not fully ruled out), <strong>no tree and no
ancestral reconstruction of any kind</strong> appears to be a genuinely
distinguishing property of <code>PartitionDispersion</code>, not something it
inherits from prior art — consistent with it being an independent
derivation rather than a literature implementation (see previous
section's caveat, now on firmer footing).</p>
<p><strong>Why a tree-free estimate is even valid — the identifiability question.</strong>
Raised directly by the user after reading Gu, Fu &amp; Li (1995), which states
explicitly: <em>"one cannot estimate the rate heterogeneity when the number
of sequences is &lt;3."</em> This is a real non-identifiability result, not a
practical inconvenience: with only 2 sequences, a site's history is
summarized by one binary observation (differ / don't differ), collapsed
across all sites into two aggregate numbers (transition and transversion
proportions) — divergence time and among-site rate variance are
confounded in that pair of numbers, with no way to separate them. Every
method surveyed above (Gu,Fu&amp;Li, Yang, Wakeley, Gu&amp;Zhang) needs ≥3
sequences <em>sharing one evolutionary history</em> (a tree) specifically to get
multiple independent looks at the <em>same</em> site's rate across different
lineages, which is what identifies its variance.</p>
<p><code>PartitionDispersion</code> doesn't violate this, because it isn't estimating
the same quantity. The literature above estimates rate variation <strong>across
sites, within one shared tree</strong>. <code>PartitionDispersion</code> estimates rate
variation <strong>across partitions, pooled over every genome pair in the
index</strong> — each genome pair stands in for one independent draw of a
partition's relative rate, the same identifying role multiple lineages
play in the tree-based methods, just substituting "genome pair" for
"lineage" and "partition" for "site." With <code>P</code> genome pairs (potentially
in the hundreds here) all contributing to every partition's pooled count,
the ≥3-samples identifiability requirement is met by the pair count, not
by tree depth — closer in spirit to Jin &amp; Nei's own original motivating
scenario (comparing several genomic <em>regions</em> across one fixed panel of
taxa) than to single-tree site-rate estimation.</p>
<p>This substitution carries its own assumption, which must be named rather
than left implicit: that a partition's <em>relative</em> rate (fast/slow) is
reasonably stable <strong>across genome pairs</strong>, not just across sites within
one pair — the direct analogue of the "no lineage-specific rate variation,
only site-specific" assumption every tree-based <code>+Γ</code> method already makes,
just moved from lineage→pair and site→partition. If this breaks — e.g. an
index mixing very closely related and very divergent genome pairs, where a
partition's saturation behavior differs qualitatively between the two —
the estimate could be misled in a way a tree-based method would at least
have the topology to detect and a tree-free, pool-everything method
cannot. Not yet tested against real data with strongly heterogeneous
pairwise divergence; worth keeping in mind as the main open validity
question for <code>--gamma-shape auto</code>, not the citation question (now settled)
this whole discussion started from.</p>
<p><strong>Gu, Fu &amp; Li (1995), read in full — the foundational ML method, not a
candidate to implement.</strong> Models rate variation as invariant+Γ (<code>θ</code> =
proportion of invariant sites, <code>α</code> = gamma shape among the variable sites),
and derives the exact joint likelihood over nucleotide <em>configurations</em>
across all <code>n</code> sequences on a <strong>fixed, a-priori-known tree topology</strong> —
for 3 sequences this is closed-form (Jukes-Cantor), for <code>n</code> sequences it's
a sum over <code>4^n</code> configurations weighted by coefficients tied to the
specific topology's branching structure (their eq. 32–34), with branch
lengths, <code>α</code>, and <code>θ</code> jointly optimized by Newton-Raphson (Hessian over all
free parameters). The site-rate integral has the same closed form
<code>E = θ + (1-θ)(1+D/α)^{-α}</code> that underlies <code>+Γ</code> distance corrections
generally (the same mechanism as <code>corrected_log</code>, not a coincidence — Jin &amp;
Nei's own formula is the <code>θ=0</code> special case applied to a pairwise <code>D</code>
rather than a whole-tree one). Explicitly stated by the authors as
infeasible beyond about 5–6 taxa (their own simulations stop at 5); not a
candidate for obikmer's typical genome counts. Notable contribution worth
keeping in mind regardless: <code>ρ = (1+θα)/(1+α)</code> is shown to be a more robust
summary of rate heterogeneity than <code>α</code> alone whenever <code>θ</code> isn't negligible
— <code>α</code> and <code>θ</code> are confounded (nearly-invariant sites can come from either a
small <code>α</code>'s left tail or from a nonzero <code>θ</code>), so <code>α</code> alone can be very
unstable while <code>ρ</code> stays well-behaved. <code>PartitionDispersion</code> has no <code>θ</code>
term at all (no invariant-site component), so this confound doesn't arise
for it the same way, but it's worth remembering if an invariant+Γ variant
is ever considered.</p>
<p><strong>Gu &amp; Zhang (1997), read in full — rejected for now.</strong> Their procedure:
(1) a tree with least-squares branch lengths must already exist; (2)
ancestral states are reconstructed at every internal node (they use Zhang &amp;
Nei 1997's likelihood method, but note plain parsimony would work, just
less accurately); (3) per site, branches are split into "changed"/"unchanged"
given the ancestral reconstruction, and the <em>expected</em> substitution count
<code>k̂</code> (corrected for multiple hits) is obtained by solving their eq. (7)
(or eq. 12 for the generalized model) numerically — a root-find per site,
not a closed form; (4) the site-level <code>k̂</code> values (real-valued, not
integers) are fit to a negative binomial (Uzzell &amp; Corbin 1971) by ML to
get α — again no closed form, numerical optimization. This is a real
per-site pipeline requiring a tree <em>before</em> distances/α can be computed —
the reverse of obikmer's current dependency order (<code>snp_distance</code> computes
distances, which <code>--nj</code>/<code>--upgma</code> only turn into a tree <em>afterward</em>). Their
own answer to this chicken-and-egg problem is an iterative
distance→tree→α→distance loop, which they themselves flag as expensive.
Adopting this would mean a new ancestral-reconstruction subsystem (even a
parsimony/Fitch-only version) plus a per-family nonlinear solve plus an NB
ML fit — a much bigger addition than <code>PartitionDispersion</code>, not something
to build without a concrete need beyond "closer to Gu&amp;Zhang's own
simulated accuracy than our moment estimator."</p>
<p><strong>Guindon &amp; Gascuel (2002), read in full — plausible future addition, not implemented.</strong>
Their <strong>Q criterion</strong>: for a candidate α, build a tree (they use BIONJ) from
the α-corrected distance matrix; for every internal branch, group taxa into
the 4 subtrees it separates (A, B, C, D), compute mean inter-subtree
distances <span class="arithmatex">\(\bar\delta_{AB}\)</span>, <span class="arithmatex">\(\bar\delta_{CD}\)</span>, etc., and let <code>S ≤ M ≤ L</code>
be the three pairings' sums (<code>{AB,CD}</code>, <code>{AC,BD}</code>, <code>{AD,BC}</code>); the branch's
reliability score is <code>Q_branch = L − M</code> (zero when the four points are
perfectly tree-additive). The whole-tree <code>Q</code> is the mean over internal
branches (negative/zero branches excluded). <code>α* = argmin_α Q(α)</code> over a
grid (their run: ~60–100 points, 0.1 to 5000, finer spacing where
sensitivity is highest). Complexity: <code>O(n²l)</code> once for the base
frequencies, then <code>O(n²r)</code> for the <code>r</code> candidate distance matrices, then
<code>O(n³r)</code> worst case for building <code>r</code> trees and evaluating <code>Q</code> on each
(same order as the tree-building step itself, so "free" relative to it).</p>
<p>Central finding, <strong>the opposite direction from an initial misreading in
this discussion</strong>: <code>α_opt</code> (Guindon-Gascuel's topology-optimal value) is
<strong>always ≥ the true α</strong>, not the reverse — underestimating rate
heterogeneity (i.e., picking a larger α than reality) reduces the variance
of distance estimates and thereby improves NJ/BIONJ topological accuracy,
especially when the molecular clock roughly holds (where <code>α_opt → ∞</code>, i.e.
no correction at all is topologically best). This is an <em>empirical
regularity</em> observed across their tested conditions (η ∈ {0.5, 2.0}, true
α ∈ {0.1, 0.7}, 20-taxon trees) — not a theorem — so treating it as a hard
guarantee would be another unverified-claim mistake of the kind this whole
discussion has been correcting.</p>
<p><strong>Proposed integration (not yet implemented)</strong>: since <code>α_true ≤ α_opt</code>
empirically, <code>PartitionDispersion::estimate_alpha()</code>'s output could seed
the <em>lower bound</em> of Guindon-Gascuel's grid (search <code>[α̂, ∞)</code> instead of
<code>[0.1, 5000]</code>), narrowing the grid substantially and reusing the existing
estimator rather than needing an independent "true α" source — this also
sidesteps Gu &amp; Zhang's tree-first dependency problem entirely, since
Guindon-Gascuel's own grid already builds a tree per candidate. Still
requires: (a) a <strong>BIONJ</strong> implementation (see below), (b) the Q-criterion
subtree-grouping logic, (c) a grid-search driver. Not started.</p>
<p><strong>BIONJ availability in the Rust ecosystem — checked 2026-09-11, none found.</strong>
Searched crates.io directly (API query for "bionj": 0 results) and read the
docs.rs pages of the most plausible candidates: <code>phylotree</code> (builds/reads/
manipulates trees but has no distance-matrix reconstruction — no NJ, no
BIONJ, no UPGMA despite web-search summaries claiming otherwise, corrected
after checking the actual docs), <code>speedytree</code> (NJ only — Canonical/RapidNJ/
Hybrid variants, explicitly no BIONJ), <code>nj</code> (plain NJ only), <code>phylo</code> (no
distance-based reconstruction at all). <code>obikphylo::neighbor_joining</code>
(<code>tree.rs</code>) is plain NJ, not BIONJ — BIONJ (Gascuel 1997) differs only in
how branch lengths are weighted during agglomeration (accounts for
distance-estimate variance, not just the sum), a modest delta over an
existing NJ implementation rather than a rewrite, but would need to be
written in-house if the Guindon-Gascuel integration above is ever pursued
(their own paper notes other tree-building methods gave similar results in
their simulations, so plain NJ may be an acceptable substitute if BIONJ
proper is judged not worth the effort).</p>
<h3 id="sharing-one-sample-across-algorithms-sankoff-tnt-phyg-iqtree-snp-distance-implemented-2026-09-11">Sharing one sample across algorithms (<code>--sankoff</code>/<code>--tnt</code>/<code>--phyg</code>/<code>--iqtree</code> + <code>snp-*</code> <code>--distance</code>) — implemented 2026-09-11</h3>
<p><strong>Correctness bug, not just a performance one.</strong> <code>--sankoff</code>/<code>--tnt</code>/<code>--phyg</code>/
<code>--iqtree</code> (via <code>SiblingExt::sankoff_bundle</code>) and a <code>snp-*</code> <code>--distance</code>
(via <code>SiblingExt::snp_distance</code>) always consume the <em>exact same</em> selection
parameters when requested together in one <code>obikmer phylo</code> invocation
(<code>n</code>/<code>free_loss</code>/<code>no_ambiguity</code>/excluded-set/<code>entropy_bias</code> — the CLI has
no way to give them different values in one run, see <code>cmd/phylo/args.rs</code>).
Before this fix, each independently called <code>sample_index</code>, and
<code>sample_layer</code>'s <code>rand::rng()</code> (<code>subsample.rs:235</code>) is a <strong>thread-local
generator that advances across calls, not reseeded each time</strong> — so the
second call silently drew a <em>different</em> random sample of sites than the
first, even with identical parameters. Verified empirically (throwaway
8-genome index): running <code>snp-jc</code> alone vs. combined with <code>--sankoff</code>
produced visibly different distance matrices from the same index/params.
This defeated the actual point of combining these flags — running several
algorithms (Sankoff/TNT/PhyG/IQ-TREE calibration, a <code>snp-*</code> distance) on
one <em>identical</em> site selection for direct comparison.</p>
<p><strong>Fix</strong>: <code>SankoffBundle</code> (<code>sankoff.rs</code>) now retains its <code>PairwiseTally</code>/
<code>PartitionDispersion</code> internally (previously consumed into <code>raw</code>/
<code>base_pair_tally</code>/<code>cardinality_tally</code> and dropped) and exposes
<code>SankoffBundle::snp_distance(kind, gamma_shape)</code>, which computes the
matrix from that <em>same</em> already-sampled tally — no second <code>sample_index</code>
call. The shared post-sampling logic (the <code>--gamma-shape</code> support check,
<code>alpha</code> resolution, final matrix build — previously all inline in the
<code>snp_distance()</code> free function) was factored into
<code>pub(crate) fn distance_matrix(tally, dispersion, kind, gamma_shape)</code> in
<code>snp_distance.rs</code>, called by both the standalone <code>snp_distance()</code> (after
its own fresh sampling) and <code>SankoffBundle::snp_distance</code> (reusing the
bundle's). <code>cmd/phylo/mod.rs</code> keeps the <code>Option&lt;SankoffBundle&gt;</code> alive past
the Sankoff-family <code>if</code> block and, when a <code>snp-*</code> <code>--distance</code> is also
requested, calls <code>bundle.snp_distance(...)</code> instead of
<code>cache.snp_distance(...)</code> whenever a bundle was built — since both branches
are driven by the same <code>args.*</code> fields, the parameters trivially always
match when both fire; no runtime "do the params match" check needed.
Verified end-to-end: the reused path logs <code>(reusing the Sankoff bundle's
sample)</code> and the <code>snp_distance</code> stage timer reads <code>0ms</code> (<code>formula(kind)</code>
is <code>O(n²)</code> post-processing, no I/O), vs. ~150-230ms for a fresh sample on
the same tiny test index.</p>
<h4 id="explicit-session-implemented-2026-09-12">Explicit <code>--session</code> (implemented 2026-09-12)</h4>
<p>The in-process fix above only covered reuse <em>within one command</em>.
<code>--session DIR</code> (<code>cmd/phylo/args.rs</code>) names a directory (outside the
index) that persists the <code>snp-*</code> <code>--distance</code> sample — the
<code>PairwiseTally</code>/<code>PartitionDispersion</code> pair <code>sample_index</code> would otherwise
rebuild from scratch — across <em>separate</em> <code>obikmer phylo</code> invocations.</p>
<p><strong>Crate placement, as planned</strong>: a new <strong><code>obiksession</code></strong> crate
(<code>src/obiksession/</code>), domain-agnostic — no <code>PairwiseTally</code>/"site" concept
anywhere in it. <code>Session::open(dir, params: &amp;[u8], force: bool)</code> handles
directory lifecycle and the params-conflict check against an opaque byte
blob; <code>Session::store(name, bytes)</code>/<code>Session::restore(name) -&gt; Option&lt;Mmap&gt;</code>
handle a checksummed artifact cache. <code>obikphylo</code>
(<code>siblings/algorithms/session_cache.rs</code>, shared by <code>snp_distance.rs</code> and
<code>sankoff.rs</code> — see below) is the consumer: it serializes its own
<code>PairwiseTally</code>/<code>PartitionDispersion</code>/<code>SnpAlignment</code> to bytes (via <code>rkyv</code>)
and hands them to <code>obiksession</code>, which never sees their type.</p>
<p><strong>Serialization</strong>: <code>rkyv</code> 0.8.18, added as planned. One deviation from the
original zero-copy pitch, scoped down deliberately: artifacts are restored
via <code>rkyv::from_bytes</code> (full owned deserialize) rather than <code>rkyv::access</code>
(zero-copy over the <code>mmap</code>). True zero-copy would require every
<code>PairwiseTally</code> query method (<code>categories</code>, <code>base_freq</code>, <code>pair</code>, ...) to
work generically over <code>Archived&lt;PairwiseTally&gt;</code> as well as the owned type
— a separate, larger change not needed to get the actual win (skipping
<code>sample_index</code>'s expensive re-scan of the sibling annex; deserializing an
already-in-memory-sized count array is comparatively cheap CPU, not I/O).
<code>#[derive(Archive, Serialize, Deserialize)]</code> was added to <code>PairStats</code>,
<code>PairwiseTally</code>, and <code>PartitionDispersion</code> (<code>pairwise.rs</code>) for this.</p>
<p><strong>Startup behavior, as designed</strong>: <code>Session::open</code> creates <code>DIR</code> if
missing (fresh, params recorded); if <code>DIR</code> already holds different saved
params, <code>cmd/phylo</code> reports a hard error and exits rather than silently
preferring one side, unless <code>--session-force</code> is given (which discards the
directory's cached artifacts and starts over under the new params) —
implements exactly the "explicit escape hatch, not silent override"
decision from the design discussion. <code>obiksession</code> itself doesn't decode
either side's bytes to produce a field-by-field diff (true to "opaque
blob," left to whoever needs it); <code>cmd/phylo</code>'s conflict message is
currently a single generic sentence listing which flags could be the
cause, not a computed diff — an honest v1 simplification, not a limitation
of <code>obiksession</code> itself.</p>
<p><strong>Per-artifact caching, as designed</strong>: only <code>PairwiseTally</code>/
<code>PartitionDispersion</code> are cached (<code>snp_distance.rs</code>'s <code>restore_tally</code>/
<code>store_tally</code>) — <code>ratio_ceiling</code>/<code>gamma_shape</code> remain pure post-processing
over whatever tally is in hand, cached or fresh, exactly as planned.</p>
<p><strong>Locking, reconsidered and kept as the whole-session <code>DirLock</code>.</strong> First
written up as a corner cut ("per-entry locking was sketched, not
implemented"). On actually working through the concrete race, whole-session
locking turned out to be the <em>correct</em> choice, not a simplification:
<code>--session-force</code> resets a session by deleting its whole <code>artifacts/</code>
directory. If the directory lock were only held briefly (during
<code>Session::open</code>, then released so a long-running <code>Session</code> doesn't block
other processes from touching <em>different</em> artifacts), a second process
calling <code>open(..., force: true)</code> could acquire the lock, see mismatched
params, and wipe <code>artifacts/</code> <strong>while a first process's already-open
<code>Session</code> is mid-checkpoint</strong> — genuine corruption risk, not just wasted
work. Holding the lock for the <code>Session</code>'s entire lifetime makes that
sequence impossible: a <code>force</code> reset must wait for every currently-open
<code>Session</code> on that directory to be dropped first. The concurrency this
gives up (two <em>different</em> processes reading/writing <em>different</em> artifacts
of the same session at once) isn't exercised by anything today — only one
code path (<code>snp_distance</code>/<code>sankoff_bundle</code>, sequentially per invocation)
uses sessions at all.</p>
<p><strong>Per-layer chunked/resumable dumps — implemented.</strong> <code>subsample::sample_index</code>
gained a <code>skip_layers: usize</code> parameter (skip the first N (partition,
layer) pairs, in its own deterministic iteration order, entirely — no
I/O, no <code>on_layer</code> call) and its <code>on_layer</code> callback gained a <code>raw_index</code>
argument (that pair's 0-based position in the same order), so a caller can
tell exactly how far a run has gotten. <code>snp_distance</code>/<code>sankoff_bundle</code>
checkpoint their tally/dispersion (and, for <code>sankoff_bundle</code>, the
in-progress <code>SnpAlignment</code>) to the session every
<code>session_cache::CHECKPOINT_INTERVAL_LAYERS</code> (8) layers or
<code>CHECKPOINT_INTERVAL</code> (30s) of wall time, whichever comes first — bounding
how much completed scanning a crash can lose, without paying a full
tally-rewrite on every one of what can be thousands of layers. A <code>progress</code>
artifact records how many layers are reflected in the checkpoint, with a
<code>PROGRESS_COMPLETE</code> (<code>u64::MAX</code>) sentinel once every layer has been
processed (distinct from any real layer count, so "finished" is never
confused with "stopped after N layers where N happens to equal the total").</p>
<p>Verified with a real kill: built a 10-genome/64-partition index, ran
<code>--distance snp-jc --session DIR</code> under <code>timeout 0.4</code>, confirmed a
checkpoint at <code>progress=8</code> (exactly <code>CHECKPOINT_INTERVAL_LAYERS</code>) was on
disk, then re-ran the same command and confirmed it resumed from layer 8
and completed successfully — 0-effort verification that the mechanism
itself is real, not just plausible-sounding.</p>
<p><strong>Important correction from that same test — resume is <em>not</em> bit-reproducible,
and shouldn't be.</strong> The output matrix from the resumed run differed from
an uninterrupted control run against the same index/params. Root cause:
<code>sample_layer</code>'s random draws come from <code>rand::rng()</code>, a per-process,
OS-seeded generator with no continuity across a process boundary — the
layers processed before a kill and the layers processed after a resume
come from two independent random streams. An earlier revision of this doc
(and of the code comments) claimed resume "reproduces the exact same
sample an uninterrupted run would have" — that's wrong, and was corrected
after the user pointed out the actual reasoning error: true randomness has
no notion of continuity in the first place, so there was never a
correctness requirement for a resumed run to match an uninterrupted one
bit-for-bit. The sample produced after a resume is exactly as legitimate a
random draw as one from an uninterrupted run — just a <em>different</em> one,
same as running the command twice without <code>--session</code> already gives two
different samples today. That variance is explicitly wanted (see below),
not a defect to fix. Comments in <code>subsample.rs</code>/<code>session_cache.rs</code> were
corrected to state this plainly instead of the false reproducibility claim.</p>
<p><strong>Explicitly declined: deterministic/seeded sampling.</strong> Raised as a
possible fix for the above (seed <code>sample_layer</code>'s RNG from a per-session
value plus <code>(partition, layer)</code>, making a resume reproduce bit-identical
results, and, if applied everywhere, making <em>any</em> two runs with identical
parameters produce identical samples). The user explicitly declined this
for now: repeated runs are relied on to measure sampling variance, and a
<code>--seed</code> flag would need its own explicit design if wanted later — this is
not an accidental gap, it's a stated preference to revisit only if asked.</p>
<p><strong><code>SankoffBundle</code> integration — implemented.</strong> <code>sankoff_bundle</code> accepts
the same <code>session: Option&lt;&amp;Session&gt;</code> and uses the <em>same</em> artifact names
(<code>session_cache::{TALLY_ARTIFACT, DISPERSION_ARTIFACT, PROGRESS_ARTIFACT}</code>)
as <code>snp_distance</code>, plus its own <code>ALIGNMENT_ARTIFACT</code> (<code>sankoff.rs</code>) folded
in lockstep with the tally at every checkpoint (same <code>on_layer</code> call
produces both, so they can never drift out of sync). Consequence verified
directly: a tally checkpointed by <code>--sankoff --session DIR</code> is restored by
a <em>later, separate</em> <code>--distance snp-k2p --session DIR</code> invocation with no
<code>--sankoff</code> at all, and vice versa — cross-consumer reuse, not just
same-command reuse, exactly the synergy this design aimed for.</p>
<p><strong>Per-artifact caching, as designed</strong>: only the tally/dispersion (plus,
for <code>sankoff_bundle</code>, the alignment) are cached — <code>ratio_ceiling</code>/
<code>gamma_shape</code> remain pure post-processing over whatever tally is in hand,
cached or fresh, exactly as planned.</p>
<p><strong>Still not done — genuine follow-up, not a justified tradeoff:</strong>
<strong>exhaustive-sample caching for <code>--subsample</code>-varying exploration.</strong> The
design discussion's suggestion — cache the exhaustive (<code>n = None</code>) sample
once and subsample <em>from</em> it on each run instead of one session per exact
<code>n</code> — wasn't implemented; a session today is still scoped to one exact
parameter tuple, <code>--subsample</code> included.</p>
<h3 id="output-format-phylip-relaxed-by-default-for-the-distance-matrix">Output format: PHYLIP-relaxed by default for the distance matrix</h3> <h3 id="output-format-phylip-relaxed-by-default-for-the-distance-matrix">Output format: PHYLIP-relaxed by default for the distance matrix</h3>
<p><strong>Implemented.</strong> The primary distance-matrix output <p><strong>Implemented.</strong> The primary distance-matrix output
(<code>_dist.csv</code> today) gains multiple formats: <strong>PHYLIP-relaxed becomes the (<code>_dist.csv</code> today) gains multiple formats: <strong>PHYLIP-relaxed becomes the
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1199,7 +1199,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1124,7 +1124,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
+1 -1
View File
@@ -1243,7 +1243,7 @@
<span class="md-ellipsis"> <span class="md-ellipsis">
Sibling annex (discussion) Sibling annex
File diff suppressed because it is too large. Load diff
@@ -12,8 +12,9 @@ this pipeline.
by `verify_presence`/`verify_merge_presence`, which only check index by `verify_presence`/`verify_merge_presence`, which only check index
*content* against the `.npz` truth, never the query API. *content* against the `.npz` truth, never the query API.
- `pack --sparse` produces a presence-matrix format documented (see - `pack --sparse` produces a presence-matrix format documented (see
[siblings.md](../architecture/siblings.md)) as faster for single-row [obicompactvec.md](obicompactvec.md), "Sparse matrix formats") as faster
access (query) and slower for column-oriented access (phylo `--metric`). for single-row access (query) and slower for column-oriented access
(phylo `--metric`).
`global_index_presence/` built by `merge_presence.sh` is always packed `global_index_presence/` built by `merge_presence.sh` is always packed
dense (packing is a stage inside `merge`, not a separate `pack` dense (packing is a stage inside `merge`, not a separate `pack`
invocation) — there was no dense/sparse regression check. invocation) — there was no dense/sparse regression check.
+1 -1
View File
@@ -299,7 +299,7 @@ pub fn sub_matrix(&self, slots: &[usize]) -> Vec<Vec<bool>>
pub fn fill_sub_matrix(&self, slots: &[usize], out: &mut [Vec<bool>]) pub fn fill_sub_matrix(&self, slots: &[usize], out: &mut [Vec<bool>])
``` ```
Column-first to match the on-disk column-major layout. `fill_sub_matrix` sorts `slots` once, then calls each column's `fill_batch` in turn — no redundant per-column sort. On `PersistentSparseBitMatrix` (k-mer-major, no column method) this degrades to a row-by-row decode; see [siblings.md](../architecture/siblings.md). Column-first to match the on-disk column-major layout. `fill_sub_matrix` sorts `slots` once, then calls each column's `fill_batch` in turn — no redundant per-column sort. On `PersistentSparseBitMatrix` (k-mer-major, no column method) this goes through `nonzero_iter` instead, decoding one row at a time; see [obicompactvec.md](obicompactvec.md), "Sparse matrix formats".
--- ---
+158 -3
View File
@@ -298,13 +298,11 @@ Both matrix types are enums behind a transparent API — the caller never matche
|---|---|---| |---|---|---|
| `Columnar` | one `.pbiv`/`.pciv` file per column + `meta.json` | build-time default (`*Builder::new`) | | `Columnar` | one `.pbiv`/`.pciv` file per column + `meta.json` | build-time default (`*Builder::new`) |
| `Packed` | single `matrix.pbmx`/`matrix.pcmx` mmap file | query-optimised, produced by `pack_bit_matrix`/`pack_compact_int_matrix` | | `Packed` | single `matrix.pbmx`/`matrix.pcmx` mmap file | query-optimised, produced by `pack_bit_matrix`/`pack_compact_int_matrix` |
| `Sparse` | bit: `sparse_meta.json` + PFIV/Elias-Fano component files, row-major. Int: same support files (built on `PersistentSparseBitMatrix` internally) plus `singleton_values.pciv`/`multi_values.pciv`/`multi_offsets` for the per-row, non-deduplicated values | `pack --sparse`; see [siblings.md](../architecture/siblings.md) for the sparse-vs-dense access-pattern trade-off | | `Sparse` | bit: `sparse_meta.json` + PFIV/Elias-Fano component files, row-major. Int: same support files (built on `PersistentSparseBitMatrix` internally) plus `singleton_values.pciv`/`multi_values.pciv`/`multi_offsets` for the per-row, non-deduplicated values | `pack --sparse`; see "Sparse matrix formats" below for the sparse-vs-dense access-pattern trade-off |
| `Implicit` (bit only) | no file at all | mono-genome presence layers — `n_cols` is always reported as `1`, every value is `true` | | `Implicit` (bit only) | no file at all | mono-genome presence layers — `n_cols` is always reported as `1`, every value is `true` |
`PersistentBitMatrix::open(layer_dir)` auto-detects the variant, in order: `matrix.pbmx` → Packed, `presence/meta.json` → Columnar, `presence/sparse_meta.json` → Sparse, `layer_meta.json` (no presence dir at all) → Implicit. `PersistentCompactIntMatrix::open(layer_dir)` mirrors the same priority order minus `Implicit` (there's no implicit count matrix — counts always have at least one on-disk column): `matrix.pcmx` → Packed, `counts/meta.json` → Columnar, `counts/singleton_values.pciv` → Sparse. `col_view`/`col`/`sub_matrix` panic on `Sparse`/`Implicit` where the operation has no direct-slice equivalent (Sparse is k-mer-major, not column-major; Implicit has no backing storage) — callers needing per-column data on those variants go through `row`/`fill_row`. `PersistentBitMatrix::open(layer_dir)` auto-detects the variant, in order: `matrix.pbmx` → Packed, `presence/meta.json` → Columnar, `presence/sparse_meta.json` → Sparse, `layer_meta.json` (no presence dir at all) → Implicit. `PersistentCompactIntMatrix::open(layer_dir)` mirrors the same priority order minus `Implicit` (there's no implicit count matrix — counts always have at least one on-disk column): `matrix.pcmx` → Packed, `counts/meta.json` → Columnar, `counts/singleton_values.pciv` → Sparse. `col_view`/`col`/`sub_matrix` panic on `Sparse`/`Implicit` where the operation has no direct-slice equivalent (Sparse is k-mer-major, not column-major; Implicit has no backing storage) — callers needing per-column data on those variants go through `row`/`fill_row`.
Unlike the bit side, `PersistentSparseCompactIntMatrix`'s values are *not* deduplicated across rows — two rows can share the same non-zero column set (same `dict_id` in the shared support) while carrying different counts — so its `CountPartials` impl can't reuse the support's dict-multiplicity shortcut the way `BitPartials for PersistentSparseBitMatrix` does. It still avoids the naive `O(n_cols² × n)` column-pair scan via a single row-major pass (`row_major_pairwise` in `sparse_intmatrix.rs`), reconstructing the squared-difference formulas (`euclidean`/`relfreq_euclidean`/`hellinger`) from per-column marginals via `Σ(a-b)² = Σa²+Σb²-2Σab` — see [siblings.md](../architecture/siblings.md)'s "`PersistentCompactIntMatrix::Sparse` — implemented" entry for the full derivation.
`col_view(c)` returns the appropriate view directly: `col_view(c)` returns the appropriate view directly:
```rust ```rust
@@ -321,6 +319,163 @@ No wrapper enums (`BitColView`, `IntColView`): the caller receives a `Copy` view
--- ---
## Sparse matrix formats
Motivated by real k-mer-family data being extremely row-sparse (most rows —
k-mers — present in only a handful of genome columns out of dozens to
thousands): a row-major, deduplicated alternative to the dense column-major
formats above, built once per layer like the rest of the pipeline (never the
whole multi-billion-row index at once). Implements the exact-duplicate
special case of Alanko, Bille, Gørtz, Navarro, Puglisi, "Compact Data
Structures for Collections of Sets" (2025,
`biblio/Alanko et al. - Compact Data Structures for Collections of
Sets.pdf`) — a plain dedup dictionary, not their full subset-containment
hierarchy.
### `PersistentSparseBitMatrix`
Four mmap-backed on-disk components: an `is_multi` rank-capable flag per row
(singleton vs. multi-genome), a fixed-bit-width array for singleton rows
(genome index directly, `ceil(log2(n_cols))` bits), a separate fixed-width
array for multi-genome rows (`dict_id`, `ceil(log2(n_distinct_multi_sets))`
bits — kept apart from the singleton array because `n_distinct_multi_sets`
can be large in absolute terms even when multi-genome rows are a small
*fraction* of all rows, and a shared array would force every row, singletons
included, to pay the wider width), and a deduplicated dictionary of distinct
multi-genome sets (Elias-Fano-encoded byte offsets + a varint-encoded values
blob). Supporting primitives: `PersistentFixedIntVec` (arbitrary,
runtime-parameterised bit width, width `0` included — needed once an
`EliasFano` reopen bug surfaced, see below), `PersistentRankSelectBitVec`
(rank1/rank0/select1 on top of the crate's existing `count_ones`, via
`common_traits::SelectInWord`), `EliasFano` (composes the two). `BinaryMatrix`
(`n`, `n_cols`, `row`/`fill_row`, `fill_sub_matrix`, `count_ones`) is the
trait unifying dense and sparse at the call sites that need both
interchangeably; column-oriented methods (`col`, `col_view`, the
`partial_*_dist_matrix` family) stay dense-only — `Sparse`/`Implicit` panic
there (see the `PersistentBitMatrix::open` note above).
Measured on real data (one layer, 30.2M rows, 91 genomes):
| | dense | sparse | ratio |
|---|---|---|---|
| on-disk size | 328.1MB | 43.7MB | **7.5x** smaller |
| build time / peak RSS | — | 4.26s / 628MB | per-layer, in-memory construction |
| row access, sequential (2M reads) | 43ns/row | 32ns/row | sparse faster (smaller structure, better cache fit) |
| row access, random (2M reads) | 409ns/row | 85ns/row | sparse **~4.8x faster** — the `--shannon`/family-lookup access shape |
| column access, one full column (30.2M rows) | 11.5ms | 993ms | sparse **86x slower** — no native column method, every read decodes a full row to keep one bit |
The row-access wins (compactness was the stated design goal, not speed) come
from dense's genome-major layout scattering a single row read across a much
bigger file — costlier than sparse's rank/select/varint decode once the file
is this much smaller. Column access is the flip side of the same layout
choice; `nonzero_iter` (below) is what removes it from the hot path that
actually matters (`query`).
Two reopen-correctness bugs, now fixed at the source: (1) `EliasFano::open`
re-derived its low-bits width from the persisted low-vector's own width
byte; the width-`0` case was built with a dummy 1-bit placeholder (the
builder used to reject true width `0`), silently doubling every reopened
value. Fixed by making `PersistentFixedIntVec` genuinely support width `0`
(no storage, `get` always `0`). (2) An empty row (cardinality 0) used to be
recorded as a singleton at genome `0`, indistinguishable on read-back from a
*real* singleton at genome `0`. Fixed by routing cardinality-0 rows through
the dictionary path (a genuine empty entry).
Still deferred: full Alanko et al. subset-hierarchy compression (only the
exact-duplicate case is built), a sparse `PersistentCompactIntMatrix`
variant beyond what's described below, BRWT-style column-correlation
exploitation, and a row-major rewrite of
`partial_jaccard_dist_matrix`/`partial_hamming_dist_matrix`/etc. as a
per-row co-occurrence accumulation (`O(Σ_rows k̄²)`) so `obikindex`'s
`--metric` distance-matrix path stops paying the column-access penalty on
`Sparse` — needs its own design pass (how it plugs into
`BitPartials`/`ColumnWeights` so both matrix types keep serving `--metric`),
not just "port the loop".
### `nonzero_iter` — the one traversal per format
`fn nonzero_iter<'a>(&'a self, slots: &'a [usize]) -> Box<dyn Iterator<Item = (usize, usize, u32)> + 'a>`
(item: index into `slots`, column, value) is the single foundational
per-format traversal primitive every consumer builds on — `fill_sub_matrix`
and a `for_each`-style callback are both trivial, free consumers of it
(`.for_each(f)` is `Iterator::for_each`; `fill_sub_matrix` drains the
iterator and scatters into `out[][]`), instead of two independently
hand-maintained traversals that can silently diverge. `Box<dyn Iterator>`,
not a bare `impl Iterator`: `Columnar`/`Packed`/`Sparse`/`Implicit` are
genuinely different concrete types and the method isn't on a
dyn-compatible trait (`BinaryMatrix` is used as `dyn BinaryMatrix`
elsewhere, and RPITIT methods aren't dyn-compatible) — one `Box` per
`nonzero_iter` call, not per cell.
Per-format implementation: `PersistentSparseBitMatrix` decodes natively,
buffered one row at a time (`std::iter::from_fn` over the existing
`for_each_genome_in_row`, no `n_cols`-wide allocation ever). `Columnar`/
`Packed` loop columns, collecting each column's hits via
`BitSliceView::nonzero_among_sorted`/`IntSliceView::nonzero_among_sorted`
(a `filter`/`filter_map` over the vector-level `get()`, no new state
machine — `std`'s own `Filter` iterator already is one) into one `Vec` via
`.extend()` (not `flat_map`: a `flat_map` closure can't lazily return
something borrowing its own captured sort permutation across separate calls
without either boxing per-column or fighting the borrow checker — eager
collection sidesteps it at zero extra cost, since `fill_sub_matrix` already
fully materialises anyway). `Implicit` is trivial (`slots.iter().map(|&i| (i, 0, 1))`).
This closed a real dispatch bug by construction, not by patching it:
`PersistentBitMatrix::fill_sub_matrix`/`sub_matrix` used to reimplement a
naive per-`(column, slot)` loop instead of delegating to
`PersistentSparseBitMatrix`'s own efficient native method for `Self::Sparse`
— two hand-written traversals for the same format, free to drift apart, and
they had (`obikphylo`'s own cache layer had independently built a parallel
enum wrapper that *did* dispatch correctly, evidence the bug was worked
around rather than fixed at the source). With `fill_sub_matrix`/`sub_matrix`
rewritten to drain `nonzero_iter`, there is only one traversal per format
left to get right. `KmerPartition::query_partition_with`
(`obikindex/src/partition/query_layer.rs`) — previously column-major
(`for g { for slot { col_value } }`, which for `Sparse` rebuilt a full row
per single cell touched, O(hits × n_cols) instead of O(hits) — the original
motivation for this primitive) — now issues one `layer.nonzero_iter(&slot_list)`
call per layer, format-agnostic. Dense/sparse query performance parity
confirmed on real data (previously sparse 30-50% slower than dense,
reproducibly; now within ~1-3% either way — noise level).
### `PersistentSparseCompactIntMatrix`
The count-matrix analogue, built on `PersistentSparseBitMatrix` as its
"which columns are non-zero" support, values **not** deduplicated (unlike
the bit side, two rows can share the same non-zero column set — same
`dict_id` — while carrying different counts, so the dict-multiplicity
shortcut `BitPartials for PersistentSparseBitMatrix` uses doesn't carry
over). `CountPartials` here: a single row-major pass (`row_major_pairwise`
in `sparse_intmatrix.rs`, decodes each row once via
`for_each_cell_in_row`, nests over that row's own co-present columns) —
`O(Σ k̄²)` over populated rows, avoiding the naive `O(n_cols² × n)`
column-pair rescan. `min(a,b)`-based kernels (`bray`, `relfreq_bray`) need
no correction — they vanish when either side is absent. `a·b` and `√(a·b)`
kernels (`euclidean`/`relfreq_euclidean`/`hellinger`) do need one, since
`(a-0)² = a² ≠ 0` unlike the `min`-based formulas — reconstructed from
per-column marginals via `Σ(a-b)² = Σa²+Σb²-2Σab`.
`threshold_jaccard(1)` shortcuts to `BitPartials::partial_jaccard`
(threshold 1 is exactly presence); `threshold_jaccard(0)` is closed-form
(every `u32` is `≥ 0`).
Wiring the `threshold==1` shortcut surfaced two pre-existing formula bugs in
`BitPartials for PersistentSparseBitMatrix` (present since that type's own
introduction, never caught because no test had compared `Sparse`'s raw
`partial_*` output against dense on real data — only the diagonal-blind
`jaccard_dist_matrix`/`hamming_dist_matrix` finalisations were tested),
fixed at the source:
1. `partial_jaccard`'s diagonal used to be `(0, 2×col_weights[i])` instead
of a genuine self-comparison `(col_weights[i], col_weights[i])` —
`col_weights_and_pair_counts`'s `inter` never pairs a column with itself
by construction, so the diagonal needs its own case.
2. `partial_hamming`'s off-diagonal formula itself was wrong: it computed
`total - union` (rows where *neither* column is present) instead of the
actual Hamming distance `col_weights[i] + col_weights[j] - 2×inter[i,j]`
(symmetric-difference size) — the two only coincide when
`col_weights[i] + col_weights[j] == total`, which small/synthetic test
data can easily satisfy by accident.
## Aggregation traits (matrix level) ## Aggregation traits (matrix level)
### ColumnWeights ### ColumnWeights
+69
View File
@@ -0,0 +1,69 @@
# Chance sharing of a kmer across genomes (discussion)
Null model for "a kmer is present in $r$ of $S$ genomes": how likely is this by chance alone? Extends the single-pair estimate $P_{\mathrm{chance}}\simeq G/4^k$ (see user doc, *K-mer specificity*).
## Homogeneous case: binomial tail
If every genome has the same per-genome chance probability $p$, the number $R$ of genomes containing a given kmer is $\mathrm{Bin}(S,p)$:
$$P(R\geq r)=\sum_{j=r}^{S}\binom{S}{j}p^j(1-p)^{S-j}=I_p(r,\,S-r+1)$$
where $I_p$ is the regularized incomplete beta function. No elementary closed form; use $I_p$ directly.
### Numerical evaluation of the sum
- Term recurrence, one `lgamma` start: $t_{j+1}=t_j\cdot\frac{S-j}{j+1}\cdot\frac{p}{1-p}$.
- Sum the tail **not containing the mode** ($Sp$, not $S/2$). If $r>Sp$, sum $\sum_{j\ge r}$ directly and stop when terms are negligible. The complement $1-\sum_{j=0}^{r-1}$ (note: from $j=0$) suffers catastrophic cancellation when the p-value is tiny.
- Large $S$: normal approximation with continuity correction, or Poisson($Sp$) when $p$ is small. Unreliable in extreme tails.
## Heterogeneous case: $p_i = f(G_i)$
The $G_i$ (number of kmers of genome $i$) are known and differ. With $p_i\simeq G_i/4^k$, the indicators "kmer present in genome $i$ by chance" are independent Bernoulli($p_i$), so $R$ follows a **Poisson-binomial** law, not a binomial:
$$P(R=j)=\sum_{|A|=j}\prod_{i\in A}p_i\prod_{i\notin A}(1-p_i).$$
Everything lives in canonical space: $G_i$ is the number of distinct canonical kmers of genome $i$, and the kmer space has size
$$N=\frac{4^k}{2}$$
exactly, since $k$ is odd (no kmer equals its own reverse complement, so canonicalization pairs the $4^k$ kmers perfectly). Exact per-genome probability: $p_i=1-(1-1/N)^{G_i}\simeq 2G_i/4^k$. This is twice the $G/4^k$ of the user doc, where $G$ is a number of positions on one strand.
### Exact computation
Dynamic programming over genomes, $d_j$ = probability of $j$ hits so far:
$$d'_j=d_j(1-p_i)+d_{j-1}p_i.$$
For the upper tail only $d_0\ldots d_{r-1}$ are needed: $P(R\ge r)=1-\sum_{j<r}d_j$, cost $O(S\,r)$, per distinct $(p_1..p_S)$ vector — independent of the kmer, so computed once per index (table of $P(R\ge r)$ for $r=1..S$), not per kmer. Cancellation caveat as above: for tiny tails compute $\Pr(R\ge r)$ by the DP on the upper side (track $d_j$ for $j\ge r$ only from a top-down recurrence) or in log space. Alternative: DFT of the characteristic function (Hong 2013), $O(S^2)$ exact.
### Approximations
- **Poisson**: $R\approx\mathrm{Poisson}(\lambda=\sum_i p_i)$ with total variation error $\le\sum_i p_i^2$ (Le Cam). Excellent when all $p_i\ll1$, i.e. $4^k\gg G_i$ (large $k$).
- **Binomial with mean $\bar p=\frac1S\sum_i p_i$**: Hoeffding (1956) shows the Poisson-binomial is more concentrated than $\mathrm{Bin}(S,\bar p)$. Hence for $r\ge S\bar p+1$, $P_{\mathrm{PB}}(R\ge r)\le P_{\mathrm{Bin}}(R\ge r)$: using the mean $\bar G$ overestimates the chance probability, i.e. is **conservative** in the upper tail. Wrong direction for $r\le S\bar p$ (lower tail), irrelevant for significance testing.
Consequence: assuming a common $G$ is safe (conservative) if $G=\bar G$ (arithmetic mean), but loses power when genome sizes span orders of magnitude; the exact DP is cheap enough (once per index) to make the approximation unnecessary. Small genomes with $k=11$ saturate ($p_i\to1$) and break the Poisson approximation, not the DP.
## Open points
- Repeats are not a problem. The model is presence/absence per genome, so copy number within a genome is irrelevant, and $G_i$ is the number of **distinct** kmers of genome $i$. A repeat shared between genomes is paralogy, i.e. homology: a true positive, not a false one. Low-complexity kmers (which would share by composition, not descent) are removed upstream by the [entropy filter](entropy.md).
- Residual violation of the equiprobability behind $p_i$: nucleotide composition bias (see Karlin–Ost in the user doc).
- Test dependence between overlapping kmers (see FDR section).
## Goal: an FDR of homology
$H_0$: the $S$ genomes are unrelated (independent random sequences of sizes $G_i$). Rejecting $H_0$ for a kmer, i.e. sharing that chance cannot explain, is the evidence of homology. The quantity wanted is the false discovery rate of the call "shared kmer $\Rightarrow$ homologous".
### Empirical FDR from the count histogram
Let $N$ be the size of the kmer space and $n_{\ge r}$ the observed number of distinct kmers present in at least $r$ genomes (a by-product of the index). Under $H_0$ the expected number of kmers with $R\ge r$ over the whole space is exactly $N\,P(R\ge r)$, with $P$ the Poisson-binomial tail above. Hence
$$\widehat{\mathrm{FDR}}(r)=\min\!\left(1,\ \frac{N\,P(R\ge r)}{n_{\ge r}}\right).$$
- No per-kmer multiple-testing correction: the number of tests ($N$) is already in the numerator.
- Conservative: the observed $n_{\ge r}$ mixes true homology and chance, and the true-null proportion $\pi_0\le1$ is taken as $1$ (Storey-type upper bound).
- Take the smallest $r$ with $\widehat{\mathrm{FDR}}(r)\le\alpha$ as the sharing threshold.
- Equivalent per-kmer view: BH on $p=P(R\ge r)$ with $N$ tests. The zero-truncation matters if one tests only kmers present in the index ($R\ge1$ by selection): use $P(R\ge r)/P(R\ge1)$, not $P(R\ge r)$, otherwise the test is too conservative by a factor $\sim1/\lambda$.
### Dependence
Kmers of one shared region overlap and are not independent tests. The FDR above holds per kmer; for a per-region FDR, count regions (unitigs / super-kmers, with the appropriate clumping of $N$ and $n_{\ge r}$) rather than kmers. Not settled.
+286
View File
@@ -0,0 +1,286 @@
# Pair-coverage-biased family sampling (discussion, 2026-10-07)
Idea: bias the family sample used by `--pseudo-alignment`/`--sankoff`/`snp-*` so that the `family_overlap` matrix of the *sample* is as uniform as possible, compensating the scarcity of shared families between distant species. Complements, does not replace, the existing proportional-by-partition and entropy-biased draws (see user doc, *Sampling design*).
## Motivation: observed on Primulaceae (180 genomes)
Scatter of patristic distance (IQ-TREE on the pseudo-alignment) vs. normalized `family_overlap` shows three pair classes:
- close intra-genus pairs: high overlap, well resolved;
- inter-genus plus distant intra-genus pairs: overlap collapses by ~2 orders of magnitude, one large noisy cloud;
- a small low-overlap cluster at the largest distances, plausibly a few poorly sequenced genomes (user hypothesis, unverified; the tree shows one tip, `Androsace_saussurei--PHA010690`, with a 2.9 terminal branch).
Uniform family draw reproduces this imbalance in the pseudo-alignment: distant pairs share few informative columns, close pairs many. The tree quality for deep splits is then limited by sampled-column count on those pairs, not by the total number of families.
## What defines a target
A family $f$ is carried by a genome set $S_f$ and contributes to every pair in $S_f \times S_f$. For a sample $\mathcal{F}$ with inclusion probabilities $\pi_f$, the expected sample overlap of pair $(i,j)$ is
$$\mathbb{E}[O^{\mathcal{F}}_{ij}] = \sum_{f:\, i,j\in S_f} \pi_f$$
The goal is a $\pi$ making this approximately constant over pairs. The full-index $O_{ij}$ (already computed by `--family-overlap`) is the pool size per pair; $\min_{ij} O_{ij}$ is a hard ceiling on the flat level reachable.
## Nesting hypothesis (user, unverified)
Families covering the poorest pairs also cover the richest ones: absent genome-skimming sampling bias (locus dropout), a family conserved across distant species is not expected to be missing between closer ones. If it holds, $S_f$ is approximately a clade closure and the family pool is nested by pair distance, which changes the design:
- no sequential/stateful draw needed: a family's weight depends only on its own reach (farthest pair covered, or equivalently its coverage of the poorest pairs), computable in one pass;
- flattening reduces to a monotone reweighting by reach: keep (nearly) all long-reach families, thin the short-reach ones, until the sample overlap of close pairs drops to the level of distant ones.
My earlier remark that the weight is stateful (depends on what other families already covered) holds only without nesting.
## Measuring nesting: `scripts/pseudo_alignment_nesting.py`
Works on a pseudo-alignment FASTA plus the IQ-TREE treefile (columns = families; a call is any character other than `-`/`?`). Outputs the sample's `family_overlap` matrix and, per clade-size stratum, the *completeness* $|S_f|/|C(S_f)|$ where $C(S_f)$ is the smallest clade containing $S_f$. Tree rooted as written in the Newick unless `--outgroup`. Uses the already-existing families × genomes presence structure only; no `S_f` is stored (clade of a column = LCA of its first and last carrier in DFS leaf order, precomputed 180×180 matrix).
### Result, Primulaceae pseudo-alignment (180 genomes, 5.0 M columns, uniform draw, root as written)
| Clade size | Families | Mean completeness | Clade-closed |
|---|---|---|---|
| 2 | 145 047 | 1.00 | 100 % |
| 3-4 | 272 918 | 0.71 | 20 % |
| 5-8 | 503 114 | 0.45 | 0.6 % |
| 9-16 | 637 896 | 0.35 | 0.1 % |
| 17-32 | 1 656 229 | 0.21 | 0 % |
| 33-64 | 299 632 | 0.18 | 0 % |
| 65-128 | 181 126 | 0.08 | 0 % |
| 129-180 | 1 307 452 | 0.12 | 0 % |
Overall 4.1 % clade-closed, mean completeness 0.275; off-diagonal overlap min 4, median 1 665, max 387 057, CV 1.57. **Strict nesting does not hold on this sample.** Caveats: unrooted tree, so the 129-180 stratum is inflated by families spanning the arbitrary root (rerun with `--outgroup` pending); this is the sample fed to IQ-TREE, not the full index; absence symbols `-`/`?` both count as absent.
### Lift test (`--lift-test`): margin-preserving null
Question: do families covering a rare pair $(A,B)$ also cover an abundant pair $(A,C)$ more often than margins imply? For each $A$, $B$ = its 10 % rarest partners, $C$ = its 10 % most abundant (ranked on pair overlap). Null: curveball swap randomisation of the genome × family matrix (exact row and column sums), re-selecting $B$/$C$ in every replicate with the same procedure. 200 754 sampled columns, 20 null replicates, 5 000 trades between replicates.
| Statistic | Observed | Null |
|---|---|---|
| $T=P(C\mid A,B)=O_{ABC}/O_{AB}$ | 0.559 | 0.498 ± 0.003 (no replicate ≥ observed, p at floor 1/21) |
| $L=\sum n_A O_{ABC}/\sum O_{AB}O_{AC}$ | 1.18 | 1.694 ± 0.004 |
The two statistics disagree, not contradictorily: $T$ above null supports the "positive association beyond margins" statement; $L$ below null says that, relative to $P(C\mid A)$, knowing $B$ adds less than under the null — the observed abundant partners of $A$ are far more abundant than null ones (phylogenetic structure inflates the $L$ denominator). Unverified: mixing of the chain (is 5 000 trades enough? the tiny null sd may reflect correlation), sensitivity to the 10 % threshold and to the 200 k-column subsample.
Combined reading: association exists but is patchy; a reach-only weight is not enough, weighting must be per presence pattern $S_f$.
## Candidate weighting strategy: pair raking (proposal, not implemented)
Goal: inclusion probabilities $\pi_f$ with $\sum_{f\ni i,j}\pi_f\approx c$ for all pairs.
1. First-order weight: $w_f=\sum_{i,j\in S_f}1/O_{ij}$ (draw a pair uniformly, then a family uniformly among those covering it). With the presence matrix $P$ and $R=1/O$, $w=\tfrac12\,\mathrm{rowsum}(P\odot RP)$, one pass in the existing chunked loop, no $S_f$ storage.
2. Iterate (raking/IPF with one multiplier per pair): update $R_{ij}$ from the overlap the current $\pi$ yields, recompute $w_f$; corrects the fact that large families are drawn for many pairs at once. $\pi_f=\min(1,c\,w_f)$, $c$ set to hit the target sample size; independent Poisson draw per family.
3. Control: recompute the sample's `family_overlap` and its CV with the script above.
Pre-conditions: exclude anecdotal genomes first (e.g. `Androsace_saussurei--PHA010690`, terminal branch 2.9), else their tiny $O_{ij}$ dominate $R$. Overlap uniformity is only a proxy: information for a deep split is informative sites across it, not mere co-presence; to be checked on node support of the resulting tree. Unknown: whether long-reach families are rare because conserved-single-copy or because repeats/misassemblies (the latter would be amplified by up-weighting).
## Alternative / complement: site classes with their own models
Analogy with multigene supermatrices: loci differ in rate *and* in taxon occupancy. Families covering rare pairs (long reach, conserved, slow) vs. families covering close pairs only could be two (or a few) site classes, each with its own substitution model / branch-length scale (IQ-TREE partitions; edge-proportional vs edge-linked options to be checked in the manual). Independent of the weighting: sampling fixes scarcity, partitioning fixes rate heterogeneity; with class-specific scales, oversampling a class would not distort that class's branch lengths, removing the need for $1/\pi_f$ reweighting (IQ-TREE support for per-site weights unverified).
Caveats: reach is a continuum, two classes is a simplification and there is no criterion for the cut; class membership is defined from presence patterns, hence correlated with the data the model sees (assignment bias, worst with `?` missing data; magnitude not assessed); partitioning does not fix repeats/misassembly, it only gives them their own rate.
The pseudo-alignment already keeps only variable families, so branch lengths are not substitutions/site anyway (ascertainment bias, handled by `+ASC`, see the constant-column fix section in [evolutionary_distances.md](evolutionary_distances.md)). With partitions the ascertainment correction must be per class: each class excludes a different number of constant sites. Whether the existing fix applies per partition is unchecked.
Literature: see the next section.
## Literature on informative-site selection (2026-10-07; read from search extracts, not full papers)
- **Phylogenetic informativeness.** Townsend 2007 (*Syst. Biol.* 56:222-231) links each site's rate of change to its power to resolve splits at a given depth: invariant sites are useless, saturated sites misleading, with an optimum in between that depends on the age of the split. Implemented online as PhyDesign (requires an ultrametric tree). Relevance: supports an entropy centre $\mu$ that depends on depth (pair distance) rather than a single value; cf. the $\mu(n)$ discussion.
- **Entropy-based trimming.** BMGE (Criscuolo & Gribaldo 2010, *BMC Evol. Biol.* 10:210) computes a per-character entropy-like score weighted by a similarity matrix and removes regions above a threshold. Uses entropy to *discard* over-variable characters, the opposite direction of the Gaussian band here.
- **Saturation / fast sites.** Classical removal methods: Slow-Fast, LQP, TIGER, Observed Variability. Counter-evidence (Tree-of-Life protein datasets, PMC10609509): even the fastest sites carry reliable signal, trimming them can lower accuracy, slow sites recover fewer true bipartitions than the fastest. Argument against penalizing high entropy ($H\ge2$) without checking that those families do not carry the deep signal; domain (conserved proteins) differs from central-position SNPs, transfer unverified.
- **Taxon-coverage theory.** Sanderson, McMahon & Steel 2010 (*BMC Evol. Biol.*, "Phylogenomics with incomplete taxon coverage: the limits to inference") characterise phylogenetically decisive collections of taxon sets via the four-way partition property: when the coverage pattern suffices to determine the tree uniquely irrespective of signal. Formal frame for pair-coverage sampling; applicability at 180 genomes not assessed.
Takeaways to check before weighting: (i) whether high-entropy families are the deep-signal ones (entropy vs carrier count measured, see below; the cross with reach is still open); (ii) depth-dependent entropy centre; (iii) whether a decisiveness criterion can serve as a sufficiency test for the sample's pair coverage.
## Simpler weight: poorest pair of the family (user preference, 2026-10-07)
$w_f=1/\min_{i,j\in S_f}O_{ij}$, $\pi_f=\min(1,c\,w_f)$. Equivalent in spirit to a reach weight but measured on actual overlaps (no tree needed), same $O(|S_f|^2)$ cost per family as the sum form. Limit: it ignores that large families also feed already-abundant pairs; flattening from above then relies only on dropping short-reach families, which is exact only under nesting, and nesting holds partially (see measurements). Untested.
### Estimating $O$ locally (per partition / per layer)
- **Per layer: not representative.** A layer is an increment of kmer content added to a partition (typically one `merge`), not a batch of genomes; all genome columns exist in every layer (`UserDocMD/formats/index_layout.md`). Layer content is dominated by kmers novel at merge time, so a layer's $O_{ij}$ reflects merge order, not the index-wide distribution; not an unbiased estimator of the global $O_{ij}$.
- **Per partition: valid only if partitions are exchangeable samples of families** (hash-based; not verified, minimizer distribution may be skewed). Even then, the pairs that matter are the rare ones, with near-zero count per partition; a `min` over noisy estimates is biased downward (winner's curse), weights would go to pairs that were unlucky in that partition rather than globally poorest.
- **Recommended:** compute $O$ globally once (the `--family-overlap` scan already exists), apply the weight locally per partition, keeping partitions independent. Without an extra pass: pilot estimate on a random subset of partitions.
- **Sequential variant:** update the $O$ estimate as partitions are processed in random order, boosting still-undersampled pairs. Self-correcting but breaks partition independence and makes the result order-dependent.
- **Quota consequence:** the current per-partition quota is proportional to candidate-family count; with weights it must be proportional to the partition's weight mass $\sum_f w_f$, otherwise partitions rich in high-weight families are undersampled.
## Does the entropy bias distort pair representation? (measured 2026-10-07)
Sample drawn with `--entropy 1 --entropy-sd 0.5` (μ=1 explicit, σ default 0.5): family weight $\exp(-2(H-1)^2)$, $H$ = `entropy15` in bits; weight 1 at $H=1$, 0.135 at $H=0$ or $2$, $\approx 3\!\times\!10^{-4}$ at $H=3$.
Comparison, per genome pair, of the full-index `family_overlap` $O^{\text{full}}$ (index scan) to the sample's overlap $O^{\text{samp}}$ (5.0 M columns), sampling fraction $r_{ij}=O^{\text{samp}}_{ij}/O^{\text{full}}_{ij}$ (uniform draw would give constant $r$):
| Quantity | Value |
|---|---|
| Spearman $O^{\text{full}}$ vs $O^{\text{samp}}$ | 0.994 (Pearson on logs 0.998): ranking preserved |
| global fraction $\sum O^{\text{samp}}/\sum O^{\text{full}}$ | 0.52 % |
| $r$ quantiles 5 / 50 / 95 % | 0.0025 / 0.0037 / 0.0055 |
| slope $\log r$ vs $\log O^{\text{full}}$ | +0.12 |
| Spearman($r$, patristic distance) | −0.71 |
Per decile of $O^{\text{full}}$, median $r$ rises from 0.0027 (poorest decile) to 0.0053 (three richest, plateau): the poorest pairs are represented about half as much as the richest, so the draw amplifies the imbalance. $r$ climbs slowly over deciles 1-6 (0.0027 to 0.0037), jumps at deciles 7-8 (0.0045-0.0052), where the $O^{\text{full}}$ distribution has a gap (689 k to 11.6 M, presumably close intra-clade pairs, unchecked).
Not established: (a) causality — a dependence of $r$ on pair richness is compatible with the entropy filter but no uniform control draw of the same size exists; (b) noise — the poorest sample pairs have tiny counts (min 4).
**Candidate mechanism: first hypothesis refuted, see the next section.** I first suggested that long-reach families, carried by many divergent genomes, spread over several states ($H\approx2\text{-}3$) and are downweighted from above by the Gaussian. The full entropy table (next section) shows the opposite: families with many carriers are mostly *low*-entropy, and are downweighted from below.
**Consequence for the pair-weight proposal:** entropy and reach are likely correlated, not independent criteria. Since the entropy weight of each family is known, the pair weight can compensate it exactly (divide by it) rather than compose with it; order of the two filters must then be defined.
## Entropy vs number of carrier genomes, full index (measured 2026-10-09)
Source: `phylo --shannon`, which is **always a full, unsampled scan** of every non-monomorphic minorant of every layer (`SiblingExt::shannon_entropy_csv(path)` takes no `subsample`/`entropy_bias` argument; `--subsample`/`--entropy` apply only to `--pseudo-alignment`/`--sankoff`/`snp-*`). Here: 19.7 GB CSV, 535 257 857 families, read in 11 s with DuckDB (no in-memory load). `UserDocMD/usage/phylo.md` line 121 ("`--subsample N --shannon` gives a bounded diagnostic sample") is stale and contradicts line 55 and the code; to fix.
| Carriers $n$ | Families | mean $H$ | median $H$ | $P(H<0.5)$ | $P(H\ge1.5)$ | mean weight ($\mu=1,\sigma=0.5$) |
|---|---|---|---|---|---|---|
| 2 | 163.3 M | 0.66 | 1.00 | 34.5 % | 0 % | 0.70 |
| 3-4 | 104.6 M | 0.94 | 0.92 | 0.5 % | 7.9 % | 0.93 |
| 5-8 | 91.8 M | 0.83 | 0.72 | 0.1 % | 4.6 % | 0.80 |
| 9-16 | 62.7 M | 0.70 | 0.50 | 43.6 % | 4.9 % | 0.66 |
| 17-32 | 45.4 M | 0.59 | 0.35 | 58.9 % | 5.9 % | 0.53 |
| 33-64 | 48.1 M | 0.34 | 0.19 | 79.7 % | 1.1 % | 0.40 |
| 65-128 | 19.1 M | 0.37 | 0.18 | 77.4 % | 3.8 % | 0.37 |
| 129-180 | 0.19 M | 0.83 | 0.47 | 53.0 % | 21.4 % | 0.46 |
Findings:
- Families with many carriers are mostly one dominant state plus rare variants ($H<0.5$ for ~77-80 % at $n\ge33$); only 1-4 % have $H\ge1.5$. The Gaussian at $\mu=1$ therefore penalizes them from the **low** side (weight 0.135 at $H=0$), not the high side.
- Relative to a uniform draw, expected inclusion is about ×1.32 at 3-4 carriers and ×0.53-0.56 at 33-128 carriers: a factor ~2.4 between small and large $n$. Same order as the ~2× pair-level undersampling of poor pairs measured above; compatible, but a family-level ratio is not a pair-level one, so causality remains unproven (no uniform control draw).
- The filter does what it is designed for (drop near-autapomorphic variants), but those low-entropy high-$n$ families are also the ones covering distant pairs, hence the side effect.
- Informative high-$n$ families are scarce: at $n>32$ only ~19 % have $H\in[0.5,1.5)$, and the 129-180 class is 0.04 % of all families. Flattening deep-pair coverage works on little informative material whatever the weights.
- Consequence for a $\mu(n)$ that grows with $n$: it would not recover these families (80 % sit below 0.5 bit); what matters at large $n$ is the share of families in the band around 1 bit, not the position of the centre. Conditional weight $w_H(f)/E[w_H\mid n_f]$ remains an option to make the entropy filter neutral to $n$; $E[w_H\mid n]$ is now available from this table.
Limit: the table has `n_genomes_present` but not the reach of the family, so the link to specific pairs is still not measured.
## Site concordance factors on the Primulaceae tree (measured 2026-10-12)
Command (IQ-TREE 3.1.3): `iqtree3 -t <treefile> -s <alignment> -m GTR+G4+ASC --scfl 100 --cf-verbose -T 5 --prefix concord`. With `-t` plus `-m`, IQ-TREE did **not** just annotate the reference tree: it ran a full ML search started from it (102 iterations, ~59 h wall-clock). `concord.treefile` differs from the input treefile by one bipartition (Robinson-Foulds 2), so sCF refer to the re-inferred tree. Without `-m`, ModelFinder is launched and required 157 GB (first attempt failed). The log also warns that all 180 sequences contain more than 50 % gaps/ambiguity. `sN` below = informative sites averaged over the 100 sampled quartets of a branch (alignment: 5 003 414 columns).
**Deep Primula/Androsace interface: too few informative sites (data scarcity).**
| Node | Tips (Primula / Androsace) | sCF | sDF1 | sDF2 | `sN` |
|---|---|---|---|---|---|
| 209 | 67 (43 / 24) | 27 | 47 | 26 | 17 |
| 210 | 66 (43 / 23) | 37 | 33 | 30 | 43 |
| 208 | 74 (50 / 24) | 54 | 16 | 29 | 190 |
| 211 | 24 (2 / 22) | 64 | 18 | 18 | 226 |
| 212 | 21 (2 / 19) | 30 | 38 | 32 | 184 |
| 216 | 10 (2 / 8) | 21 | 47 | 32 | 7 |
| 217 | 9 (1 / 8) | 43 | 20 | 36 | 7 |
Quartets crossing these nodes have tens to a few hundred informative sites out of 5 M columns, the quantitative counterpart of the pair-overlap scarcity. Primula tips are spread over several nodes mixed with Androsace (e.g. 43 + 24 at node 209); no monophyletic Primula in this tree.
**Within Androsace: conflict, not scarcity.** Nodes 283 (72 Androsace, `sN` 17 127), 292 (49 tips, 10 335), 305 (22, 11 980), 342 (11, 6 566) have thousands of informative sites but sCF 33-37 % with both alternatives nearly as supported: sites split almost evenly among the three quartet topologies. More sites would not fix this; cause not established (a poor fit of a tree model to intra-species divergence is one hypothesis, untested). Node 185 (23 Androsace): sDF1 53.6 % > sCF 30.6 %, a majority of the 893 sites prefer an alternative (real conflict).
**Well-supported nodes have long branches:** node 296 (45 tips, length 0.23, sCF 90 %), 341 (0.21, 91 %), 330 (0.09, 85.5 %), 181 (0.099, 89.5 %); most branches of length 0.01-0.05 have sCF 33-45 %. Degenerate: node 186 (length 0.001, `sN` 0.37) and 187 (`sN` 2.2) carry no informative site.
Median sCF shows no gradient with clade size (about 39-48 % in every class), so the clade-size class hides the effect; the scarcity is specific to the interface nodes above.
**Implication for sampling.** The part a sampling design can address is the interface scarcity: select families carried by genomes from the four groups around each target node (a quartet-targeted selection) rather than flattening the whole pair matrix. Not assessed: how many such families the index holds (the `sN` of nodes 209 and 216 suggests few). For the intra-Androsace conflict no sampling strategy is suggested by these measurements alone.
## Quartet coverage (measured 2026-10-12, `--quartet-test`)
`scripts/pseudo_alignment_nesting.py --quartet-test --quartets N` draws random genome quartets and counts exactly the columns where all four carry a call, stratified by the size of the smallest tree clade containing the four. Cost: 20 000 quartets over 5.0 M columns in about 35 s total. Exact per-family quartet weighting is out of reach ($\binom{180}{4}\approx 42.3$ M quartets; one family carried by 100 genomes covers $\binom{100}{4}\approx 3.9$ M), so quartets serve as a *diagnostic* of a sample, not as a weight.
Result on the current sample: 4-way count quantiles 0 / 1 / 10 / 50 / 90 / 99 / 100 % = 0, 3, 68, 200, 2 329, 66 504, 194 460 (CV 3.5, 0.1 % uncovered). By depth: median 131-209 for quartets inside clades ≥ 65 genomes versus 11 580-57 387 for clades 17-64. The ratio of the 4-way count to the smallest of the six pair overlaps has median 0.20-0.29 for deep quartets (0.53 for clades 33-64; 1 would be perfect nesting): pair overlap is only a loose upper bound of 4-way coverage, so flattening pairs does not by itself flatten quartets. 88 % of random quartets fall in the deepest class (root as written; strata with < 5 quartets are noise). Co-presence is not informativeness (a column must also differ among the four). Next measurement: repeat on a sample drawn with the pair weight and check whether the ratio moves toward 1.
## Two kinds of family loss: sequencing dropout vs divergence (2026-10-12)
- **Sequencing dropout (genome skimming, ~1× coverage).** About $e^{-1}\approx 37\%$ of each genome is uncovered, independently per family. Predicted for a family truly present in a clade of $m$ genomes: completeness ≈ 0.63-0.70 and clade-closed fraction $c^m$, independent of clade depth. Consistent with small clades (3-4 tips: completeness 0.71, 20 % closed vs $0.65^3=27\%$, $0.65^4=18\%$). Does not predict the observed decay at larger clades (0.45 at 5-8 tips, 0.21 at 17-32, 0.08-0.12 beyond).
- **Loss by divergence (user observation).** A family is a kmer whose 30 flanking positions (15 each side for $k=31$) are identical, with a variable central base; with per-site divergence $d$ the flanks survive with probability ≈ $(1-d)^{30}\approx e^{-30d}$ (0.74, 0.21, 0.042, 0.0012 for $d$ = 0.01, 0.05, 0.10, 0.20). Phylogeny-dependent and tied to local conservation, unlike sequencing dropout. Explains the loss of completeness with clade size, and sets a floor: no weighting can sample families that no longer exist for pairs whose $e^{-30d}$ is negligible. Surviving deep families are selected for conserved flanks, hence plausibly slow-evolving (fewer variable sites for deep splits; hypothesis, untested).
- The patristic distances of the IQ-TREE tree (1 to 3.5) come from an alignment with variable sites only, hence strongly inflated; the true $d$ is unknown and these numbers cannot be plugged into $e^{-30d}$.
- **Test (user's plan), done 2026-10-12: see the next section.**
## Overlap vs Mash distance on the full index (measured 2026-10-12)
Inputs: `phylo --distance mash --csv --shared-kmers --nj` on the 180-genome index (distance matrix, shared-kmer matrix, NJ tree) against the full-index `family_overlap` $O_{ij}$. Mash $D$: range 0.011-0.337, median 0.20.
| Regression | Slope | $R^2$ |
|---|---|---|
| $\log O_{ij}$ vs $D$, all pairs | -26.95 | 0.979 |
| $\log$(shared kmers) vs $D$ | -31.87 | 0.984 |
| $\log O_{ij}$ vs $D$ + additive genome effect | -25.3 | 0.9999 |
Spearman($D$, $O$) = -0.95; Spearman($D$, shared kmers) = -0.95; Spearman($D$, IQ-TREE patristic) = 0.81.
Reading:
- Overlap decays log-linearly with distance, slope about -27 versus -30 predicted by flank survival (previous section). **Not an independent confirmation of the flank model**: Mash $D$ is derived from kmer sharing and $O$ counts families defined by kmers, so both measure the same shared content. The kmer slope of -32 is $-k$ by construction of Mash (implementation check only). The ratio of the two slopes, 27/32 ≈ 0.85, is below the 30/31 ≈ 0.97 expected from flank survival alone; cause unknown, the gap is modest.
- Local slopes vary: -21 for $D\in[0.011,0.07]$ ($R^2$ 0.45), -28 for [0.07, 0.20] (0.96), -35 for $D>0.23$ (0.83). Half the pairs lie in $D\in[0.20,0.23]$, where the fit explains almost nothing ($R^2$ 0.26 and 0.07): a plateau where Mash has little resolution.
- Genome effects (log scale, sd 0.21): lowest `Androsace_saussurei--PHA010690` (factor ≈ 0.39), `Androsace_triflora--PHA000558` (≈ 0.62), `Androsace_vesulensis--PHA010698` and `Primula_stricta_var_obesior--TROM_V_149128` (≈ 0.65); highest `Androsace_pubescens--PHA010697` (≈ 2.8). Three of the four lowest are also among the genomes with the fewest calls in the pseudo-alignment (saussurei, triflora, stricta), pubescens has the most; consistent with a coverage effect at the extremes, correlation over all genomes not computed.
- NJ on Mash vs the IQ-TREE tree: Robinson-Foulds 182 of 354 (0.51 normalized); the Mash plateau near 0.2 probably limits NJ resolution for most pairs.
- Consequence for normalization: the residual $\log O_{ij}-(a+bD_{ij})$ measures coverage deviation at a given distance, a normalization of $O$ that needs no per-genome call counts. Untested on a weighted sample.
## Data-poor genomes (measured 2026-10-12)
Per-genome share of the 5 003 414 sampled columns with a call: median 5.2 %, max 14.3 %; 8 genomes below 1 % and 23 below 2 %. Fewest calls: `Androsace_triflora--PHA000558` 1 936, `Primula_stricta_var_obesior--TROM_V_149128` 2 403, `Primula_carniolica--PHA007185` 4 937, `Androsace_saussurei--PHA010690` 6 986, `Primula_pumila--TROM_V_135924` 17 393, `Androsace_maxima--PHA000534` 17 939, `Primula_auricula_subsp_serratifolia--PHA007184` 30 621, `Androsace_pyrenaica--PHA000543` 37 725. Three of them (saussurei, serratifolia, pyrenaica PHA000543) are among the tips whose placement looked aberrant, previously attributed to possible mislabelling or contamination. A simpler alternative is too little data to place them reliably; testable by removing them (`--exclude-genome`) and watching deep-node support.
Consequence for flattening: raw $O_{ij}$ mixes evolutionary distance and per-genome coverage; flattening on it chases pairs involving data-poor genomes, for which no family exists. Normalizing, $O_{ij}/(c_ic_j)$ with $c_i$ the number of families carried by genome $i$ (per-genome counts from `--sibling-stats`), targets distance instead of coverage; the best normalization (smoothing of $c_i$, etc.) is not established.
## Implemented: entropy annex parametrised by `--no-ambiguity` (2026-10-13)
Design decision (user): the way genomes are counted depends on `--no-ambiguity`, so that flag, not an "alphabet" option, is the annex parameter. Over single-member genomes the 15-state entropy only has the four single-base states, hence `entropy4` (redefined: 4 bases over single-member genomes) equals `entropy15` under `--no-ambiguity`; a unit test checks it.
- `entropy_annex.rs`: header `flags` (the former padding), bit 0 = `no_ambiguity`; old files have 0 and stay valid. One file per convention (`entropy.pent`, `entropy.noamb.pent`), so switching the flag builds the missing one without discarding the other. `EntropyAnnex::no_ambiguity()`; `iter_full_entropy` rejects a header that disagrees with the requested convention.
- `ensure_layer_entropy_annex` takes the list of conventions to build; one scan feeds every missing annex and the overlap accumulator. `sample_index` builds and reads the convention matching its `no_ambiguity` argument, removing the mismatch between the draw (previously always raw masks) and the alignment (masked).
- `--sibling-annex` builds both conventions and invalidates both on rebuild. `--shannon` no longer builds any annex as a prerequisite (it recomputes everything from its own scan).
- Checked on the 1x benchmark index: a `--no-ambiguity` run creates `entropy.noamb.pent` beside the existing `entropy.pent` in all 512 layers; workspace tests pass.
- Still to do, in this order: `--quartet` (per-family bit annex, same parameter), `--pair-balance` (mean of 1/shared-families over the carrier pairs; second overlap matrix for the single-member convention, annex header carrying a fingerprint of the matrix it came from).
## Implemented: `--quartet` (2026-10-13)
`--quartet` keeps only the families with at least two called states each carried by at least two genomes (`masking::is_quartet_informative` for the raw masks, `survives_quartet` for the exact check on masked states and `--exclude-genome`). Absence never counts as a state; with `--no-ambiguity`, multi-member genomes are left out of the count. The persisted annex is a plain `PersistentBitVec` (one bit per non-monomorphic family, compact ordinal) — no ad hoc format; the `--no-ambiguity` convention is carried by the file name (`quartet.pbiv`, `quartet.noamb.pbiv`) because that header has no room for a flag. It is a safe pre-filter: excluding genomes can only destroy a bipartition, never create one.
Plumbing: `AnnexRequest` (which annexes, per convention) and `ensure_layer_family_annexes` (one shared scan for entropy, quartet and overlap) replace the entropy-only builder; the sampling parameters travel as one `SamplingSpec { free_loss, no_ambiguity, quartet, entropy_bias }` instead of a growing positional list.
First test on the 1x benchmark testbed (3 seeds, exhaustive alignment, `GTR+G4+ASC`, species monophyly out of 3 per seed): without filter 1 / 0 / 0 correct monophylies; carriers >= 4 only: 3 / 1 / 2; `--quartet`: 2 / 2 / 3 (370, 148, 369 columns, all informative by construction). *Klebsiella* stays fragile (wrong in 2 seeds out of 3); two seeds still show a branch at the IQ-TREE ceiling of 10 with so few columns. Small testbed, three seeds: a direction, not a measurement.
## Implemented: `--subsample` renamed `--n-sites N|all` (2026-10-13)
`--subsample` read as "draw a subset", while `--pseudo-alignment`/`--sankoff` made it mandatory and accepted no way to say "everything" (the workaround was a number larger than the family count, e.g. `--subsample 100000000`). The option is now `--n-sites <N|all>`: `all` is an explicit value, parsed into its own type (`NSitesArg::{All, N}`, like `GammaShapeArg`) rather than an in-band sentinel (negative number, `0`); `all` gives the exhaustive scan the `snp-*` path already ran when the option was omitted. Still mandatory for `--pseudo-alignment`/`--sankoff`; still optional for `snp-*` `--distance`. No alias is kept for the old name (the software is in active development). The benchmark commands and measurements recorded in the earlier sections of this file were run with the old name.
## Implemented: `--pair-balance` (2026-10-13)
Weight of a family = **mean** over the pairs of its carriers of 1/O (O = index-wide shared variable families of the pair, same `--no-ambiguity` convention): the simulation on the *Primulaceae* sample (above) had the mean flatten best (expected-overlap range 23 000× to ~600×, slope 0.37) without chasing high-carrier families, unlike the sum (65 % of the draw at >= 33 carriers).
- `algorithms/pair_weight.rs`: `inverse_overlap_matrix` (dense n×n of 1/O from the persisted overlap annex), `pair_balance_weight` (mean over carrier pairs; 0 below two carriers). Carriers are defined once, `helpers::is_carrier(mask, no_ambiguity)`, shared with the overlap accumulator and the quartet test.
- Storage: no new format. The entropy annex is generalised to `FamilyScalarAnnex` with a `ScalarKind` (`Entropy` magic `PENT`, `PairWeight` magic `PPWT`, one file per kind and convention, header flag `no_ambiguity`); `entropy_annex.rs` became `family_scalar_annex.rs`. Family overlap is now one file per convention too (`family_overlap.povl`, `family_overlap.noamb.povl`, header flag); `--family-overlap` and `--min-shared-family` follow `--no-ambiguity`.
- Build order: sweep 1 builds entropy, quartet and the missing overlap annexes together; sweep 2 builds the pair weights, which need the finished matrix (`ensure_layer_pair_weight_annexes`). `AnnexRequest` now lists `entropy`, `quartet`, `overlap`, `pair_weight`; a pair weight implies its overlap. A rebuilt sibling annex removes every annex derived from it (entropy, quartet, pair weight, overlap), so a weight can never outlive the matrix it came from; there is no fingerprint, only that single invalidation point.
- Sampler: `LayerPlan` (eligible bits, minorant count, mass) replaces the positional tuple; a layer's quota is `n × mass / Σ mass` (mass = eligible count without the option, Σ weights with it); a family is accepted with probability `quota/mass × weight × entropy kernel`, capped at 1 (the cap, and kernels below 1, undershoot the quota, absorbed by the existing top-up rounds).
- Cost note: weights need O(carriers²) per family at build time; not measured on a large index.
First test, 1x benchmark testbed (20 genomes, 46 706 variable families, `--n-sites 5000 --free-loss --no-ambiguity`, 8 replicates each; sample overlap computed from the alignment, compared with the index `--family-overlap --no-ambiguity`):
| | slope of log(sample overlap) on log(index overlap) | pairs (index overlap > 0) covered by >= 1 column | columns with >= 10 carriers |
|---|---|---|---|
| uniform | 1.02 ± 0.14 | 64 % | 0.18 % |
| `--pair-balance` | 0.84 ± 0.001 | 97 % | 1.1 % |
The weight flattens the representation (slope toward 0) and, above all, covers most of the pairs a uniform draw misses. Not measured: effect on the tree (sCF / monophyly), interaction with `--entropy`, behaviour on the *Primulaceae* index. 20 genomes only.
## Quota rounding fix, and the combined test on the 1x testbed (2026-10-13)
**Fix.** `sample_index` rounded each layer's quota down on its own, losing up to one site per layer: with 512 layers a budget of 100 sites gave 0 to 3 columns. Quotas now use cumulative rounding (`floor(n × cumulative mass / total)` minus what earlier layers got), so they sum to exactly `n`; a 100-site budget now yields 50-80 usable columns. Not a result of the options below, a defect the small testbed exposed.
**Test.** 1x testbed, 3 seeds × 10 replicates per variant, 11 genomes (the 9 genomes with fewest calls excluded, so no all-missing sequence), `--free-loss --no-ambiguity`, IQ-TREE `GTR+G4+ASC` on each sampled alignment; score = number of the three species (*E. coli*, *Salmonella*, *Klebsiella*) recovered monophyletic (0-3), mean over the 30 runs; "informative" = columns with two bases each carried by >= 2 genomes.
| `--n-sites` | variant | trees obtained | columns | informative columns | mean species monophyletic (of 3) | all 3 |
|---|---|---|---|---|---|---|
| 100 | uniform | 77 % | 49 | 0.5 | 0.04 | 0 % |
| 100 | `--quartet` | 100 % | 82 | 82 | 2.30 | 50 % |
| 100 | `--pair-balance` | 100 % | 52 | 2.1 | 0.20 | 0 % |
| 100 | `--quartet --pair-balance` | 100 % | 67 | 67 | 2.53 | 53 % |
| 100 | `... --entropy 1` | 100 % | 67 | 67 | 2.17 | 17 % |
| 300 | uniform | 93 % | 163 | 2.1 | 0.04 | 0 % |
| 300 | `--quartet` | 100 % | 239 | 239 | 2.33 | 33 % |
| 300 | `--pair-balance` | 100 % | 179 | 6.2 | 0.57 | 0 % |
| 300 | `--quartet --pair-balance` | 100 % | 197 | 197 | 2.67 | 67 % |
| 300 | `... --entropy 1` | 100 % | 196 | 196 | 2.67 | 67 % |
(Mean over all runs counting a failed tree as 0 is identical to the "mean species" column wherever trees were obtained; the uniform rows lose runs because IQ-TREE refuses alignments where a genome has no data.)
Reading: `--quartet` is the decisive option here — a uniform draw of 100-300 sites contains almost no informative column (0.5-2), the restricted draw contains only informative ones. `--pair-balance` alone barely helps (it favours rare pairs but does not remove the uninformative columns); added to `--quartet` it raises the share of replicates recovering all three species (50→53 % and 33→67 %). The entropy kernel (centre 1 bit, default width) adds nothing at 300 sites and costs at 100. Limits: 11 genomes, three simulated 1x datasets, small budgets, a single criterion (species monophyly, not deep branches), and the differences between the `--quartet` variants (a few runs out of 30) are small relative to the replicate noise — a direction, not a ranking.
## Open questions
- Per-family $S_f$ without materializing the full matrix: a first pass storing only a per-family summary (reach, $|S_f|$), as `--shannon` already does a full unsampled scan for entropy.
- Combination with entropy bias: not independent criteria if entropy correlates with reach (see section above); options: compensate the known entropy weight inside the pair weight, or apply the Gaussian inside reach strata.
- Pairs with near-zero $O_{ij}$ (suspected badly sequenced genomes) set the ceiling for everyone; `--min-shared-family`/`--exclude-genome` should be applied first so the floor is not dictated by anecdotal genomes.
- Effect on the SNP-distance estimators: a non-uniform draw over pairs biases per-pair eligible-family counts, but each pair's $p$-distance is a ratio over its own eligible families, so unbiasedness per pair is expected to hold. To confirm before relying on it.
@@ -0,0 +1,60 @@
# Sibling partition unification and masked canonical form (discussion)
Status: **open, nothing implemented**. Records the state of the reflection on (a) routing the 4 members of a sibling family to one partition and (b) a canonical form that makes siblings directly comparable. Measurements are throwaway (not in the repo); figures are for $k=31$, $m=11$, 256 partitions, 20 bacterial genomes (98.4 M kmer positions), unless stated.
## Problem
A sibling family = the 4 kmers differing only at the central base (position $c=(k-1)/2$, $k$ odd). Routing is **not** a hash of all bases: a kmer goes to `minimizer().seq_hash() & mask`, and consecutive kmers of a superkmer share their minimizer. A family splits across partitions whenever the central base falls in (or changes) the selected m-mer.
Fraction of families whose 4 variants are not all in one partition, standard minimizer: $4m/(k+2m+1)$ (fixed candidates $k-2m+1$ versus $4m$ variable ones). Measured: 81.4 % at $m=11$ (60.2 % at $m=7$, 46.8 % at $m=5$). This is the *theoretical* rate assuming all 4 members present; for two present members it is ≈ 68 %. Real families are overwhelmingly of size 1, so it only becomes cost where something probes variants.
## Masked canonical form (Can3)
Notation: `CentreA(K)` = K with its central base set to A; `RC(K)` its reverse complement.
- Can1 = `min(K, RC(K))` (current). Each sibling canonicalised alone, so some may be flipped relative to the others.
- Can2 = orient by `CentreA(K)` vs `RC(CentreA(K))`. **Not a valid canonical form**: when the flanks are reverse complements of each other ($L=\mathrm{rc}(R)$, frequency ≈ $4^{-c}$, 1/1024 at $k=11$), $K$ and $\mathrm{RC}(K)$ get different canonicals (k=5: `ACAGT` and `ACTGT` both kept). Cause: `CentreA(RC(K)) ≠ RC(CentreA(K))` (the latter has centre T).
- **Can3** (retained):
```
Can3(K) = K if CentreA(K) < CentreA(RC(K))
= RC(K) if CentreA(K) > CentreA(RC(K))
= Can1(K) otherwise // self-revcomp family
```
Orientation is decided on the flanks only (centre ignored), tie broken on the full kmer. Gain: the 4 canonical siblings have identical flanks in the same orientation, so they compare directly with no reverse complement. Self-revcomp families have only 2 distinct canonical members (centres A/C; T/G fold onto them). The A↔T (C↔G) substitution in that context is undetectable by any double-strand canonical set, same as under Can1 — not a loss.
Gain is simplification only: `central_canonical_neighbors` already canonicalises each variant independently and is correct (see `evolutionary_distances.md`, per-partition sweep). The earlier "masked-flank grouping" there is the Can2 idea; Can3 is its repaired form. **No performance gain by itself**, and it breaks existing indexes (canonical orientation changes for some kmers → MPHF hashes change; rebuild).
Prerequisite if adopted: `Minimizer = CanonicalKmerOf<MLen>` shares the canonical type with index kmers; an m-mer has no sibling family and must keep Can1. Decouple with a distinct `Minimizer` type (6 files outside `kmer.rs`: `routable.rs`, `packed_seq.rs`, `obiskbuilder/{rolling_stat,stream_iter,iter}.rs`, `obifastwrite`).
## Routing that excludes the centre (scheme B) — rejected
Candidates restricted to m-mers not overlapping the centre ($m\le c$): $S(j)=\min$ hash over m-mers $p\in[j,j+c-m]$, minimizer$(i)=\min(S(i),S(i+c+1))$. Family- and strand-invariant by construction (checked). But unitigs are partition-local (`pipeline.md`), and the hole moves with each kmer, so runs shrink:
| $m$ | mean run, current | mean run, B | bases/kmer, current → B |
|---|---|---|---|
| 5 | 14.9 | 6.3 | 3.02 → 5.76 |
| 11 | 11.0 | 3.0 | 3.72 → 10.96 |
| 15 | 9.0 | 1.0 | 4.32 → 30.9 |
Proxy: run = unitig (upper bound; real unitigs may merge). Independent of partition count. In `benchmark/run/global_index_count` (786 MB) `unitigs.bin` + idx ≈ 241 MB (31 %), so tripling them ≈ +60 % total index. Hashing the masked kmer per kmer (no minimizer) would cut every path at every kmer: worse.
Structural tension: path coherence (long unitigs) needs a key shared by consecutive kmers, family coherence needs a key independent of each kmer's own centre, which is an ordinary base for its neighbour. Decoupling sequence storage from MPHF partitioning fails because a partition can only enumerate its kmers from its own unitigs (MPHF not invertible). Redefining the family on a terminal base would cut the split rate to ≈ 17 % but is not closed under revcomp and changes the SNP semantics. Lower $m$ reduces the split rate for free but deviates from the literature $k/m\approx 2.5$ optimum (balance, bucket size), unmeasured here — $m=11$ kept.
## What the cross-partition cost actually is
- Phylo-time: only families of size > 1 trigger remote lookups (a small share).
- Annex construction probes the 3 variants of **every** kmer (size-1 families included), ≈ 2/3 of probes crossing partitions; batch bounded to `#kmers(p)*3` per partition (not the whole index).
- Real remaining benefit of unification: the outer sweep over source partitions could run in parallel (it is sequential today for memory and for the `q >= p` dedup rule); plus code simplification in `family_scan.rs` / `annex.rs`. Not quantified.
- Unification would also allow an MPHF keyed on the family (one lookup, 4-bit member mask, union/intersection as OR/AND); needs the family-size histogram (1–4 members) to judge storage.
## Open measurements (index not on this machine)
1. Family-size histogram of the real index: `obikmer phylo --sibling-hist` (needs a built annex).
2. Time and peak RSS of `--sibling-annex` on the Vaccinium/Salix index (`Stage` "sibling_annex" traces time; peak RSS from outside).
3. Only if those show the sequential sweep or the probe volume is a real bottleneck: real-index test of scheme B or of a smaller $m$.
## Decision state
No code change decided. Can3 + `Minimizer` decoupling is the only self-contained step and is independent of the measurements above; it forces an index rebuild, so it is worth doing only if its simplification is wanted.
+2 -2
View File
@@ -1,6 +1,6 @@
# Architecture notes for advanced use # Architecture notes for advanced use
This page describes execution-level behavior relevant to sizing and running `obikmer` on large datasets or multi-socket machines. It complements the [index format](formats/index_layout.md) and [theory](theory/indexing_architecture.md) pages. This page describes execution-level behavior relevant to sizing and running `obikmer` on large datasets or multi-socket machines. It complements the [index format](formats/index_layout.md) and [theory](theory/kmer_indexing/indexing_architecture.md) pages.
## Sequence invariant ## Sequence invariant
@@ -8,7 +8,7 @@ Every input sequence is treated purely as a compact representation of a set of o
- Only the `A`/`C`/`G`/`T` alphabet (case-insensitive) is recognized; a sequence is cut at any other character (including IUPAC ambiguity codes), so runs containing them are not represented in the index. - Only the `A`/`C`/`G`/`T` alphabet (case-insensitive) is recognized; a sequence is cut at any other character (including IUPAC ambiguity codes), so runs containing them are not represented in the index.
- Sequences are internally processed in chunks of at most 256 nucleotides; a chunk shorter than k is dropped. This is invisible to the user beyond the ACGT-only, minimum-length-k constraints above. - Sequences are internally processed in chunks of at most 256 nucleotides; a chunk shorter than k is dropped. This is invisible to the user beyond the ACGT-only, minimum-length-k constraints above.
- Kmers are always handled in canonical form (see [DNA encoding](theory/encoding.md)), so the tool is strand-agnostic throughout: a kmer and its reverse complement are always the same entry. - Kmers are always handled in canonical form (see [DNA encoding](theory/kmer_indexing/encoding.md)), so the tool is strand-agnostic throughout: a kmer and its reverse complement are always the same entry.
## Index dimensioning ## Index dimensioning
+2 -2
View File
@@ -2,9 +2,9 @@
## Construction pipeline ## Construction pipeline
Building an index ([`index`](../usage/index_command.md)) proceeds through a fixed sequence of phases, each operating independently per partition (see [Partitioning and indexing architecture](../theory/indexing_architecture.md)): Building an index ([`index`](../usage/index_command.md)) proceeds through a fixed sequence of phases, each operating independently per partition (see [Partitioning and indexing architecture](../theory/kmer_indexing/indexing_architecture.md)):
1. **Scatter.** A single streaming pass over the input. Each sequence fragment is cut at non-ACGT bases, passed through the low-complexity entropy filter (see [Low-complexity kmer filter](../theory/entropy_filter.md)), and any resulting segment shorter than k is dropped. Surviving segments are decomposed into super-kmers, canonicalized, and routed by `hash(minimizer) mod n_partitions` into one file per partition. 1. **Scatter.** A single streaming pass over the input. Each sequence fragment is cut at non-ACGT bases, passed through the low-complexity entropy filter (see [Low-complexity kmer filter](../theory/kmer_indexing/entropy_filter.md)), and any resulting segment shorter than k is dropped. Surviving segments are decomposed into super-kmers, canonicalized, and routed by `hash(minimizer) mod n_partitions` into one file per partition.
2. **Dereplication.** Within each partition, identical super-kmer sequences are merged and their occurrence counts summed. This count is per super-kmer, not per kmer — a kmer's true abundance is the sum of the counts of every super-kmer containing it. 2. **Dereplication.** Within each partition, identical super-kmer sequences are merged and their occurrence counts summed. This count is per super-kmer, not per kmer — a kmer's true abundance is the sum of the counts of every super-kmer containing it.
3. **Exact counting.** Every kmer in every dereplicated super-kmer is enumerated and its exact total count computed. A per-genome kmer frequency spectrum is produced at this stage. 3. **Exact counting.** Every kmer in every dereplicated super-kmer is enumerated and its exact total count computed. A per-genome kmer frequency spectrum is produced at this stage.
4. **Quorum filtering.** Kmers outside the `--min-abundance`/`--max-abundance` range are dropped, and super-kmers are recompacted around the surviving kmer set. 4. **Quorum filtering.** Kmers outside the `--min-abundance`/`--max-abundance` range are dropped, and super-kmers are recompacted around the surviving kmer set.
+4 -4
View File
@@ -6,11 +6,11 @@ All functionality is exposed through a single binary, `obikmer`, organized as su
## Core principles ## Core principles
- Kmers are of fixed, odd length $k$, chosen at index-construction time in the range $[11, 31]$ (see [Kmers and super-kmers](theory/kmers_and_superkmers.md)). - Kmers are of fixed, odd length $k$, chosen at index-construction time in the range $[11, 31]$ (see [Kmers](theory/kmer_indexing/kmers.md)).
- Each kmer fits in a 64-bit word using a 2-bit-per-base encoding (see [DNA encoding](theory/encoding.md)). - Each kmer fits in a 64-bit word using a 2-bit-per-base encoding (see [DNA encoding](theory/kmer_indexing/encoding.md)).
- Kmers are handled in **canonical form** ($\text{canonical}(kmer) = \min(kmer, \text{revcomp}(kmer))$), making counting strand-independent. - Kmers are handled in **canonical form** ($\text{canonical}(kmer) = \min(kmer, \text{revcomp}(kmer))$), making counting strand-independent.
- Sequences are decomposed into **super-kmers** before storage, anchored on a hash-selected **minimizer** (see [Minimizer selection](theory/minimizer_selection.md)), then routed to one of several **partitions** for parallel, memory-bounded processing (see [Partitioning and indexing architecture](theory/indexing_architecture.md)). - Sequences are decomposed into **super-kmers** before storage, anchored on a hash-selected **minimizer** (see [Minimizer selection](theory/kmer_indexing/minimizer_selection.md)), then routed to one of several **partitions** for parallel, memory-bounded processing (see [Partitioning and indexing architecture](theory/kmer_indexing/indexing_architecture.md)).
- Low-complexity kmers can be filtered out at index-construction time using an entropy-based score (see [Low-complexity kmer filter](theory/entropy_filter.md)). - Low-complexity kmers can be filtered out at index-construction time using an entropy-based score (see [Low-complexity kmer filter](theory/kmer_indexing/entropy_filter.md)).
## Commands ## Commands
+223
View File
@@ -0,0 +1,223 @@
<?xml version="1.0" encoding="utf-8"?>
<style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" version="1.0" default-locale="en-US" demote-non-dropping-particle="sort-only">
<info>
<title>Molecular Ecology Modified</title>
<id>http://www.zotero.org/styles/molecular-ecology</id>
<link href="http://www.zotero.org/styles/molecular-ecology" rel="self"/>
<link href="http://www.zotero.org/styles/ecology-letters" rel="template"/>
<link href="http://onlinelibrary.wiley.com/journal/10.1111/%28ISSN%291365-294X/homepage/ForAuthors.html" rel="documentation"/>
<author>
<name>Xiaodong Dang</name>
<email>dangxdong@gmail.com</email>
</author>
<contributor>
<name>Johan Asplund</name>
<email>asplundj@gmail.com</email>
</contributor>
<contributor>
<name>David Kaplan</name>
<email>david.kaplan@ird.fr</email>
</contributor>
<category citation-format="author-date"/>
<category field="biology"/>
<issn>0962-1083</issn>
<eissn>1365-294X</eissn>
<updated>2012-09-09T22:24:43+00:00</updated>
<rights license="http://creativecommons.org/licenses/by-sa/3.0/">This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License</rights>
</info>
<macro name="editor-translator">
<names variable="editor translator" prefix=" (" delimiter=", " suffix=")">
<name initialize-with="" delimiter=", "/>
<label form="short" prefix=", " text-case="capitalize-first" suffix="," strip-periods="true"/>
</names>
</macro>
<macro name="author">
<names variable="author">
<name name-as-sort-order="all" sort-separator=" " initialize-with="" delimiter=", " delimiter-precedes-et-al="never"/>
<label form="short" prefix=" (" suffix=")" text-case="capitalize-first"/>
<et-al font-style="italic"/>
<substitute>
<names variable="editor"/>
<names variable="translator"/>
<text macro="title"/>
</substitute>
</names>
</macro>
<macro name="author-short">
<names variable="author">
<name form="short" and="symbol" delimiter=", " initialize-with=". "/>
<et-al font-style="italic"/>
<substitute>
<names variable="editor"/>
<names variable="translator"/>
<choose>
<if type="bill book graphic legal_case legislation motion_picture report song" match="any">
<text variable="title" form="short" font-style="italic"/>
</if>
<else>
<text variable="title" form="short" quotes="true"/>
</else>
</choose>
</substitute>
</names>
</macro>
<macro name="title">
<choose>
<if type="bill book graphic legal_case legislation motion_picture report song" match="any">
<text variable="title" font-style="italic"/>
</if>
<else>
<text variable="title"/>
</else>
</choose>
</macro>
<macro name="access-detail">
<group delimiter=" ">
<text variable="URL" prefix="Available at: "/>
<group prefix="(" suffix=")" delimiter=" ">
<text term="accessed"/>
<date variable="accessed">
<date-part name="day" suffix=" "/>
<date-part name="month" form="long" suffix=" "/>
<date-part name="year"/>
</date>
</group>
</group>
</macro>
<macro name="access">
<choose>
<if type="webpage post post-weblog entry entry-encyclopedia dataset software report manuscript document" match="any">
<text macro="access-detail"/>
</if>
<else-if variable="accessed">
<text macro="access-detail"/>
</else-if>
</choose>
</macro>
<macro name="access-fallback">
<group delimiter=" ">
<choose>
<if variable="URL">
<text macro="access-detail" suffix="."/>
</if>
<else-if variable="publisher">
<text variable="publisher" prefix="Available at: " suffix="."/>
</else-if>
</choose>
<text variable="note" suffix="."/>
</group>
</macro>
<macro name="issued-year">
<choose>
<if variable="issued">
<date variable="issued">
<date-part name="year"/>
</date>
</if>
<else>
<text term="no date" form="short"/>
</else>
</choose>
</macro>
<macro name="publisher">
<group delimiter=", ">
<text variable="publisher"/>
<text variable="publisher-place"/>
</group>
</macro>
<citation collapse="year-suffix" et-al-min="3" et-al-use-first="1" disambiguate-add-year-suffix="true">
<sort>
<key variable="issued"/>
<key variable="author"/>
</sort>
<layout prefix="(" suffix=")" delimiter="; ">
<group delimiter=" ">
<text macro="author-short"/>
<text macro="issued-year"/>
<group>
<label variable="locator" form="short"/>
<text variable="locator" prefix=" "/>
</group>
</group>
</layout>
</citation>
<bibliography hanging-indent="true" et-al-min="6" et-al-use-first="1000" entry-spacing="0.5" line-spacing="1">
<sort>
<key macro="author-short"/>
<key variable="issued"/>
</sort>
<layout>
<text macro="author" suffix=" "/>
<text macro="issued-year" prefix="(" suffix=")"/>
<choose>
<if type="bill book graphic legal_case legislation motion_picture report song" match="any">
<group suffix=".">
<text macro="title" prefix=" "/>
<text macro="editor-translator" prefix=" "/>
</group>
<text prefix=" " suffix="." macro="publisher"/>
<text macro="access" prefix=" " suffix="."/>
</if>
<else-if type="thesis" match="any">
<group suffix=".">
<text macro="title" prefix=" " suffix="."/>
<text variable="genre" prefix=" " suffix=" Thesis."/>
<text prefix=" " macro="publisher"/>
</group>
<text macro="access" prefix=" " suffix="."/>
</else-if>
<else-if type="chapter paper-conference" match="any">
<text macro="title" prefix=" "/>
<group prefix=".">
<group prefix=" In:">
<text variable="container-title" font-style="italic" prefix=" "/>
<text variable="collection-title" prefix=" " suffix="."/>
<names variable="editor translator" prefix=" (" delimiter=", " suffix=")">
<label form="short" suffix=" " strip-periods="true"/>
<name name-as-sort-order="all" sort-separator=" " initialize-with="" delimiter=", " delimiter-precedes-last="never"/>
</names>
<group suffix=".">
<label variable="page" form="short" prefix=", " suffix=" "/>
<text variable="page"/>
<text macro="publisher" prefix=". " suffix="."/>
</group>
</group>
</group>
</else-if>
<else-if type="webpage post post-weblog entry entry-encyclopedia dataset software" match="any">
<group suffix=".">
<text macro="title" prefix=" "/>
<text macro="editor-translator" prefix=" "/>
</group>
<group prefix=" " suffix=".">
<text variable="container-title" text-case="title" font-style="italic"/>
<text variable="genre" prefix=", "/>
<text macro="publisher" prefix=". "/>
</group>
<text macro="access" prefix=" " suffix="."/>
</else-if>
<else>
<group suffix=".">
<text macro="title" prefix=" "/>
<text macro="editor-translator" prefix=" "/>
</group>
<group prefix=" " suffix=".">
<text variable="container-title" text-case="title" font-style="italic"/>
<group prefix=", ">
<text variable="volume" font-weight="bold"/>
</group>
<text variable="page" prefix=", "/>
</group>
<choose>
<if variable="container-title">
<text macro="access" prefix=" " suffix="."/>
</if>
<else>
<text macro="access-fallback" prefix=" "/>
</else>
</choose>
</else>
</choose>
</layout>
</bibliography>
</style>
+598
View File
@@ -259,3 +259,601 @@
url = {https://doi.org/10.1186/s12864-015-1647-5}, url = {https://doi.org/10.1186/s12864-015-1647-5},
volume = 16, volume = 16,
year = 2015} year = 2015}
@article{Roberts2004-rz,
title = "{Reducing storage requirements for biological sequence
comparison}",
author = "Roberts, Michael and Hayes, Wayne and Hunt, Brian R and Mount,
Stephen M and Yorke, James A",
journal = "Bioinformatics (Oxford, England)",
publisher = "Oxford University Press (OUP)",
volume = 20,
number = 18,
pages = "3363--3369",
abstract = "MOTIVATION: Comparison of nucleic acid and protein sequences is a
fundamental tool of modern bioinformatics. A dominant method of
such string matching is the 'seed-and-extend' approach, in which
occurrences of short subsequences called 'seeds' are used to
search for potentially longer matches in a large database of
sequences. Each such potential match is then checked to see if it
extends beyond the seed. To be effective, the seed-and-extend
approach needs to catalogue seeds from virtually every substring
in the database of search strings. Projects such as mammalian
genome assemblies and large-scale protein matching, however, have
such large sequence databases that the resulting list of seeds
cannot be stored in RAM on a single computer. This significantly
slows the matching process. RESULTS: We present a simple and
elegant method in which only a small fraction of seeds, called
'minimizers', needs to be stored. Using minimizers can speed up
string-matching computations by a large factor while missing only
a small fraction of the matches found using all seeds.",
month = dec,
year = 2004,
url = "https://dx.doi.org/10.1093/bioinformatics/bth408",
doi = "10.1093/bioinformatics/bth408",
pmid = 15256412,
issn = "1367-4803,1367-4811",
language = "en"
}
@INPROCEEDINGS{Steele2014-cz,
title = "{Fast splittable pseudorandom number generators}",
author = "Steele, Jr, Guy L and Lea, Doug and Flood, Christine H",
booktitle = "{Proceedings of the 2014 ACM International Conference on Object
Oriented Programming Systems Languages \& Applications}",
publisher = "ACM",
address = "New York, NY, USA",
abstract = "We describe a new algorithm SplitMix for an object-oriented and
splittable pseudorandom number generator (PRNG) that is quite
fast: 9 64-bit arithmetic/logical operations per 64 bits
generated. A conventional linear PRNG object provides a generate
method that returns one pseudorandom value and updates the state
of the PRNG, but a splittable PRNG object also has a second
operation, split, that replaces the original PRNG object with two
(seemingly) independent PRNG objects, by creating and returning a
new such object and updating the state of the original object.
Splittable PRNG objects make it easy to organize the use of
pseudorandom numbers in multithreaded programs structured using
fork-join parallelism. No locking or synchronization is required
(other than the usual memory fence immediately after object
creation). Because the generate method has no loops or
conditionals, it is suitable for SIMD or GPU implementation. We
derive SplitMix from the DotMix algorithm of Leiserson, Schardl,
and Sukha by making a series of program transformations and
engineering improvements. The end result is an object-oriented
version of the purely functional API used in the Haskell library
for over a decade, but SplitMix is faster and produces
pseudorandom sequences of higher quality; it is also far superior
in quality and speed to java.util.Random, and has been included
in Java JDK8 as the class java.util.SplittableRandom. We have
tested the pseudorandom sequences produced by SplitMix using two
standard statistical test suites (DieHarder and TestU01) and they
appear to be adequate for ``everyday'' use, such as in Monte
Carlo algorithms and randomized data structures where speed is
important.",
month = oct,
year = 2014,
url = "http://dx.doi.org/10.1145/2660193.2660195",
doi = "10.1145/2660193.2660195",
isbn = 9781450325851
}
@online{Stafford2011,
author = {Stafford, David},
title = {Better Bit Mixing - Improving on MurmurHash3's 64-bit Finalizer},
date = {2011-09-28},
url = {https://zimbry.blogspot.com/2011/09/better-bit-mixing-improving-on.html},
urldate = {2026-09-12}
}
@ARTICLE{Hamming1950-cw,
title = "{Error detecting and error correcting codes}",
author = "Hamming, R W",
journal = "The Bell System Technical Journal",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
volume = 29,
number = 2,
pages = "147--160",
abstract = "The author was led to the study given in this paper from a
consideration of large scale computing machines in which a large
number of operations must be performed without a single error in
the end result. This problem of “doing things right” on a large
scale is not essentially new; in a telephone central office, for
example, a very large number of operations are performed while
the errors leading to wrong numbers are kept well under control,
though they have not been completely eliminated. This has been
achieved, in part, through the use of self-checking circuits. The
occasional failure that escapes routine checking is still
detected by the customer and will, if it persists, result in
customer complaint, while if it is transient it will produce only
occasional wrong numbers. At the same time the rest of the
central office functions satisfactorily. In a digital computer,
on the other hand, a single failure usually means the complete
failure, in the sense that if it is detected no more computing
can be done until the failure is located and corrected, while if
it escapes detection then it invalidates all subsequent
operations of the machine. Put in other words, in a telephone
central office there are a number of parallel paths which are
more or less independent of each other; in a digital machine
there is usually a single long path which passes through the same
piece of equipment many, many times before the answer is
obtained.",
month = apr,
year = 1950,
url = "http://dx.doi.org/10.1002/j.1538-7305.1950.tb00463.x",
doi = "10.1002/j.1538-7305.1950.tb00463.x",
issn = "0005-8580"
}
@ARTICLE{Ondov2016-dq,
title = "{Mash: fast genome and metagenome distance estimation using
{MinHash}}",
author = "Ondov, Brian D and Treangen, Todd J and Melsted, Páll and
Mallonee, Adam B and Bergman, Nicholas H and Koren, Sergey and
Phillippy, Adam M",
journal = "Genome biology",
volume = 17,
number = 1,
pages = 132,
abstract = "Mash extends the MinHash dimensionality-reduction technique to
include a pairwise mutation distance and P value significance
test, enabling the efficient clustering and search of massive
sequence collections. Mash reduces large sequences and sequence
sets to small, representative sketches, from which global mutation
distances can be rapidly estimated. We demonstrate several use
cases, including the clustering of all 54,118 NCBI RefSeq genomes
in 33 CPU h; real-time database search using assembled or
unassembled Illumina, Pacific Biosciences, and Oxford Nanopore
data; and the scalable clustering of hundreds of metagenomic
samples by composition. Mash is freely released under a BSD
license ( https://github.com/marbl/mash ).",
month = jun,
year = 2016,
url = "http://dx.doi.org/10.1186/s13059-016-0997-x",
keywords = "Alignment; Comparative genomics; Genomic distance; Metagenomics;
Nanopore; Sequencing",
doi = "10.1186/s13059-016-0997-x",
pmc = "PMC4915045",
pmid = 27323842,
issn = "1465-6906",
language = "en"
}
@ARTICLE{Bray1957-vv,
title = "{An ordination of the upland forest communities of southern
Wisconsin}",
author = "Bray, J Roger and Curtis, J T",
journal = "Ecological Monographs",
publisher = "Wiley",
volume = 27,
number = 4,
pages = "325--349",
month = oct,
year = 1957,
url = "http://dx.doi.org/10.2307/1942268",
doi = "10.2307/1942268",
issn = "0012-9615,1557-7015",
language = "en"
}
@ARTICLE{Gower1986-ri,
title = "{Metric and Euclidean properties of dissimilarity coefficients}",
author = "Gower, J C and Legendre, P",
journal = "Journal of Classification",
publisher = "Springer Science and Business Media LLC",
volume = 3,
number = 1,
pages = "5--48",
abstract = "We assemble here properties of certain dissimilarity coefficients
and are specially concerned with their metric and Euclidean
status. No attempt is made to be exhaustive as far as
coefficients are concerned, but certain mathematical results that
we have found useful are presented and should help establish
similar properties for other coefficients. The response to
different types of data is investigated, leading to guidance on
the choice of an appropriate coefficient.",
month = mar,
year = 1986,
url = "http://dx.doi.org/10.1007/bf01896809",
doi = "10.1007/bf01896809",
issn = "0176-4268,1432-1343",
language = "en"
}
@ARTICLE{Legendre2001-cq,
title = "{Ecologically meaningful transformations for ordination of species
data}",
author = "Legendre, Pierre and Gallagher, Eugene D",
journal = "Oecologia",
volume = 129,
number = 2,
pages = "271--280",
abstract = "This paper examines how to obtain species biplots in unconstrained
or constrained ordination without resorting to the Euclidean
distance [used in principal-component analysis (PCA) and
redundancy analysis (RDA)] or the chi-square distance [preserved
in correspondence analysis (CA) and canonical correspondence
analysis (CCA)] which are not always appropriate for the analysis
of community composition data. To achieve this goal,
transformations are proposed for species data tables. They allow
ecologists to use ordination methods such as PCA and RDA, which
are Euclidean-based, for the analysis of community data, while
circumventing the problems associated with the Euclidean distance,
and avoiding CA and CCA which present problems of their own in
some cases. This allows the use of the original (transformed)
species data in RDA carried out to test for relationships with
explanatory variables (i.e. environmental variables, or factors of
a multifactorial analysis-of-variance model); ecologists can then
draw biplots displaying the relationships of the species to the
explanatory variables. Another application allows the use of
species data in other methods of multivariate data analysis which
optimize a least-squares loss function; an example is K-means
partitioning.",
month = oct,
year = 2001,
url = "http://dx.doi.org/10.1007/s004420100716",
keywords = "Biplot diagram; Canonical correspondence analysis; Correspondence
analysis; Principal-component analysis; Redundancy analysis",
doi = "10.1007/s004420100716",
pmid = 28547606,
issn = "0029-8549,1432-1939",
language = "en"
}
@ARTICLE{Anderson2011-rq,
title = "{Navigating the multiple meanings of β diversity: a roadmap for
the practicing ecologist}",
author = "Anderson, Marti J and Crist, Thomas O and Chase, Jonathan M and
Vellend, Mark and Inouye, Brian D and Freestone, Amy L and
Sanders, Nathan J and Cornell, Howard V and Comita, Liza S and
Davies, Kendi F and Harrison, Susan P and Kraft, Nathan J B and
Stegen, James C and Swenson, Nathan G",
journal = "Ecology Letters",
publisher = "Wiley",
volume = 14,
number = 1,
pages = "19--28",
abstract = "A recent increase in studies of β diversity has yielded a
confusing array of concepts, measures and methods. Here, we
provide a roadmap of the most widely used and ecologically
relevant approaches for analysis through a series of mission
statements. We distinguish two types of β diversity: directional
turnover along a gradient vs. non-directional variation.
Different measures emphasize different properties of ecological
data. Such properties include the degree of emphasis on
presence/absence vs. relative abundance information and the
inclusion vs. exclusion of joint absences. Judicious use of
multiple measures in concert can uncover the underlying nature of
patterns in β diversity for a given dataset. A case study of
Indonesian coral assemblages shows the utility of a multi-faceted
approach. We advocate careful consideration of relevant
questions, matched by appropriate analyses. The rigorous
application of null models will also help to reveal potential
processes driving observed patterns in β diversity.",
month = jan,
year = 2011,
url = "http://dx.doi.org/10.1111/j.1461-0248.2010.01552.x",
doi = "10.1111/j.1461-0248.2010.01552.x",
pmid = 21070562,
issn = "1461-023X,1461-0248",
language = "en"
}
@ARTICLE{Jaccard1901-mx,
title = "{Étude comparative de la distribution florale dans une portion
des Alpes et du Jura}",
author = "Jaccard, Paul",
journal = "Bulletin de la Société vaudoise des sciences naturelles",
publisher = "Imprimerie Corbaz \& Comp.",
volume = 37,
number = 142,
pages = "547--579",
abstract = "Schweizer Zeitschriften online - Ein Service der ETH-Bibliothek.
Revues suisses en ligne - Un service de ETH Library. Swiss
journals online - A service by ETH Library.",
year = 1901,
url = "http://dx.doi.org/10.5169/seals-266450",
doi = "10.5169/seals-266450",
issn = "0037-9603",
language = "de"
}
@ARTICLE{Kosub2019-xt,
title = "{A note on the triangle inequality for the Jaccard distance}",
author = "Kosub, Sven",
journal = "Pattern Recognition Letters",
publisher = "Elsevier BV",
volume = 120,
pages = "36--38",
month = apr,
year = 2019,
url = "http://dx.doi.org/10.1016/j.patrec.2018.12.007",
doi = "10.1016/j.patrec.2018.12.007",
issn = "0167-8655,1872-7344",
language = "en"
}
@ARTICLE{Fleischmann2014-ed,
title = {Evolution of genome size and chromosome number in the
carnivorous plant genus Genlisea (Lentibulariaceae), with a new
estimate of the minimum genome size in angiosperms},
author = "Fleischmann, Andreas and Michael, Todd P and Rivadavia, Fernando
and Sousa, Aretuza and Wang, Wenqin and Temsch, Eva M and
Greilhuber, Johann and Müller, Kai F and Heubl, Günther",
journal = "Annals of Botany",
publisher = "Oxford University Press (OUP)",
volume = 114,
number = 8,
pages = "1651--1663",
abstract = "BACKGROUND AND AIMS: Some species of Genlisea possess ultrasmall
nuclear genomes, the smallest known among angiosperms, and some
have been found to have chromosomes of diminutive size, which may
explain why chromosome numbers and karyotypes are not known for
the majority of species of the genus. However, other members of
the genus do not possess ultrasmall genomes, nor do most taxa
studied in related genera of the family or order. This study
therefore examined the evolution of genome sizes and chromosome
numbers in Genlisea in a phylogenetic context. The correlations
of genome size with chromosome number and size, with the
phylogeny of the group and with growth forms and habitats were
also examined. METHODS: Nuclear genome sizes were measured from
cultivated plant material for a comprehensive sampling of taxa,
including nearly half of all species of Genlisea and representing
all major lineages. Flow cytometric measurements were conducted
in parallel in two laboratories in order to compare the
consistency of different methods and controls. Chromosome counts
were performed for the majority of taxa, comparing different
staining techniques for the ultrasmall chromosomes. KEY RESULTS:
Genome sizes of 15 taxa of Genlisea are presented and interpreted
in a phylogenetic context. A high degree of congruence was found
between genome size distribution and the major phylogenetic
lineages. Ultrasmall genomes with 1C values of <100 Mbp were
almost exclusively found in a derived lineage of South American
species. The ancestral haploid chromosome number was inferred to
be n = 8. Chromosome numbers in Genlisea ranged from 2n = 2x = 16
to 2n = 4x = 32. Ascendant dysploid series (2n = 36, 38) are
documented for three derived taxa. The different ploidy levels
corresponded to the two subgenera, but were not directly
correlated to differences in genome size; the three different
karyotype ranges mirrored the different sections of the genus.
The smallest known plant genomes were not found in G. margaretae,
as previously reported, but in G. tuberosa (1C ≈ 61 Mbp) and some
strains of G. aurea (1C ≈ 64 Mbp). CONCLUSIONS: Genlisea is an
ideal candidate model organism for the understanding of genome
reduction as the genus includes species with both relatively
large (∼1700 Mbp) and ultrasmall (∼61 Mbp) genomes. This
comparative, phylogeny-based analysis of genome sizes and
karyotypes in Genlisea provides essential data for selection of
suitable species for comparative whole-genome analyses, as well
as for further studies on both the molecular and cytogenetic
basis of genome reduction in plants.",
month = dec,
year = 2014,
url = "http://dx.doi.org/10.1093/aob/mcu189",
keywords = "Bladderwort; Genlisea; Lamiales; Lentibulariaceae; carnivorous
plant; chromosome number; flow cytometry; genome miniaturization;
genome size",
doi = "10.1093/aob/mcu189",
pmc = "PMC4649684",
pmid = 25274549,
issn = "0305-7364,1095-8290",
language = "en"
}
@ARTICLE{Fernandez2024-kd,
title = "A 160 Gbp fork fern genome shatters size record for eukaryotes",
author = "Fernández, Pol and Amice, Rémy and Bruy, David and Christenhusz,
Maarten J M and Leitch, Ilia J and Leitch, Andrew L and Pokorny,
Lisa and Hidalgo, Oriane and Pellicer, Jaume",
journal = "iScience",
publisher = "Elsevier BV",
volume = 27,
number = 6,
pages = 109889,
abstract = "Vascular plants are exceptional among eukaryotes due to their
outstanding genome size diversity which ranges ∼2,400-fold,
including the largest genome so far recorded in the angiosperm
Paris japonica (148.89 Gbp/1C). Despite available data showing
that giant genomes are restricted across the Tree of Life, the
biological limits to genome size expansion remain to be
established. Here, we report the discovery of an even larger
eukaryotic genome in Tmesipteris oblanceolata, a New Caledonian
fork fern. At 160.45 Gbp/1C, this record-breaking genome
challenges current understanding and opens new avenues to explore
the evolutionary dynamics of genomic gigantism.",
month = jun,
year = 2024,
url = "http://dx.doi.org/10.1016/j.isci.2024.109889",
keywords = "Plant evolution; Plant genetics",
doi = "10.1016/j.isci.2024.109889",
pmc = "PMC11270024",
pmid = 39055604,
issn = "2589-0042",
language = "en"
}
@ARTICLE{Fraser1995-jc,
title = "The minimal gene complement of Mycoplasma genitalium",
author = "Fraser, C M and Gocayne, J D and White, O and Adams, M D and
Clayton, R A and Fleischmann, R D and Bult, C J and Kerlavage, A
R and Sutton, G and Kelley, J M and Fritchman, R D and Weidman, J
F and Small, K V and Sandusky, M and Fuhrmann, J and Nguyen, D
and Utterback, T R and Saudek, D M and Phillips, C A and Merrick,
J M and Tomb, J F and Dougherty, B A and Bott, K F and Hu, P C
and Lucier, T S and Peterson, S N and Smith, H O and Hutchison,
3rd, C A and Venter, J C",
journal = "Science (New York, N.Y.)",
publisher = "American Association for the Advancement of Science (AAAS)",
volume = 270,
number = 5235,
pages = "397--403",
abstract = "The complete nucleotide sequence (580,070 base pairs) of the
Mycoplasma genitalium genome, the smallest known genome of any
free-living organism, has been determined by whole-genome random
sequencing and assembly. A total of only 470 predicted coding
regions were identified that include genes required for DNA
replication, transcription and translation, DNA repair, cellular
transport, and energy metabolism. Comparison of this genome to
that of Haemophilus influenzae suggests that differences in
genome content are reflected as profound differences in
physiology and metabolic capacity between these two organisms.",
month = oct,
year = 1995,
url = "http://dx.doi.org/10.1126/science.270.5235.397",
doi = "10.1126/science.270.5235.397",
pmid = 7569993,
issn = "0036-8075,1095-9203",
language = "en"
}
@ARTICLE{Schneiker2007-gs,
title = "Complete genome sequence of the myxobacterium Sorangium
cellulosum",
author = "Schneiker, Susanne and Perlova, Olena and Kaiser, Olaf and Gerth,
Klaus and Alici, Aysel and Altmeyer, Matthias O and Bartels,
Daniela and Bekel, Thomas and Beyer, Stefan and Bode, Edna and
Bode, Helge B and Bolten, Christoph J and Choudhuri, Jomuna V and
Doss, Sabrina and Elnakady, Yasser A and Frank, Bettina and
Gaigalat, Lars and Goesmann, Alexander and Groeger, Carolin and
Gross, Frank and Jelsbak, Lars and Jelsbak, Lotte and Kalinowski,
Jörn and Kegler, Carsten and Knauber, Tina and Konietzny,
Sebastian and Kopp, Maren and Krause, Lutz and Krug, Daniel and
Linke, Bukhard and Mahmud, Taifo and Martinez-Arias, Rosa and
McHardy, Alice C and Merai, Michelle and Meyer, Folker and
Mormann, Sascha and Muñoz-Dorado, Jose and Perez, Juana and
Pradella, Silke and Rachid, Shwan and Raddatz, Günter and
Rosenau, Frank and Rückert, Christian and Sasse, Florenz and
Scharfe, Maren and Schuster, Stephan C and Suen, Garret and
Treuner-Lange, Anke and Velicer, Gregory J and Vorhölter,
Frank-Jörg and Weissman, Kira J and Welch, Roy D and Wenzel,
Silke C and Whitworth, David E and Wilhelm, Susanne and Wittmann,
Christoph and Blöcker, Helmut and Pühler, Alfred and Müller, Rolf",
journal = "Nature Biotechnology",
publisher = "Springer Science and Business Media LLC",
volume = 25,
number = 11,
pages = "1281--1289",
abstract = "The genus Sorangium synthesizes approximately half of the
secondary metabolites isolated from myxobacteria, including the
anti-cancer metabolite epothilone. We report the complete genome
sequence of the model Sorangium strain S. cellulosum So ce56,
which produces several natural products and has morphological and
physiological properties typical of the genus. The circular
genome, comprising 13,033,779 base pairs, is the largest
bacterial genome sequenced to date. No global synteny with the
genome of Myxococcus xanthus is apparent, revealing an
unanticipated level of divergence between these myxobacteria. A
large percentage of the genome is devoted to regulation,
particularly post-translational phosphorylation, which probably
supports the strain's complex, social lifestyle. This regulatory
network includes the highest number of eukaryotic protein
kinase-like kinases discovered in any organism. Seventeen
secondary metabolite loci are encoded in the genome, as well as
many enzymes with potential utility in industry.",
month = nov,
year = 2007,
url = "http://dx.doi.org/10.1038/nbt1354",
doi = "10.1038/nbt1354",
pmid = 17965706,
issn = "1087-0156,1546-1696",
language = "en"
}
@incollection{Karlin1985,
author = {Karlin, Samuel and Ost, Fr{\'e}d{\'e}ric},
title = {Maximal segmental match length among random sequences from a finite alphabet},
booktitle = {Proceedings of the Berkeley Conference in Honor of Jerzy Neyman and Jack Kiefer},
editor = {Le Cam, Lucien M. and Olshen, Richard A.},
volume = {1},
pages = {225--243},
year = {1985},
publisher = {Wadsworth},
address = {Monterey, CA}
}
@article{Karlin1988,
author = {Karlin, Samuel and Ost, Fr{\'e}d{\'e}ric},
title = {Maximal length of common words among random letter sequences},
journal = {The Annals of Probability},
volume = {16},
number = {2},
pages = {535--563},
year = {1988}
}
@ARTICLE{Le-Cam1960-pe,
title = "{An approximation theorem for the Poisson binomial distribution}",
author = "Le Cam, Lucien",
journal = "Pacific Journal of Mathematics",
publisher = "Mathematical Sciences Publishers",
volume = 10,
number = 4,
pages = "1181--1197",
month = dec,
year = 1960,
url = "http://dx.doi.org/10.2140/pjm.1960.10.1181",
doi = "10.2140/pjm.1960.10.1181",
issn = "0030-8730,1945-5844"
}
@ARTICLE{Hoeffding1956-bx,
title = "{On the distribution of the number of successes in independent
trials}",
author = "Hoeffding, Wassily",
journal = "The Annals of Mathematical Statistics",
publisher = "Institute of Mathematical Statistics",
volume = 27,
number = 3,
pages = "713--721",
abstract = "Let $S$ be the number of successes in $n$ independent trials, and
let $p_j$ denote the probability of success in the $j$th trial,
$j = 1, 2, \cdots, n$ (Poisson trials). We consider the problem
of finding the maximum and the minimum of $Eg(S),$ the expected
value of a given real-valued function of $S,$ when $ES = np$ is
fixed. It is well known that the maximum of the variance of $S$
is attained when $p_1 = p_2 = \cdots = p_n = p.$ This can be
interpreted as showing that the variability in the number of
successes is highest when the successes are equally probable
(Bernoulli trials). This interpretation is further supported by
the following two theorems, proved in this paper. If $b$ and $c$
are two integers, $0 \leqq b \leqq np \leqq c \leqq n,$ the
probability $P(b \leqq S \leqq c)$ attains its minimum if and
only if $p_1 = p_2 = \cdots = p_n = p,$ unless $b = 0$ and $c =
n$ (Theorem 5, a corollary of Theorem 4, which gives the maximum
and the minimum of $P(S \leqq c)$). If $g$ is a strictly convex
function, $Eg(S)$ attains its maximum if and only if $p_1 = p_2 =
\cdots = p_n = p$ (Theorem 3). These results are obtained with
the help of two theorems concerning the extrema of the expected
value of an arbitrary function $g(S)$ under the condition $ES =
np.$ Theorem 1 gives necessary conditions for the maximum and the
minimum of $Eg(S).$ Theorem 2 gives a partial characterization of
the set of points at which an extremum is attained. Corollary 2.1
states that the maximum and the minimum are attained when $p_1,
p_2, \cdots, p_n$ take on, at most, three different values, only
one of which is distinct from 0 and 1. Applications of Theorems 3
and 5 to problems of estimation and testing are pointed out in
Section 5.",
month = sep,
year = 1956,
url = "http://dx.doi.org/10.1214/aoms/1177728178",
doi = "10.1214/aoms/1177728178",
issn = "0003-4851,2168-8990",
language = "en"
}
@ARTICLE{Gleser1975-yu,
title = "{On the distribution of the number of successes in independent
trials}",
author = "Gleser, Leon Jay",
journal = "Annals of Probability",
publisher = "Institute of Mathematical Statistics",
volume = 3,
number = 1,
pages = "182--188",
abstract = "Let $S$ be the number of successes in $n$ independent Bernoulli
trials, where $p_j$ is the probability of success on the $j$th
trial. Let $\mathbf{p} = (p_1, p_2, \cdots, p_n)$, and for any
integer $c, 0 \leqq c \leqq n$, let $H(c \mid \mathbf{p}) = P\{S
\leqq c\}$. Let $\mathbf{p}^{(1)}$ be one possible choice of
$\mathbf{p}$ for which $E(S) = \lambda$. For any $n \times n$
doubly stochastic matrix $\Pi$, let $\mathbf{p}^{(2)} =
\mathbf{p}^{(1)}\Pi$. Then in the present paper it is shown that
$H(c \mid \mathbf{p}^{(1)}) \leqq H(c \mid \mathbf{p}^{(2)})$ for
$0 \leqq c \leqq \lbrack\lambda - 2\rbrack$, and $H(c \mid
\mathbf{p}^{(1)}) \geqq H(c \mid \mathbf{p}^{(2)})$ for
$\lbrack\lambda + 2\rbrack \leqq c \leqq n$. These results
provide a refinement of inequalities for $H(c \mid \mathbf{p})$
obtained by Hoeffding [3]. Their derivation is achieved by
applying consequences of the partial ordering of majorization.",
month = feb,
year = 1975,
url = "http://dx.doi.org/10.2307/2959277",
doi = "10.1214/aop/1176996461",
issn = "0091-1798,2168-894X"
}
-32
View File
@@ -1,32 +0,0 @@
# Partitioning and indexing architecture
An index is split into a fixed number of **partitions**, each handling an independent, disjoint slice of the kmer space. Partitioning keeps the working set of each stage small enough to process efficiently and enables parallel construction and querying.
## Routing
The canonical minimizer of a super-kmer (see [Minimizer selection](minimizer_selection.md)) is hashed to produce a $p$-bit routing value that selects the destination partition:
```
canonical minimizer → hash(minimizer) → p-bit value → partition index
```
The routing value is recomputed whenever it is needed (during construction and again at query time) rather than stored — it is not part of the on-disk super-kmer representation.
Within a partition, kmers are indexed as plain values via a minimal perfect hash function (see [On-disk storage](../formats/index_layout.md)); the minimizer plays no further role once a super-kmer has reached its partition.
## Why hashing is necessary
A canonical minimizer is an m-mer ($m \in \{9, 11, 13, 15\}$), and its distribution over all possible m-mer values is not uniform — as the lexicographic minimum of a window, small values are systematically over-represented [@Zheng2020-ji; @Zheng2021-cc; @Pan2024-hb; @Kille2023-px; @Golan2025-xf]. Routing directly on the raw minimizer value would therefore produce badly unbalanced partitions.
Hashing the minimizer before routing redistributes this skewed distribution uniformly across partitions. This works reliably because the number of partition-index bits $p$ is chosen well below the number of bits available in the minimizer ($2m$): even with strong bias in the minimizer distribution, the hash has enough entropy margin to absorb it, provided the number of distinct minimizers actually observed is much larger than the number of partitions.
## Parameter guidance
| Minimizer size $m$ | Minimizer bits ($2m$) | Typical partition-index bits $p$ | Partitions |
|----|-----------|-----------|------------|
| 9 | 18 | 6–8 | 64–256 |
| 11 | 22 | 8–10 | 256–1 024 |
| 13 | 26 | 10–12 | 1 024–4 096|
| 15 | 30 | 10–14 | 1 024–16 384|
The number of partitions must satisfy $p \le 2m$, and in practice $p$ is chosen well below that bound to leave a comfortable entropy margin. For $k=31$, $m=13$, $p=10$ (1024 partitions), partition load is well balanced on real genomic data.
@@ -21,8 +21,8 @@ Reverse complement is computed by bit manipulation directly on the packed word,
## Canonical form ## Canonical form
The canonical form of a kmer is the lexicographic minimum of the kmer and its reverse complement: The canonical form of a packed 2-bit sequence is the lexicographic minimum of the sequence and its reverse complement:
$$\text{canonical}(kmer) = \min\big(kmer,\ \text{revcomp}(kmer)\big)$$ $$\text{canonical}(x) = \min\big(x,\ \text{revcomp}(x)\big)$$
Using the canonical form halves the kmer space and makes counting strand-independent: a kmer and its reverse complement are always treated as the same entity, regardless of which DNA strand was sequenced. This is a single operation on the packed representation, so it applies identically regardless of what `x` represents — a kmer (see [Kmers](kmers.md)), an m-mer (see [Minimizer selection](minimizer_selection.md)), or a super-kmer (see [Super-kmers](superkmers.md)). Using the canonical form halves the relevant space and makes counting/selection strand-independent: a sequence and its reverse complement are always treated as the same entity, regardless of which DNA strand was sequenced.
@@ -0,0 +1,28 @@
# Partitioning and indexing architecture
An index is split into a fixed number of **partitions**, each handling an independent, disjoint slice of the kmer space. Partitioning keeps the working set of each stage small enough to process efficiently and enables parallel construction and querying.
## Routing
The canonical minimizer of a super-kmer (see [Minimizer selection](minimizer_selection.md)) is hashed to produce a $p$-bit routing value that selects the destination partition — the low $p$ bits of the minimizer's hash:
```
canonical minimizer → hash(minimizer) → p-bit value → partition index
```
$$\text{partition} = H(\text{minimizer}) \bmod 2^p$$
Within a partition, kmers are indexed as plain values via a minimal perfect hash function (see [On-disk storage](../../formats/index_layout.md)); the minimizer plays no further role once a super-kmer has reached its partition.
## Parameter guidance
Even though $H$ already makes minimizer values well-distributed (see [Minimizer selection](minimizer_selection.md)), choosing $p$ well below the number of bits available in the minimizer ($2m$) leaves a comfortable entropy margin, provided the number of distinct minimizers actually observed is much larger than the number of partitions.
| Minimizer size $m$ | Minimizer bits ($2m$) | Typical partition-index bits $p$ | Partitions |
|----|-----------|-----------|------------|
| 9 | 18 | 6–8 | 64–256 |
| 11 | 22 | 8–10 | 256–1 024 |
| 13 | 26 | 10–12 | 1 024–4 096|
| 15 | 30 | 10–14 | 1 024–16 384|
The number of partitions must satisfy $p \le 2m$, and in practice $p$ is chosen well below that bound to leave a comfortable entropy margin. For $k=31$, $m=13$, $p=10$ (1024 partitions), partition load is well balanced on real genomic data.
+416
View File
@@ -0,0 +1,416 @@
# K-mer size
A k-mer is a DNA sequence of length $k$. OBIKmer is designed to index large k-mers. Here, *large* refers to a k-mer length for which the probability of observing the same k-mer in several genomes by chance alone is sufficiently small. The k-mer length must therefore be large enough that, when a k-mer is observed in several genomes of the dataset, the probability that this shared occurrence is due to chance alone is sufficiently low for the match to be considered evidence of homology.
OBIKmer restricts $k$ to odd values in the range
$$
11 \leq k \leq 31.
$$
These limits result from two different considerations. The upper bound is imposed by the representation used by OBIKmer, whereas the lower bound defines a practical range of k-mer lengths for genome-scale sequence comparisons. This range covers most practical applications: the lower limit is well below the k-mer size that can be considered large, even for the smallest bacterial genomes, whereas the upper limit provides sufficient specificity for most applications, including those involving very large genomes.
## Representation limit
OBIKmer uses two bits to encode each nucleotide. Therefore, a k-mer requires $2k$ bits. To ensure computational efficiency, OBIKmer limits the representation of k-mers to a single 64-bit word, thereby restricting their length.
$$
2k \leq 64,
$$
This gives the hard representation limit: $k \leq 32.$ Furthermore, OBIKmer only considers odd values of $k$, meaning the largest supported k-mer size is $31$.
### K-mer specificity
One simple way to illustrate the effect of k-mer size is to consider a random DNA sequence in which the four nucleotides are independent and equally probable. There are $4^k$ possible k-mers, so a particular k-mer is expected to occur once every $4^k$ positions on average. In a sequence of length $G$, the expected number of occurrences of a particular k-mer is approximately $G \cdot 4^{-k}$. When k is large enough to ensure $4^k >> G$, the chance of a second occurrence of the same k-mer becomes close to zero. Consequently, observing the same k-mer twice can only be explained by a homology relationship, except for low-complexity k-mers, which are overrepresented in genomes.
### Estimating False discovery rate on homology inference
OBIKmer uses k-mers long enough that their occurrence in multiple indexed genomes provides evidence of homology. The corresponding false discovery rate (FDR) can be expressed in terms of the probability of observing a k-mer in at least $R$ of the $S$ indexed genomes under a purely random model.
#### The random model
The random model, or null hypothesis, assumes that the $S$ genomes are unrelated and that each genome is an independent random sequence in which each nucleotide occurs with equal probability. Rejecting this hypothesis for a given k-mer indicates that its presence in multiple genomes is unlikely to be explained by chance alone, providing evidence for homology.
For a genome of size $G$, the number of occurrences of a given canonical k-mer $K$ is approximated by a Poisson distribution with parameter
$$ \lambda = 2\frac{G}{4^k}, $$
which is also the expected number of occurrences under the random model. The factor of two accounts for k-mer canonicalisation, which halves the k-mer space when $k$ is odd.
The probability of observing at least one occurrence of this k-mer is therefore
$$
\begin{aligned}
P(n_K > 0) &= 1-e^{-\lambda} \\
&= 1-e^{-2G/4^k}.
\end{aligned}
$$
Assuming equal genome lengths, the number of genomes containing at least one occurrence of $K$ among the $S$ sequences follows a binomial distribution. The probability of observing $K$ in at least $r$ genomes is therefore
$$
P(X \geq r)=\sum_{j=r}^{S}\binom{S}{j}\left(1-e^{-2G/4^k}\right)^j\left(e^{-2G/4^k}\right){S-j}.
$$
This sum is the regularized incomplete beta function $I_p(r,\,S-r+1)$, where
$$
p = 1-e^{-2G/4^k}.
$$
Different genome sizes
When genome sizes differ, the probability of observing a given k-mer also differs between genomes. A simple approximation is to replace the individual genome sizes $G_i$ by their mean
$$ \bar G = \frac{1}{S}\sum_{i=1}^{S}G_i. $$
This gives a common probability
$$ \bar p = 1-e^{-2\bar G/4^k}, $$
and the number of genomes containing the k-mer can then be approximated by a binomial distribution:
$$ P(X\geq r)=\sum_{j=r}^{S}\binom{S}{j}\bar p^j(1-\bar p)^{S-j}. $$
This approximation is conservative for the upper tail. Hoeffding [-@Hoeffding1956-bx, p. 717, Eq. 26] shows that, for a fixed mean, the binomial upper tail is at least as large as the corresponding Poisson-binomial tail for
$$ r\geq S\bar p+1. $$
Using the mean genome size therefore provides a conservative estimate of the FDR.
When genome sizes differ substantially, however, this approximation can become overly conservative. In that case, the exact Poisson-binomial distribution can be computed directly from the individual genome-specific probabilities $p_i$.
### Exact tail probability
With genome-specific probabilities $p_i$, the number of genomes containing the k-mer follows a Poisson-binomial distribution. Writing the probability of exactly $j$ presences as a sum over all subsets of $j$ genomes would be impractical, since there can be up to $2^S$ subsets. The distribution can instead be obtained by adding the genomes one at a time.
Let $d_j$ be the probability that exactly $j$ of the genomes processed so far contain the k-mer. Adding genome $i$ leaves $j$ unchanged if the genome does not contain the k-mer, and moves $j-1$ to $j$ if it does:
$$
\left \{
\begin{aligned}
d'_j &= d_j(1-p_i) + d_{j-1}p_i, \\
d_0&=1
\end{aligned}
\right .
$$
before processing the first genome.
The table $d$ only needs to record how many genomes contain the k-mer, not which ones, reducing the computational cost to $O(S^2)$. The result is independent of the order in which the genomes are processed and of the k-mer itself, so it can be computed once per index. The upper tail is then
$$
P(X\geq r)=1-\sum_{j=0}^{r-1}d_j.
$$
Only $d_0,\ldots,d_{r-1}$ are needed, reducing the cost to $O(Sr)$.
When all $p_i$ are small, as is typically the case for large $k$, the Poisson-binomial distribution can also be approximated by a Poisson distribution with mean
$$
\lambda=\sum_{i=1}^{S}p_i.
$$
The approximation error is bounded in terms of $\sum_i p_i^2$ by Le Cam's inequality [@LeCam1960-pe].
*******
This probability decreases by a factor of four for every additional nucleotide in the k-mer. Conversely, it increases linearly with the amount of sequence searched.
This simple model already shows why very short k-mers provide limited specificity for genome-scale analyses. With $k=11$,
$$
4^{11}\simeq4.2\times10^6,
$$
which is a small combinatorial space even compared with the size of very small bacterial genomes. In contrast,
$$
4^{31}\simeq4.6\times10^{18},
$$
which is vastly larger than the number of k-mer positions even in very large genomes. Thus, increasing $k$ from 11 to 31 provides an enormous increase in sequence specificity.
The estimate above is intentionally simplistic. Real genomes do not consist of independent, equiprobable nucleotides: nucleotide composition and sequence dependencies affect the probability of observing particular words. More accurate estimates of the probability of observing matches by chance therefore take sequence length and nucleotide composition into account.
Karlin and Ost provide an analytical framework for this problem based on the distribution of the longest exact match expected between random sequences. If $L_{\max}$ denotes the length of the longest seed observed in random sequences of given size and nucleotide composition, the corresponding seed-level probability is
$$
P_{\mathrm{seeds}}(L)=P(L_{\max}\geq L).
$$
Conversely, for a chosen false-positive probability $P$, one can determine the minimum seed length $L_{\min}$ such that matches of length $L_{\min}$ or greater are not expected to occur by chance. This is the approach used by Repseek to determine statistically significant seed lengths.
The simple $G/4^k$ estimate and the Karlin–Ost statistics therefore describe the same fundamental effect at different levels of approximation: the probability of a chance match decreases rapidly with k-mer length, while the amount of sequence being searched increases the opportunity for such matches.
Consequently, the appropriate value of $k$ depends on the total amount of sequence being compared and its nucleotide composition. Choosing $k$ appropriately allows the false-positive rate of homology inference to be controlled.
Considering that bacterial genomes are typically a few megabases long, with the smallesr plublished today *Mycoplasma genitalium* having a size $G=580\,Mb$ [@Fraser1995-jc], and the largest $13\,Mb$ in *Sorangium cellulosum* [@Schneiker2007-gs]. For such genomes, the space of 11-mers is already to small to get a reasonable false positive rate:
$$
\begin{aligned}
P(C\geq1) &= 1- e^{-\frac{580.000^2}{2 \cdot 4^{11}}} \\
&\simeq 1
\end{aligned}
$$
, whereas 21-mers already provide a space of several trillion possible sequences.
Plant genomes illustrate the opposite situation. Plant genome sizes span several orders of magnitude, from the smallest angiosperm genomes present in the carnivorous plans genus [@Fleischmann2014-ed] about 60 Mb to the largest one 160 Gb in Tmesipteris oblanceolata, a New Caledonian fork fern [@Fernandez2024-kd], and large genomes often contain substantial amounts of repeated sequence. Even at $k=31$, however, the theoretical k-mer space remains vastly larger than any individual genome. At these lengths, the limiting factor is therefore not exhaustion of the theoretical k-mer space but the biological repetitiveness and non-random composition of the genome.
For example, the number of possible k-mers grows as follows:
| $k$ | $4^k$ | $4^k/2$ after canonicalization |
| ----: | --------------------: | -------------------------------: |
| 11 | $4.19\times10^6$ | $2.10\times10^6$ |
| 15 | $1.07\times10^9$ | $5.37\times10^8$ |
| 21 | $4.40\times10^{12}$ | $2.20\times10^{12}$ |
| 25 | $1.13\times10^{15}$ | $5.63\times10^{14}$ |
| 31 | $4.61\times10^{18}$ | $2.31\times10^{18}$ |
Canonicalization approximately halves the number of possible representations because a k-mer and its reverse complement are represented by the same canonical form.
The distinction between the simple $4^k$ model and the Karlin--Ost framework is important. The former describes the size of the combinatorial k-mer space; the latter describes the probability of observing long matches in sequences whose composition may depart from the uniform random model. Consequently, the value of $k$ cannot be selected from genome size alone.
These scales have very different implications for different genome sizes.
The random-sequence calculation is only a null model. Real genomes exhibit strong and reproducible oligonucleotide composition biases. Karlin and colleagues showed that relative abundances of short oligonucleotides, in particular dinucleotides, form characteristic genomic signatures that remain relatively stable within genomes and differ between organisms [@Karlin1995; @Karlin1997]. More generally, short k-mer frequencies can therefore capture compositional properties of genomes rather than provide highly specific sequence identifiers.
This distinction is important for whole-genome k-mer comparison. Increasing $k$ increases the theoretical diversity of the k-mer space exponentially and generally increases the proportion of k-mers that occur at unique genomic positions. Conversely, shorter k-mers occur more frequently and are more strongly influenced by genomic composition and repeated sequence. Empirical studies of k-mer spectra show this transition clearly: for example, k-mers of length $k\leq11$ can behave primarily as genomic-composition signatures, whereas longer k-mers progressively provide greater sequence specificity.
The supported range $11\leq k\leq31$ should therefore be understood as an engineering compromise rather than as a universal biological optimum. Smaller values increase the probability that unrelated genomic regions share the same k-mers, while larger values increase specificity but also make the representation more sensitive to substitutions, indels, and incomplete homology. The appropriate value within this range consequently depends on the biological scale and comparison task.
## Odd k-mer lengths
OBIKmer additionally requires $k$ to be odd. This constraint is independent of the resolution argument above.
For an odd-length DNA sequence, a k-mer cannot be identical to its own reverse complement. Consequently, every k-mer has two distinct orientations, which can be unambiguously collapsed into a canonical representation. For even $k$, self-reverse-complementary sequences exist, so a k-mer can coincide with its own reverse complement.
Odd $k$ is therefore **not required for canonicalization itself**: the canonical form
$$
s^c=\min_{\mathrm{lex}}\left(s,\operatorname{RC}(s)\right)
$$
remains well defined for even $k$. The odd-$k$ restriction instead guarantees that the two orientations are always distinct, which simplifies the representation and orientation handling used by OBIKmer.
## Karlin--Ost (1988) formula
[@Karlin1988] considers $s$ independent stationary letter sequences over a finite alphabet and studies $K_{r,s}(N)$, the length of the longest word common to $r$ of the $s$ sequences, each of length $N$. For i.i.d. equiprobable letters over an alphabet of size $m$ (here $m=4$ for DNA), the characteristic local match parameter reduces to
$$
\lambda^{[r]} = m^{1-r},
$$
so for $r=2$ (a word shared by two occurrences), $\lambda = m^{-1} = 1/4$.
The expected number of common words of length $k$ among the $\binom{s}{r}$ relevant groups of sequences is
$$
S_1(N,k) = N^{r}\binom{s}{r}\gamma\,\lambda^{k}\,(1+o(1)),
$$
with $\gamma=1$ exactly in the i.i.d. equiprobable case. Theorem 2.2 gives the limiting distribution of $K_{r,s}(N)$, with $k$ set on the scale $k=\left[\dfrac{\log N^{r}}{-\log\lambda^{*}}+x+1\right]$:
$$
\lim_{N\to\infty}\left[\Pr\{K_{r,s}(N)<k\} - \exp\{-(1-\lambda^{*})\,S_1(N,k)\}\right] = 0,
$$
equivalently
$$
\frac{-\log\Pr\{K_{r,s}(N)<k\}}{(\lambda^{*})^{\rho(N,x)}} \xrightarrow[N\to\infty]{} (1-\lambda^{*})\,\gamma^{*}(\lambda^{*})^{x}.
$$
The factor $(1-\lambda^{*})$ multiplying $S_1(N,k)$ is the key correction over the naive pairwise-collision count: it de-clumps overlapping candidate matches, which are not independent events, into an effective Poisson rate. This theorem is stated for $s\geq2$ independent sequences (e.g. comparing two distinct genomes); the intra-sequence self-repeat case (a single genome compared to itself) is treated separately, via the reverse-complement match length $R(N)$, in [@Karlin1985].
$o(1)$ (« petit o de 1 ») désigne une quantité qui **tend vers 0 quand $N\to\infty$**, mais dont on ne précise pas la vitesse exacte ni la formule exacte. C'est une façon d'écrire « il reste un terme d'erreur, mais il devient négligeable ».
Concrètement dans $S_1(N,k) = N^{r}\binom{s}{r}\gamma\,\lambda^{k}\,(1+o(1))$ :
- $N^{r}\binom{s}{r}\gamma\,\lambda^{k}$ est la valeur **exacte à la limite**, celle qu'on utilise en pratique (c'est elle qui redonne $E[C]$ de notre discussion).
- $(1+o(1))$ dit : « la vraie valeur de $S_1(N,k)$ n'est pas *exactement* égale à ce produit pour $N$ fini, mais le rapport entre les deux tend vers 1 quand $N\to\infty$ ». Autrement dit $S_1(N,k) / \left[N^{r}\binom{s}{r}\gamma\lambda^{k}\right] \to 1$.
Pourquoi ce terme existe : la formule $F_\sigma(k)/\lambda^k \to \gamma$ (éq. 2.8 du papier) est elle-même une limite quand $k\to\infty$ — pour $k$ fini, il y a un petit écart entre $F_\sigma(k)$ et $\gamma\lambda^k$. C'est cet écart-là qui devient le $o(1)$.
Ce que ça implique pour l'usage pratique : dans le cas iid équiprobable que tu utilises (ADN, $\gamma=1$ exactement, pas seulement à la limite — je l'ai vérifié directement sur la dérivation : $F_\sigma(k)=m^{-k}=\lambda^k$ pour tout $k$, pas juste asymptotiquement), le $o(1)$ est en réalité **nul** dans ce cas précis, pas juste négligeable. La formule $S_1(N,k)=N^r\binom{s}{r}\lambda^k$ est donc exacte (à l'asymptotique en $N$ près, qui elle vient d'ailleurs — de l'approximation de Poisson elle-même, pas de ce $\gamma$).
Les deux approches sont légitimes, mais elles répondent à des questions différentes — et il y a une relation algébrique exacte entre les deux qui vaut la peine d'être explicitée.
**Ce que calcule l'approche naïve.** Pour **un k-mer $w$ déjà observé et fixé**, $p_i\simeq1-\exp(-G_i/4^k)$ est la probabilité que *ce mot précis* apparaisse quelque part dans le génome $i$ par hasard, et $P(R\geq r)$ (Poisson-binomiale ou binomiale) est la probabilité que *ce mot précis* soit partagé par au moins $r$ des $S$ génomes par hasard. C'est une **p-value par observation** : « j'ai vu ce k-mer particulier dans 5 génomes sur 10, est-ce surprenant pour lui ? »
**Ce que calcule Karlin-Ost.** $S_1(k)$ et $P(K_{r,s}\geq k)$ répondent à : « parmi **tous les $4^k$ mots possibles**, quelle est la probabilité qu'au moins un seul d'entre eux atteigne ce seuil de partage par hasard, n'importe où dans les génomes ? » C'est une question **globale sur tout l'espace des k-mers**, pas sur un mot déjà identifié.
**La relation exacte entre les deux.** Reprenons le cas $r=s=2$, génomes égaux de taille $G$ :
- Naïf (mot $w$ fixé) : $P(R=2\mid w)\simeq p^2=(G\cdot4^{-k})^2=G^2\cdot4^{-2k}$
- Karlin-Ost : $S_1=G^2\cdot4^{-k}$
Le rapport est exactement $S_1 / P(R=2\mid w) = 4^{k}$ — c'est-à-dire le nombre de mots possibles. Ce n'est pas une coïncidence : $S_1=N^r\binom{s}{r}\lambda^k$ vient de $\lambda^k=\sum_w \Pr\{w\}^r$, une somme explicite sur les $4^k$ mots, alors que le calcul naïf tel que présenté ne somme sur rien — il traite $w$ comme donné.
**Donc l'approche naïve, formellement, c'est Karlin-Ost auquel il manque le facteur « nombre de k-mers testés ».** Pour la rendre comparable à la question « dois-je m'attendre à *une* collision fortuite n'importe où dans mon jeu de données », il faudrait une correction à la Bonferroni : multiplier $P(R\geq r\mid w)$ par le nombre effectif de k-mers canoniques testables ($\approx4^k/2$). Karlin-Ost fait cette correction analytiquement et correctement (avec en prime le facteur de déclumping $(1-\lambda)$ qu'on a discuté, qui corrige le sur-comptage des matches chevauchants — une union bound brute comme le Bonferroni décrit ci-dessus le surestimerait légèrement).
**Ce qui veut dire, en pratique, que les deux outils ne sont pas concurrents mais complémentaires :**
- **Choix a priori de $k$ / FPR global du dataset** (la question de `kmers.md` depuis le début de cette conversation) → Karlin-Ost, parce qu'il intègre nativement la multiplicité sur tous les mots possibles.
- **Score de significativité a posteriori pour un k-mer effectivement observé dans l'index** (« ce hit précis, présent dans $r$ génomes sur $S$, est-il compatible avec le hasard ? ») → l'approche Poisson-binomiale est exactement le bon outil, et même préférable à Karlin-Ost pour cet usage : elle gère nativement des $G_i$ inégaux sans les subtilités de convergence du théorème 2.2, et elle donne directement une p-value par hit exploitable pour filtrer les résultats d'un index présence/absence — ce qui correspond bien à l'usage qu'a en tête ton correspondant.
Une seule réserve sur le texte proposé tel quel : $p_i\simeq1-\exp(-G_i/4^k)$ souffre du même biais que celui identifié plus tôt dans notre discussion — un mot de longueur $k$ n'est pas indépendant à chaque position (chevauchement), donc ce $p_i$ est un peu optimiste (légèrement trop haut) pour les mêmes raisons que $E[C]$ l'était. Négligeable pour $k\geq21$, plus discutable à $k=11$.
## Chance sharing across genomes and the FDR of homology
The formulas above ask how likely a match is between two sequences. The question OBIKmer actually has to answer is different: a k-mer is found in $r$ of the $S$ indexed genomes, and one wants to know whether this sharing can be explained by chance or whether it is evidence of homology. This section builds a null model for that question and turns it into a false discovery rate (FDR) for the call "a k-mer shared by at least $r$ genomes is homologous".
### The null model
The null hypothesis is that the $S$ genomes are unrelated, that is, that each one is an independent random sequence. Rejecting it for a k-mer means that chance alone cannot explain why the k-mer is shared, which is the signal of homology one is looking for.
The model only records whether a k-mer is present in a genome, not how many times. Two consequences follow. First, repeats inside a genome are irrelevant, and the size $G_i$ of genome $i$ is its number of **distinct canonical k-mers**. Second, a repeat family shared between genomes is paralogy, which is a form of homology; it is a true positive and not a false one. The only k-mers that could be shared by composition rather than by descent are low-complexity ones, which OBIKmer removes beforehand with its entropy filter.
Everything takes place in canonical space. Because $k$ is odd, no k-mer equals its own reverse complement, so the $4^k$ k-mers pair up perfectly and the space contains exactly
$$
N=\frac{4^k}{2}
$$
canonical k-mers. A given canonical k-mer is present in genome $i$ by chance with probability
$$
p_i = 1-\left(1-\frac1N\right)^{G_i}\simeq \frac{G_i}{N}=\frac{2\,G_i}{4^k}.
$$
This is twice the $G/4^k$ used earlier in this page, because there $G$ is a number of positions on one strand, whereas $G_i$ here counts canonical k-mers, for which both strands are already merged.
Let $R$ be the number of genomes, out of $S$, that contain a given canonical k-mer by chance. Genomes are independent under the null, so $R$ is a sum of independent presence indicators, each with its own probability $p_i$.
### Exact tail probability
When genome sizes differ, the $p_i$ differ, and $R$ follows a Poisson-binomial distribution. Writing the probability of exactly $j$ presences as a sum over all subsets of $j$ genomes would be hopeless, since there are up to $2^S$ subsets. The distribution is instead obtained by adding the genomes one at a time. Let $d_j$ be the probability that exactly $j$ of the genomes processed so far contain the k-mer. Adding genome $i$ leaves $j$ unchanged if the genome does not contain the k-mer, and moves $j-1$ to $j$ if it does:
$$
d'_j = d_j\,(1-p_i) + d_{j-1}\,p_i, \qquad d_0=1 \text{ before the first genome.}
$$
The table $d$ only needs to remember how many genomes were hit, not which ones, and this brings the cost down to $O(S^2)$. The result does not depend on the order in which the genomes are processed. It does not depend on the k-mer either, so it is computed once per index. The upper tail is then
$$
P_0(R\geq r) = 1-\sum_{j=0}^{r-1} d_j .
$$
Only $d_0,\dots,d_{r-1}$ are needed, so the cost is $O(S\,r)$.
### Approximation with equal genome sizes
If all genomes are given the same size, taken as the mean
$$
\bar G=\frac1S\sum_{i=1}^{S}G_i, \qquad \bar p=\frac{2\bar G}{4^k},
$$
then $R$ follows a plain binomial distribution and the tail is
$$
P_0(R\geq r)\simeq\sum_{j=r}^{S}\binom{S}{j}\,\bar p^{\,j}(1-\bar p)^{S-j}.
$$
This sum is the regularized incomplete beta function $I_{\bar p}(r,\,S-r+1)$, available in standard statistical libraries. If it is summed by hand, the terms are obtained one from the next by $t_{j+1}=t_j\,\frac{S-j}{j+1}\,\frac{\bar p}{1-\bar p}$.
A theorem of Hoeffding [@Hoeffding1956-bx] shows that this approximation errs on the safe side. For a fixed mean, the Poisson-binomial distribution is more concentrated than the binomial one, so for $r\geq S\bar p+1$ the binomial tail is never smaller than the exact tail. Using the mean genome size therefore overestimates the chance of sharing and can only make the FDR more pessimistic. Gleser [@Gleser1975-yu] refines this result: replacing the $p_i$ by any partial average of themselves, not only by their full mean, also moves the upper tail towards the binomial one, provided $r-1\geq S\bar p+2$. Grouping genomes of similar size is therefore safe in the same sense. What it loses is power when genome sizes differ by orders of magnitude, since one large genome then weighs as much as several small ones in $\bar p$.
When all $p_i$ are small, which is the case for large $k$, the number of hits is also well approximated by a Poisson distribution of mean $\lambda=\sum_i p_i$, with an error bounded by $\sum_i p_i^2$ [@Le-Cam1960-pe].
For the numerical evaluation, the tail that does not contain the mode $S\bar p$ should be summed directly. When $r>S\bar p$, computing the sum from $j=r$ upwards is accurate even for very small probabilities, whereas computing $1$ minus the sum of the lower terms loses all precision once the tail falls below the machine epsilon.
### False discovery rate
The FDR of the call "present in at least $r$ genomes" is the fraction of retained k-mers expected to be pure chance:
$$
\widehat{\mathrm{FDR}}(r)=\min\!\left(1,\ \frac{N\,P_0(R\geq r)}{n_{\geq r}}\right).
$$
The numerator is the number of k-mers expected to reach $r$ genomes by chance if the genomes were unrelated. Each of the $N$ canonical k-mers has probability $P_0(R\geq r)$ of doing so, and no further correction for multiple testing is needed because the number of tests is already in the product. The denominator $n_{\geq r}$ is the number of distinct k-mers actually observed in at least $r$ genomes, which is read directly from the index. The observed count mixes chance and true homology, so the ratio is an upper bound on the true FDR: it implicitly assumes that all k-mers are null, and it never underestimates the noise. The minimal $r$ for which $\widehat{\mathrm{FDR}}(r)$ falls below the accepted level, for example 5 %, is the sharing threshold to use.
As an illustration, take $k=21$ (so $N=2.2\times10^{12}$), $S=10$ genomes and $G_i=10^9$ distinct canonical k-mers each, hence $p=4.5\times10^{-4}$. The number of k-mers expected to be shared by chance is:
| $r$ | $N\,P_0(R\geq r)$ |
| ---: | ---: |
| 2 | $2\times10^{7}$ |
| 3 | $2.5\times10^{4}$ |
| 4 | $\approx 20$ |
| 5 | $\approx 0.01$ |
Chance alone produces millions of pairwise shared 21-mers at this genome size, a few tens of thousands shared by three genomes, and almost none shared by five or more. Whether a given $r$ is acceptable then depends on how many k-mers the index actually reports at that level.
### Limits of the model
- The FDR is computed per k-mer. Neighbouring k-mers of a shared region overlap and are not independent, so a single homologous region contributes many correlated k-mers. A per-region FDR would count regions instead of k-mers and is not covered here.
- The probability $p_i$ assumes equiprobable, independent nucleotides. The composition biases discussed earlier in this page violate this assumption, and the resulting error is not accounted for.
---
Je n'ai rien modifié. Voici la formalisation des deux points, à valider avant de l'écrire dans `kmers.md`.
## 1. FDR d'un ensemble de k-mers sélectionnés
**Estimation de l'espérance du nombre de faux positifs.** Soit $M$ le nombre de k-mers canoniques testés, $M = 4^k/2$ pour k impair. Soit $q(r)=P(X\ge r)$ la queue du modèle nul. Le nombre attendu de k-mers présents par hasard dans au moins $r$ génomes vaut
$$
E[\mathrm{FP}(r)] = M\,q(r).
$$
Cette égalité est exacte par linéarité de l'espérance, même si les k-mers chevauchants sont dépendants. La dépendance n'affecte que la variance, pas l'espérance. Seule l'approximation de Poisson par génome reste une approximation.
**FDR.** Soit $N(r)=\#\{i : r_i\ge r\}$ le nombre observé de k-mers couvrant au moins $r$ génomes. Alors
$$
\mathrm{FDR}(r)=\min\!\Big(1,\ \frac{M\,q(r)}{N(r)}\Big).
$$
Cette estimation est légèrement conservatrice. Elle suppose $\pi_0=1$, c'est-à-dire que presque tout l'espace $M$ est nul, ce qui est vrai pour k grand.
**Ensemble hétérogène en $r_i$.** Si le jeu n'est pas défini par un seuil unique, on utilise le local fdr par classe de couverture :
$$
\mathrm{fdr}(r)=\frac{M\,P(X=r)}{N_r},\qquad N_r=\#\{i : r_i=r\}.
$$
Le FDR de l'ensemble est alors la moyenne $\frac1N\sum_i \mathrm{fdr}(r_i)$. Pour un ensemble défini par seuil $r_{\min}$, cela redonne exactement la formule précédente.
**Remarque.** $M\,p\approx G$, d'où $E[\mathrm{FP}(r)]\approx\binom{S}{r}\,G^r/M^{r-1}$ en régime de petits $p$. Cela donne une lecture directe de la quantité.
## 2. Markov d'ordre 0 avec fréquences inégales
Soit $\pi_b$ la fréquence du nucléotide $b$. Pour un k-mer $w$ de composition $n=(n_A,n_C,n_G,n_T)$ avec $\sum n_b=k$, on a $P(w)=\prod_b \pi_b^{n_b}$.
**Attendu par génome.** Le k-mer canonique $K=\{w,\overline w\}$ est vu quand le brin direct porte $w$ ou $\overline w$, donc
$$
\lambda_K = G\,\big(P(w)+P(\overline w)\big)=G\Big(\prod_b\pi_b^{n_b}+\pi_A^{n_T}\pi_T^{n_A}\pi_C^{n_G}\pi_G^{n_C}\Big).
$$
Cela ne dépend que de la composition. Si $\pi_A=\pi_T$ et $\pi_C=\pi_G$, on retrouve $2P(w)$.
**Faux positifs.** Le test n'est plus homogène : chaque composition a sa propre $p(n)=1-e^{-\lambda(n)}$. Il faut donc sommer sur les classes de composition (un k-mer et son complément inverse partagent le même $\lambda$, d'où le facteur ½) :
$$
E[\mathrm{FP}(r)]=\frac12\sum_{n}\binom{k}{n_A,n_C,n_G,n_T}\,P\big(X\ge r\mid p(n)\big).
$$
Cette somme porte sur $\binom{k+3}{3}$ compositions, soit 5 984 pour k = 31. Elle est donc légère avec la binomiale de la moyenne, ou avec une Poisson-binomiale par composition si les $G_i$ diffèrent. Si les $\pi_b$ varient d'un génome à l'autre (GC différent), les $p_i(n)$ se construisent par génome.
**Effet attendu.** La moyenne de $\lambda_w$ sur tous les k-mers reste $2G/4^k$, car $\sum_w P(w)=1$. Dans le régime de petits $p$, le terme dominant $\binom{S}{r}p^r$ est convexe en $\lambda$. Par Jensen, le modèle équiprobable est donc le minimum de $E[\mathrm{FP}]$, et la déviation de composition ne peut qu'augmenter le FDR. Les k-mers riches en AT ou GC dominent la somme, ce qui rejoint ton remarque sur la faible complexité. C'est un résultat sur le terme dominant, pas une preuve pour la queue exacte.
**Limites à signaler dans le texte.** Markov 0 ignore les dinucléotides, comme les CpG ou les répétitions, et le $M$ du modèle nul reste celui de l'espace total.
Veux-tu que j'écrive ces deux sections, avec les corrections de numérique évoquées plus haut (`expm1`, somme directe de la queue) ?
@@ -0,0 +1,82 @@
# Minimizer selection
## Definition
The **minimizer** of a k-mer is the canonical form of the m-mer that is smallest according to a chosen ordering among the $k-m+1$ overlapping m-mers contained in the k-mer, with $m<k$ [@Roberts2004-rz]. Canonical form is the same operation defined for a full kmer (see [DNA encoding](encoding.md)), applied here to an m-mer $s$ instead: $s^c = \min_{\mathrm{lex}}\left(s,\operatorname{RC}(s)\right)$.
In **OBIkmer**, canonical m-mers are ordered according to a deterministic hash function $H$ applied to their canonical form:
$$
s_1^c <_h s_2^c
\quad\Longleftrightarrow\quad
H(s_1^c) < H(s_2^c).
$$
Thus, for a k-mer $K$, let
$$
M(K)=(s_1,\ldots,s_{k-m+1})
$$
be its sequence of overlapping m-mers. The minimizer is
$$
\operatorname{minimizer}(K) = s_j^c,
\qquad
j=\underset{i}{\operatorname{argmin}}\;H(s_i^c).
$$
In other words, the hash function defines the ordering of canonical m-mers, while the minimizer itself is the canonical form of the m-mer selected by that ordering.
Applying the minimizer to consecutive k-mers partitions a sequence into super-kmers (see [Super-kmers](superkmers.md)).
## Hash-based minimizer ordering
`obikmer` selects minimizers by hash order rather than plain lexicographic order. Ordering m-mers lexicographically on their 2-bit encoding systematically favors AT-rich m-mers (an all-A m-mer always encodes to 0), which causes low-complexity regions to dominate as minimizers and produces unbalanced partitions [@Zheng2020-ji; @Zheng2021-cc; @Pan2024-hb; @Kille2023-px; @Golan2025-xf].
Instead, a well-distributed hash function $H$ is applied to the canonical (lexicographically minimal) form of each m-mer, and the m-mer with the smallest $H$ value wins. Because $H$ is a bijective mixing function with good avalanche properties [@Steele2014-cz], its output behaves approximately as a composition-independent pseudorandom ordering of distinct m-mers. Under the usual random-hash assumption, each distinct m-mer in a window has approximately the same probability of being the minimum, independently of nucleotide composition.
The canonical form used as input to $H$ is still the lexicographic minimum of forward/reverse-complement — hashing is applied on top of it, not used to redefine it. Defining canonicity by hash value instead would bias the *distribution of hash values themselves* toward small values (the minimum of two independent hashes is not uniformly distributed), reintroducing a bias one layer down.
### Hash function
The hash function \(H\) applies Stafford's 64-bit mixing function, variant 13 [@Stafford2011], to the m-mer encoding XORed with a seed $\sigma$:
```text
H(x):
x ← x ⊕ σ
x ← x ⊕ (x >> 30)
x ← x × 0xbf58476d1ce4e5b9
x ← x ⊕ (x >> 27)
x ← x × 0x94d049bb133111eb
return x ⊕ (x >> 31)
```
The hash uses a fixed non-zero seed
$$ \sigma=\texttt{0x9e3779b97f4a7c15}. $$
The choice of $\sigma$ is not arbitrary. Low-complexity m-mers (homopolymers and short tandem repeats) are disproportionately abundant in real genomes. If one of them happened to be the global argmin of $H$, it could therefore occur as the minimizer in far more windows than expected from the composition-uniform behavior described above. This is not a bias of the mixing function itself, but a consequence of the repeated occurrence of the same input in real sequence data.
In particular, with $\sigma=0$, the all-A m-mer is encoded as $0$, and
$$ \operatorname{Mix13}(0)=0, $$
This makes it the global argmin of the hash function. The non-zero seed eliminates the particular pathological correspondence between the all-A m-mer and the zero output of the mixer.
Exhaustive enumeration of all $4^m$ m-mers confirms that, with $\sigma=\texttt{0x9e3779b97f4a7c15}$, the global argmin is neither a homopolymer nor a periodic repeat for any tested \(m\):
| $m$ | argmin (canonical) | decoded sequence | minimal period |
|---|---|---|---|
| 3 | 16 | `CAA` | 3 |
| 5 | 78 | `ACATG` | 5 |
| 7 | 5512 | `CCCGAGA` | 7 |
| 9 | 108760 | `CGGGATCGA` | 9 |
| 11 | 179014 | `AAGGTGTCACG` | 11 |
| 13 | 33759044 | `GAAATACTTCACA` | 13 |
| 15 | 29869313 | `AACTACTTACCAAAC` | 15 |
When the minimal period of the sequence is $m$, as observed in the table above, the sequence is primitive: it cannot be represented as repetitions of a shorter sequence.
See [Partitioning and indexing architecture](indexing_architecture.md) for how this hash routes a super-kmer to a partition.
@@ -0,0 +1,15 @@
# Super-kmers
A **super-kmer** is a maximal run of consecutive, overlapping kmers from a read that share the same canonical minimizer (see [Minimizer selection](minimizer_selection.md)). Each kmer in the run overlaps the next by $k-1$ nucleotides. A super-kmer is capped at 256 nucleotides; a longer run is split at that boundary.
For a random minimizer of length $m$ over kmers of length $k$, the expected length of a super-kmer is approximately [@Zheng2020-ji; @Golan2025-xf]:
$$L_{\text{nt}} \approx \frac{k-m+2}{2} + k - 1$$
For $k=31$, $m=13$ this is about 40 nucleotides; in practice super-kmers rarely exceed a few dozen nucleotides.
## Canonical super-kmers
A **canonical super-kmer** is the canonical form of a super-kmer (see [DNA encoding](encoding.md)): the lexicographic minimum of the super-kmer and its reverse complement. When a read and its reverse complement are both encountered, they produce super-kmers that are reverse complements of each other; both reduce to the same canonical super-kmer, so a genomic region is represented once regardless of which strand was read.
Super-kmers are the unit of work used throughout construction and querying: sequences are decomposed into super-kmers first, and every downstream step (partition routing, deduplication, counting) operates on them rather than on individual kmers.
-24
View File
@@ -1,24 +0,0 @@
# Kmers and super-kmers
## Kmers
A **kmer** is a DNA subsequence of fixed length $k$. Two constraints apply to $k$, both enforced when a command starts (an invalid value exits immediately with an error):
- $k \in [11, 31]$: long enough to be specific, short enough to fit in a single 64-bit word at 2 bits/base ($k \le 32$ is the hard limit; $k < 11$ gives insufficient specificity).
- $k$ **is odd**: an odd-length sequence can never equal its own reverse complement, so the two orientations of any kmer are always distinct. This is required for the canonical form (see [DNA encoding](encoding.md)) to be well defined.
## Super-kmers
A **super-kmer** is a maximal run of consecutive, overlapping kmers from a read that share the same canonical minimizer (see [Minimizer selection](minimizer_selection.md)). Each kmer in the run overlaps the next by $k-1$ nucleotides. A super-kmer is capped at 256 nucleotides; a longer run is split at that boundary.
For a random minimizer of length $m$ over kmers of length $k$, the expected length of a super-kmer is approximately [@Zheng2020-ji; @Golan2025-xf]:
$$L_{\text{nt}} \approx \frac{k-m+2}{2} + k - 1$$
For $k=31$, $m=13$ this is about 40 nucleotides; in practice super-kmers rarely exceed a few dozen nucleotides.
### Canonical super-kmers
A **canonical super-kmer** is the lexicographic minimum of a super-kmer and its reverse complement. When a read and its reverse complement are both encountered, they produce super-kmers that are reverse complements of each other; both reduce to the same canonical super-kmer, so a genomic region is represented once regardless of which strand was read.
Super-kmers are the unit of work used throughout construction and querying: sequences are decomposed into super-kmers first, and every downstream step (partition routing, deduplication, counting) operates on them rather than on individual kmers.
-42
View File
@@ -1,42 +0,0 @@
# Minimizer selection
## Definition
A **minimizer** of a kmer window is the m-mer ($m < k$) that is smallest, among all $k - m + 1$ overlapping m-mers in the window, under a chosen ordering. The minimizer is always taken in canonical form (lexicographic minimum of forward and reverse complement) so that selection is strand-independent.
The minimizer partitions a sequence into super-kmers: maximal runs of overlapping kmers that share the same minimizer (see [Kmers and super-kmers](kmers_and_superkmers.md)).
## Hash-based ("random") minimizer
`obikmer` selects minimizers by hash order rather than plain lexicographic order. Ordering m-mers lexicographically on their 2-bit encoding systematically favors AT-rich m-mers (an all-A m-mer always encodes to 0), which causes low-complexity regions to dominate as minimizers and produces unbalanced partitions.
Instead, a well-distributed hash function $H$ is applied to the canonical (lexicographically minimal) form of each m-mer, and the m-mer with the smallest $H$ value wins. Because $H$ is a bijection with good avalanche properties, every distinct m-mer in a window has an equal chance of holding the minimum hash value, independent of its nucleotide composition.
The canonical form used as input to $H$ is still the lexicographic minimum of forward/reverse-complement — hashing is applied on top of it, not used to redefine it. Defining canonicity by hash value instead would bias the *distribution of hash values themselves* toward small values (the minimum of two independent hashes is not uniformly distributed), reintroducing a bias one layer down.
### Hash function
The hash function is a 64-bit mixing function (splitmix64-style finalizer) applied to the m-mer XORed with a fixed non-zero seed:
$$H(x) = \text{mix64}(x \oplus s), \quad s = \lfloor 2^{64}/\varphi \rfloor = \texttt{0x9e3779b97f4a7c15}$$
```
H(x):
x ← x ⊕ 0x9e3779b97f4a7c15
x ← x ⊕ (x >> 30)
x ← x × 0xbf58476d1ce4e5b9
x ← x ⊕ (x >> 27)
x ← x × 0x94d049bb133111eb
return x ⊕ (x >> 31)
```
The XOR seed avoids the finalizer's fixed point at 0 ($\text{mix64}(0) = 0$), which would otherwise make an all-A m-mer (canonical value 0) win every window comparison.
## Partition routing is independent of minimizer selection
The hash used to select a minimizer within a window (the minimum of several hash values) and the hash used to route a super-kmer to a storage partition are computed separately:
- **Selection** uses $H$ applied to every candidate m-mer in the window, keeping the minimum.
- **Partition routing** recomputes $H$ on the single selected minimizer only, once its position is fixed. This is a hash of one specific value, not the minimum of several, so it is uniformly distributed and safe to use directly for routing.
See [Partitioning and indexing architecture](indexing_architecture.md) for how the routing value is turned into a partition index.
@@ -0,0 +1,140 @@
# Whole k-mer set distances
The k-mer composition of a genome provides a representation of its sequence content that can be compared directly between genomes. The distances considered here quantify dissimilarity between genomes from their complete k-mer composition, independently of any particular representation, storage scheme, or indexing strategy.
Two complementary classes of comparison arise according to the information retained about k-mer occurrences [@Anderson2011-rq]. **Presence/absence-based distances** consider only whether each distinct k-mer occurs in a genome, whereas **abundance-based distances** also incorporate its observed frequency. Abundance-based measures may be computed either from raw k-mer counts or from the corresponding relative frequencies.
Let $A$ and $B$ denote the k-mer sets of two genomes. For each distinct k-mer $i$, let $c_i^A$ and $c_i^B$ denote its counts in the two genomes, and let
$$
p_i^A=\frac{c_i^A}{\sum_j c_j^A},
\qquad
p_i^B=\frac{c_i^B}{\sum_j c_j^B}
$$
denote the corresponding relative frequencies.
The resulting measures can be classified along two independent dimensions: the **information retained about k-mer occurrences** (presence/absence versus abundance) and the **metric properties** of the resulting dissimilarity, in particular whether the triangle inequality is satisfied.
## Presence/absence-based distances
When only occurrence is retained, each genome is represented by its incidence vector over the k-mer space. The comparison therefore depends exclusively on the presence or absence of each distinct k-mer and is insensitive to its multiplicity.
The **Jaccard distance** compares two k-mer sets from the cardinalities of their intersection and union [@Jaccard1901-mx]:
$$
D = 1 - \frac{\lvert A \cap B \rvert}{\lvert A \cup B \rvert}.
$$
Jaccard distance is a metric and therefore satisfies the triangle inequality [@Kosub2019-xt].
The **Hamming distance** is the $L^1$ distance between the corresponding binary incidence vectors:
$$
D = \sum_i \mathbb{1}[a_i \ne b_i],
$$
where $a_i,b_i\in\{0,1\}$ indicate the presence of k-mer $i$ in the two genomes. It counts the number of k-mers for which the two incidence vectors differ, without normalization by the size of the k-mer space. As an $L^1$ distance, Hamming distance is a metric. Unlike abundance-based measures, it cannot be recovered from k-mer counts alone once the presence/absence representation has been discarded.
**Mash** is not an independent set dissimilarity but a nonlinear transformation of the Jaccard similarity [@Ondov2016-dq]. If
$$
J = 1-D_{\mathrm{Jaccard}},
$$
the Mash distance is defined as
$$
D = -\frac{1}{k}\ln\left(\frac{2J}{1+J}\right)
= -\frac{1}{k}\ln\left(\frac{2(1-J_{\mathrm{Jaccard}})}
{2-J_{\mathrm{Jaccard}}}\right),
$$
with the result clamped to $1.0$ when the Jaccard similarity reaches zero. This transformation is monotone increasing with Jaccard distance and therefore preserves the ordering of pairwise dissimilarities. Monotonicity alone, however, does not guarantee preservation of the triangle inequality. Mash should consequently be regarded as an evolutionary distance estimator derived from k-mer similarity rather than assumed to be a metric.
## Abundance-based distances
When k-mer abundances are retained, genomes are represented by non-negative vectors of k-mer counts or frequencies. Distances can then distinguish genomes that contain the same k-mers but differ in their relative abundances.
The **Euclidean distance** is the ordinary $L^2$ distance between the corresponding vectors. On raw counts it is
$$
D = \sqrt{\sum_i (c_i^A-c_i^B)^2},
$$
and the same definition applied to relative frequencies gives `relfreq-euclidean`. In both cases, Euclidean distance is a metric.
The **Hellinger distance** applies the Euclidean distance to the square-root-transformed relative frequencies [@Legendre2001-cq]:
$$
D =
\frac{1}{\sqrt{2}}\sqrt{\sum_i\left(\sqrt{p_i^A}-\sqrt{p_i^B}\right)^2}.
$$
It is bounded between 0 and 1 and is a metric because it is a positive rescaling of the Euclidean distance between the transformed vectors $\sqrt{p^A}$ and $\sqrt{p^B}$. Its unnormalized form, `hellinger-euclidean`,
$$
\begin{aligned}
D &=\sqrt{\sum_i\left(\sqrt{p_i^A}-\sqrt{p_i^B}\right)^2} \\
&=\sqrt{2}\,D_{\mathrm{Hellinger}},
\end{aligned}
$$
is likewise a metric, since multiplication by a positive constant preserves the triangle inequality.
The **Bray–Curtis dissimilarity** [@Bray1957-vv] is defined from the amount of abundance shared between two vectors:
$$
D = 1-\frac{2\sum_i\min(c_i^A,c_i^B)}{\sum_i c_i^A+\sum_i c_i^B}.
$$
Using
$$
a+b-2\min(a,b)=|a-b|,
$$
this can equivalently be written as
$$
D =
\frac{\sum_i|c_i^A-c_i^B|}
{\sum_i c_i^A+\sum_i c_i^B}.
$$
For arbitrary count vectors, **Bray–Curtis** is not a metric [@Gower1986-ri]: the pair-dependent normalization by the combined abundance can lead to violations of the triangle inequality. This distinguishes it from the $L^1$-based distances above, whose normalization factor is fixed independently of the pair being compared.
The metric property is recovered when all vectors under comparison have the same total abundance $S$. In that case,
$$
\sum_i c_i^A=\sum_i c_i^B=S
$$
for every pair, and **Bray–Curtis** reduces to
$$
D =
\frac{1}{2S}
\sum_i|c_i^A-c_i^B|.
$$
It is therefore a positive rescaling of the $L^1$ distance and is a metric on this fixed-total space.
Relative frequencies satisfy this condition by construction, since
$$
\sum_i p_i^A=\sum_i p_i^B=1.
$$
Consequently, `relfreq-bray-curtis` reduces to
$$
D =
\frac12\sum_i|p_i^A-p_i^B|,
$$
which is the **total variation distance** between the two frequency distributions. It is therefore a metric.
Thus, `bray-curtis` and `relfreq-bray-curtis` have the same algebraic form but operate on different domains: the former compares count vectors whose total abundance may vary between genomes, whereas the latter compares normalized frequency vectors with a fixed total. This difference in normalization is sufficient to change the metric properties of the measure.
See [`phylo`](../../../usage/phylo.md) for how to select a distance and the resulting output formats.
@@ -0,0 +1,85 @@
# Central-position SNP model
## Family
A **family** is the set of up to 4 kmers sharing identical flanking sequence and differing only at the central base — the odd kmer length guarantees a single, well-defined central position (see [Kmers](../../kmer_indexing/kmers.md)). A family is **eligible** for a genome pair $(i,j)$ only if both genomes carry exactly one of its observed forms (single-copy, unambiguous) — this excludes multi-copy and absent loci from the comparison rather than folding them into an undifferentiated "not identical" bucket the way a whole-index distance would.
Conditioning on eligibility this way restricts every comparison to loci that are directly, positively confirmed comparable in both genomes: a locus never enters the statistic because of a genuinely absent homologous region, a diverged paralogous copy, or a genome-size asymmetry — only because a real single-copy substitution (or lack of one) was observed at flanks confirmed intact in both genomes.
## Substitution corrections (`snp-*`)
For a genome pair, let $L$ be its total number of eligible loci, $p$ the raw proportion of substitutions among those loci, $P$/$Q$ the transition/transversion proportions, $Q_1$/$Q_2$ Kimura's two transversion categories (A↔C & G↔T vs. A↔T & C↔G), $P_1$/$P_2$ the purine (A↔G) / pyrimidine (C↔T) transition proportions, and $\pi_A,\pi_C,\pi_G,\pi_T$ the pair's pooled base frequencies.
**`snp-raw`**
$$d = p$$
**`snp-jc`**
$$d = -\frac{3}{4}\ln\!\left(1-\frac{4p}{3}\right)$$
**`snp-k2p`**
$$
\begin{aligned}
a_1 &= 1-2P-Q \\
a_2 &= 1-2Q \\
d &= -\frac{1}{2}\ln a_1-\frac{1}{4}\ln a_2
\end{aligned}
$$
**`snp-k81`**
$$
\begin{aligned}
a_1 &= 1-2P-2Q_1 \\
a_2 &= 1-2P-2Q_2 \\
a_3 &= 1-2Q_1-2Q_2 \\
d &= -\frac{1}{4}\left(\ln a_1+\ln a_2+\ln a_3\right)
\end{aligned}
$$
**`snp-f81`**
$$
\begin{aligned}
E &= 1-\left(\pi_A^2+\pi_C^2+\pi_G^2+\pi_T^2\right) \\
d &= -E\ln\!\left(1-\frac{p}{E}\right)
\end{aligned}
$$
**`snp-t92`**
$$
\begin{aligned}
g &= \pi_C+\pi_G \\
w &= 2g(1-g) \\
a_1 &= 1-\frac{P}{w}-Q \\
a_2 &= 1-2Q \\
d &= -w\ln a_1-\frac{1}{2}(1-w)\ln a_2
\end{aligned}
$$
**`snp-tn93`**
$$
\begin{aligned}
g_R &= \pi_A+\pi_G \\
g_Y &= \pi_C+\pi_T \\
k_1 &= \frac{2\pi_A\pi_G}{g_R} \\
k_2 &= \frac{2\pi_C\pi_T}{g_Y} \\
k_3 &= 2\left(g_Rg_Y-\frac{\pi_A\pi_G\,g_Y}{g_R}-\frac{\pi_C\pi_T\,g_R}{g_Y}\right) \\
w_1 &= 1-\frac{P_1}{k_1}-\frac{Q}{2g_R} \\
w_2 &= 1-\frac{P_2}{k_2}-\frac{Q}{2g_Y} \\
w_3 &= 1-\frac{Q}{2g_Rg_Y} \\
d &= -k_1\ln w_1-k_2\ln w_2-k_3\ln w_3
\end{aligned}
$$
**`snp-tv`** — transversions only, deliberately uncorrected:
$$d = Q$$
A rate-heterogeneity correction applies to every formula above except `snp-raw` and `snp-tv`: each $-\ln(x)$ term is replaced by $\alpha\left(x^{-1/\alpha}-1\right)$ (same weight, same $x$) — see [Gamma rate heterogeneity](gamma_rate_heterogeneity.md) for the correction itself and how $\alpha$ is estimated.
See [`phylo`](../../../usage/phylo.md) for how to select a `snp-*` value and the prerequisite index annex it requires.
@@ -0,0 +1,27 @@
# Gamma rate heterogeneity
Real substitution rates vary across sites rather than being uniform, which a plain substitution correction (see [Central-position SNP model](central_snp_model.md)) ignores. The standard $+\Gamma$ correction models this by replacing each $-\ln(x)$ term in a correction formula with $\alpha\left(x^{-1/\alpha}-1\right)$ — the same $x$, the same weight, under the assumption that the per-site rate is $\mathrm{Gamma}(\alpha,\alpha)$-distributed (mean 1) rather than fixed. A small $\alpha$ indicates strong among-site rate heterogeneity (many near-invariant sites, a few fast ones); as $\alpha$ grows large the correction converges to the uncorrected formula.
## Automatic $\alpha$ estimation
$\alpha$ can be estimated automatically from the index itself, using a method-of-moments estimator computed once, from the same sampling pass that builds the pairwise substitution tally — no extra scan of the index.
The estimator pools substitution counts by **partition** rather than by genome pair: for partition $i$, let $n_i$ be the total number of substitutions observed across every genome pair, and $L_i$ the total number of eligible loci across every genome pair, in that partition. Define the partition's observed substitution rate:
$$R_i = \frac{n_i}{L_i}$$
Under a single shared substitution rate with no among-site heterogeneity, each $R_i$ would vary only by Poisson sampling noise. Rate heterogeneity is modeled, as in the correction itself, by a $\mathrm{Gamma}(\alpha,\alpha)$-distributed multiplicative rate (mean 1) shared by every locus in a partition — the classical Poisson–Gamma (negative-binomial) mixture. Under that model:
$$\mathbb{E}[R_i] = \mu \qquad \mathrm{Var}[R_i] = \frac{\mu}{L_i} + \frac{\mu^2}{\alpha}$$
where $\mu$ is the pooled substitution rate across every partition. Weighting each partition's squared deviation by its own $L_i$ removes the first (Poisson) term before attributing what's left to genuine rate heterogeneity:
$$\hat\mu = \frac{\sum_i n_i}{\sum_i L_i} \qquad V = \frac{\sum_i L_i\,(R_i-\hat\mu)^2}{\sum_i L_i} \qquad \bar L = \frac{\sum_i L_i}{\text{number of partitions}}$$
$$\hat\alpha = \frac{\hat\mu^2}{V - \hat\mu/\bar L}$$
If the measured variance $V$ doesn't exceed the Poisson floor $\hat\mu/\bar L$ (no detectable over-dispersion across partitions — the data are consistent with a single shared rate), $\alpha$ is left undefined: the correction is silently disabled for that run rather than applying a fabricated value, and a warning is logged.
**This is not Jin & Nei's (1990) original estimator.** Their publication defines the $+\Gamma$ distance formula itself and, absent an estimate, recommends the fixed default $\alpha = 1$ — it does not propose a way to estimate $\alpha$ from data. The method-of-moments estimator above is a standard consequence of the Poisson–Gamma relationship between substitution counts and gamma-distributed rate variation, applied per-partition; it is `obikmer`'s own addition, not part of the cited correction.
See [`phylo`](../../../usage/phylo.md#distance-matrix---distance) for how to select a fixed $\alpha$ or request automatic estimation.
@@ -0,0 +1,34 @@
# Sampling design
Exhaustive computation over every non-monomorphic family in an index (see [Central-position SNP model](central_snp_model.md)) is the default, but can be bounded to approximately `N` families instead. Sampling is designed around two properties: staying representative of the whole index, and letting the user favor families that actually carry signal.
## Proportional sampling
Families are drawn in proportion to how many candidate families each part of the index actually holds, rather than uniformly across index partitions — this keeps the sample's composition representative of the whole index regardless of how unevenly candidate families happen to be distributed across partitions.
## Per-family informativeness: Shannon entropy
A family's informativeness is measured directly rather than assumed uniform. For a family, entropy is computed over its observed states across genomes:
| Quantity | Definition |
|---|---|
| `entropy15` | Shannon entropy (bits) over the 16 possible states (the 15 non-empty subsets of `{A,C,G,T}`), genomes absent from the family excluded from the count |
| `entropy4` | the same over the 4 plain bases, restricted to the genomes carrying exactly one member of the family (those that stay informative when multi-member genomes are treated as missing data) |
With `--no-ambiguity` the entropy is `entropy4`, computed over the genomes carrying exactly one member of the family, so that the weighting sees the same genomes as the final alignment; without it, `entropy15` is used. Each is stored in its own annex.
A family where every genome carries the same single state has entropy 0 (uninformative); one where genomes are spread evenly across several states has higher entropy (more informative for distinguishing genomes).
## Quartet restriction
A family only constrains the shape of a tree if its carrier genomes show a bipartition: two distinct states, each carried by at least two genomes. With fewer carriers, or with a single variant against a uniform background, every topology explains the family equally well. In a skimming dataset many families have only two or three carriers, so a uniform draw spends a large share of its quota on them. `--quartet` removes them before the draw. The test counts called states only, so absence never forms one of the two pairs.
## Pair balance
How well a pair of genomes is represented in a sample depends on how many families the pair shares: pairs of distant genomes share few, so a uniform draw gives them few sites, and the deep branches of a tree — which rest on exactly those pairs — are the least supported. `--pair-balance` weights each family by the mean, over the pairs of genomes carrying it, of 1 / (families shared by the pair), computed on the whole index. Averaging rather than summing keeps the weight from growing with the number of carriers, which would favour the families carried by most genomes regardless of which pairs they inform. Layers are allotted their share of the draw in proportion to the total weight of their families.
## Entropy-biased sampling
By default, sampling draws families uniformly. Weighting instead by informativeness biases the draw toward a target entropy $\mu$ with a Gaussian curve of width $\sigma$: a family's probability of being kept scales with $\exp\!\left(-\dfrac{(\text{entropy15} - \mu)^2}{2\sigma^2}\right)$ — a soft preference, not a hard cutoff, so no family is categorically excluded purely for having low or high entropy.
See [`phylo`](../../../usage/phylo.md#sampling-at-scale---n-sites---shannon---entropy) for how to bound and bias the sample, and for session/checkpointing behavior.
@@ -0,0 +1,22 @@
# The 16-state Sankoff model
Each family (see [Central-position SNP model](central_snp_model.md)) is treated as a character with 16 possible states: one per subset of the 4 possible central bases, including the empty subset (no observed form). A genome pair's calibration reduces to two separately-estimated first-order Markov models, both restricted to genome pairs below a configurable SNP-ratio ceiling (excluding saturated pairs from skewing the calibration):
- **Cardinality transitions** ($5 \times 5$, row-stochastic): the probability that a family observed with $i$ forms in one genome ($i \in \{0,\dots,4\}$) is observed with $j$ forms in the other.
- **Composition transitions** ($4 \times 4$, row-stochastic): the probability that an unambiguous, single-copy base observed as one of A/C/G/T in one genome is observed as another base in the other genome.
## Combining into a 16×16 cost matrix
The two matrices are *not* combined as a plain tensor product. For a pair of states $(A, B)$ — each a subset of $\{A,C,G,T\}$ — let `shared` $= A \cap B$, `lost` $= A \setminus B$, `gained` $= B \setminus A$. The log-probability of the transition $A \to B$ is:
$$\log P(A,B) = \underbrace{\log P_{\text{card}}(|A|,|B|)}_{\text{cardinality term, omitted when loss events are treated as free}} \;+\; \underbrace{\sum_{i \,\in\, \text{shared}} \log P_{\text{comp}}(i,i)}_{\text{bases conserved on both sides}} \;-\; \underbrace{\text{best\_pairing\_cost}(\text{lost}, \text{gained})}_{\text{substitutions among the differing bases}}$$
`best_pairing_cost` enumerates every injection pairing elements of `lost` with elements of `gained` and keeps the one minimizing $-\sum \log P_{\text{comp}}$ over the pairs — the discrete analogue of "prefer a substitution over an independent loss and gain": if a base is lost from one side and a different base is gained on the other, that is scored as a single substitution between them (cheaper, under any sane calibration, than treating them as two unrelated cardinality-changing events) whenever such a pairing is possible.
The resulting $16 \times 16$ log-probability matrix is row-normalized in log-space (log-sum-exp, not a direct `exp()`/divide, for numerical stability), giving a genuine row-stochastic transition matrix $P$. The cost matrix is then $\text{cost}(A,B) = -\ln P(A,B)$, symmetrized by simple averaging:
$$\text{sym}(A,B) = \frac{\text{cost}(A,B) + \text{cost}(B,A)}{2}$$
This calibrated cost matrix is what every downstream export (for TNT, PhyG, IQ-TREE) reuses, recoded into each tool's own format.
See [`phylo`](../../../usage/phylo.md#sankoff-calibration-and-phylogenetic-exports) for how to run the calibration and produce these exports.
+37 -135
View File
@@ -17,131 +17,17 @@ obikmer phylo INDEX [OPTIONS]
| Option | Default | Description | | Option | Default | Description |
|---|---|---| |---|---|---|
| `--distance` | `jaccard` | See the two tables below for the full list of accepted values | | `--distance` | `jaccard` | See the two tables below for the full list of accepted values |
| `--gamma-shape ALPHA\|auto` | none | Rate-heterogeneity correction, for `snp-*` values that support it (see below). Either a fixed $\alpha$ or `auto`/`estimate` to fit it from the data (see "Automatic $\alpha$ estimation" below). No effect on the other values; rejected if given together with a value that doesn't support it | | `--gamma-shape ALPHA\|auto` | none | Rate-heterogeneity correction, for `snp-*` values that support it (see [Gamma rate heterogeneity](../theory/phylogeny/snp_based/gamma_rate_heterogeneity.md)). Either a fixed $\alpha$ or `auto`/`estimate` to fit it from the data. No effect on the other values; rejected if given together with a value that doesn't support it |
| `--presence-threshold` | `1` | Minimum count for a kmer to be considered present, for `jaccard`/`mash` on a count index | | `--presence-threshold` | `1` | Minimum count for a kmer to be considered present, for `jaccard`/`mash` on a count index |
| `--csv` | off | Write the matrix as plain CSV instead of the default relaxed-PHYLIP format | | `--csv` | off | Write the matrix as plain CSV instead of the default relaxed-PHYLIP format |
| `--shared-kmers` | off | Also write the shared-kmer count matrix. Only valid with a whole-index metric, not a `snp-*` value | | `--shared-kmers` | off | Also write the shared-kmer count matrix. Only valid with a whole-index distance, not a `snp-*` value |
| `--nj` | off | Compute and write a Neighbor-Joining tree (Newick) | | `--nj` | off | Compute and write a Neighbor-Joining tree (Newick) |
| `--upgma` | off | Compute and write a UPGMA tree (Newick) | | `--upgma` | off | Compute and write a UPGMA tree (Newick) |
| `-o, --output` | none (stdout) | Output file prefix | | `-o, --output` | none (stdout) | Output file prefix |
Every value routes to one of two independent computations: Every value routes to one of two independent computations: **whole-index distances** (`jaccard`, `mash`, `hamming`, `bray-curtis`, `relfreq-bray-curtis`, `euclidean`, `relfreq-euclidean`, `hellinger`, `hellinger-euclidean` — see [Whole k-mer set distances](../theory/phylogeny/kmer_based/kmer_set_distances.md) for the definitions; `hamming` requires a presence/absence index, the others work on either index type), or **`snp-*` corrections** (`snp-raw`, `snp-jc`, `snp-k2p`, `snp-k81`, `snp-f81`, `snp-t92`, `snp-tn93`, `snp-tv` — see the [central-position SNP model](../theory/phylogeny/snp_based/central_snp_model.md) for the definitions).
### Whole-index metrics `snp-*` values require the sibling annex (`--sibling-annex`, below) and are, by default, computed exhaustively over every non-monomorphic family in the index; add `--n-sites N` to bound the computation to approximately `N` families instead (see "Sampling at scale" below — the same option `--pseudo-alignment`/`--sankoff` use, but optional here).
| Value | Definition |
|---|---|
| `jaccard` | $D = 1 - \dfrac{\lvert A \cap B \rvert}{\lvert A \cup B \rvert}$ over the sets of kmers present in each genome |
| `mash` | derived from the Jaccard distance via $D = -\dfrac{1}{k} \ln\!\left(\dfrac{2J}{1+J}\right)$ where $J = 1 - D_{\text{jaccard}}$ and $k$ is the index's kmer size; clamped to 1.0 when $J \le 0$ |
| `hamming` | number of kmer positions where presence differs between the two genomes (presence index only, not normalized): $D = \sum_i \mathbb{1}[a_i \ne b_i]$ |
| `bray-curtis` | $D = 1 - \dfrac{2 \sum_i \min(c_i^A, c_i^B)}{\sum_i c_i^A + \sum_i c_i^B}$ on raw per-kmer counts |
| `relfreq-bray-curtis` | the same formula computed on per-genome relative frequencies $p_i = c_i / \sum_j c_j$ instead of raw counts |
| `euclidean` | $D = \sqrt{\sum_i (c_i^A - c_i^B)^2}$ on raw counts |
| `relfreq-euclidean` | the same formula on relative frequencies |
| `hellinger` | $D = \dfrac{1}{\sqrt{2}} \sqrt{\sum_i \left(\sqrt{p_i^A} - \sqrt{p_i^B}\right)^2}$ on relative frequencies, bounded in $[0, 1]$ |
| `hellinger-euclidean` | the unnormalized variant, $D = \sqrt{2} \times D_{\text{hellinger}}$ |
`hamming` requires a presence/absence index; the others work on either index type.
### `snp-*` corrections
Computed from the central-position SNP model (see "Central-position SNP model" below): a family is the set of up to 4 kmers sharing identical flanking sequence and differing only at the central base. These values require the sibling annex (`--sibling-annex`, below) and are, by default, computed exhaustively over every non-monomorphic family in the index; add `--subsample N` to bound the computation to approximately `N` families instead (see "Sampling at scale" below — the same flag `--pseudo-alignment`/`--sankoff` use, but optional here).
For a genome pair, let $L$ be its total number of eligible loci (both genomes single-copy at that family), $p$ the raw proportion of substitutions among those loci, $P$/$Q$ the transition/transversion proportions, $Q_1$/$Q_2$ Kimura's two transversion categories (A↔C & G↔T vs. A↔T & C↔G), $P_1$/$P_2$ the purine (A↔G) / pyrimidine (C↔T) transition proportions, and $\pi_A,\pi_C,\pi_G,\pi_T$ the pair's pooled base frequencies.
**`snp-raw`**
$$d = p$$
**`snp-jc`**
$$d = -\frac{3}{4}\ln\!\left(1-\frac{4p}{3}\right)$$
**`snp-k2p`**
$$
\begin{aligned}
a_1 &= 1-2P-Q \\
a_2 &= 1-2Q \\
d &= -\frac{1}{2}\ln a_1-\frac{1}{4}\ln a_2
\end{aligned}
$$
**`snp-k81`**
$$
\begin{aligned}
a_1 &= 1-2P-2Q_1 \\
a_2 &= 1-2P-2Q_2 \\
a_3 &= 1-2Q_1-2Q_2 \\
d &= -\frac{1}{4}\left(\ln a_1+\ln a_2+\ln a_3\right)
\end{aligned}
$$
**`snp-f81`**
$$
\begin{aligned}
E &= 1-\left(\pi_A^2+\pi_C^2+\pi_G^2+\pi_T^2\right) \\
d &= -E\ln\!\left(1-\frac{p}{E}\right)
\end{aligned}
$$
**`snp-t92`**
$$
\begin{aligned}
g &= \pi_C+\pi_G \\
w &= 2g(1-g) \\
a_1 &= 1-\frac{P}{w}-Q \\
a_2 &= 1-2Q \\
d &= -w\ln a_1-\frac{1}{2}(1-w)\ln a_2
\end{aligned}
$$
**`snp-tn93`**
$$
\begin{aligned}
g_R &= \pi_A+\pi_G \\
g_Y &= \pi_C+\pi_T \\
k_1 &= \frac{2\pi_A\pi_G}{g_R} \\
k_2 &= \frac{2\pi_C\pi_T}{g_Y} \\
k_3 &= 2\left(g_Rg_Y-\frac{\pi_A\pi_G\,g_Y}{g_R}-\frac{\pi_C\pi_T\,g_R}{g_Y}\right) \\
w_1 &= 1-\frac{P_1}{k_1}-\frac{Q}{2g_R} \\
w_2 &= 1-\frac{P_2}{k_2}-\frac{Q}{2g_Y} \\
w_3 &= 1-\frac{Q}{2g_Rg_Y} \\
d &= -k_1\ln w_1-k_2\ln w_2-k_3\ln w_3
\end{aligned}
$$
**`snp-tv`** — transversions only, deliberately uncorrected:
$$d = Q$$
`--gamma-shape ALPHA` applies to every value above except `snp-raw` and `snp-tv`: each $-\ln(x)$ term in the formulas above is replaced by $\alpha\left(x^{-1/\alpha}-1\right)$ (the same weight, same $x$).
### Automatic $\alpha$ estimation (`--gamma-shape auto`)
`--gamma-shape auto` (or the equivalent `--gamma-shape estimate`) fits $\alpha$ from the index itself instead of requiring a user-supplied value, using a method-of-moments estimator computed once, from the same sampling pass that builds the pairwise substitution tally — no extra scan of the index.
The estimator pools substitution counts by **partition** rather than by genome pair: for partition $i$, let $n_i$ be the total number of substitutions observed across every genome pair, and $L_i$ the total number of eligible loci across every genome pair, in that partition. Define the partition's observed substitution rate:
$$R_i = \frac{n_i}{L_i}$$
Under a single shared substitution rate with no among-site heterogeneity, each $R_i$ would vary only by Poisson sampling noise. Rate heterogeneity is modeled, as elsewhere in this correction, by a $\mathrm{Gamma}(\alpha,\alpha)$-distributed multiplicative rate (mean 1) shared by every locus in a partition — the classical Poisson–Gamma (negative-binomial) mixture. Under that model:
$$\mathbb{E}[R_i] = \mu \qquad \mathrm{Var}[R_i] = \frac{\mu}{L_i} + \frac{\mu^2}{\alpha}$$
where $\mu$ is the pooled substitution rate across every partition. Weighting each partition's squared deviation by its own $L_i$ removes the first (Poisson) term before attributing what's left to genuine rate heterogeneity:
$$\hat\mu = \frac{\sum_i n_i}{\sum_i L_i} \qquad V = \frac{\sum_i L_i\,(R_i-\hat\mu)^2}{\sum_i L_i} \qquad \bar L = \frac{\sum_i L_i}{\text{number of partitions}}$$
$$\hat\alpha = \frac{\hat\mu^2}{V - \hat\mu/\bar L}$$
If the measured variance $V$ doesn't exceed the Poisson floor $\hat\mu/\bar L$ (no detectable over-dispersion across partitions — the data are consistent with a single shared rate), $\alpha$ is left undefined: the correction is silently disabled for that run rather than applying a fabricated value, and a warning is logged. When an estimate is produced, it's logged at the `info` level before the distance matrix is computed.
Note: this is a method-of-moments estimator derived from the standard Poisson–Gamma relationship between substitution counts and gamma-distributed rate variation, applied per-partition — it is not part of Jin & Nei's (1990) original publication, which only defines the `+Γ` distance formula itself and, absent an estimate, recommends the fixed default $\alpha = 1$ (`--gamma-shape 1`) rather than proposing a way to estimate it from data. `alpha < 1` indicates strong among-site rate heterogeneity (many near-invariant loci, a few fast ones); `alpha` growing large makes the correction converge to the uncorrected formula.
### Output ### Output
@@ -152,13 +38,13 @@ Without `-o`, the matrix goes to stdout in relaxed-PHYLIP format (`n` on the fir
| Option | Description | | Option | Description |
|---|---| |---|---|
| `--exclude-genome LABEL` | Exclude a genome (repeatable). Drops its row/column from the distance/shared-kmer matrix output, and removes it from the sampling used by `--pseudo-alignment`/`--sankoff`/a `snp-*` `--distance` value. Does not change the value computed for any remaining pair | | `--exclude-genome LABEL` | Exclude a genome (repeatable). Drops its row/column from the distance/shared-kmer matrix output, and removes it from the sampling used by `--pseudo-alignment`/`--sankoff`/a `snp-*` `--distance` value. Does not change the value computed for any remaining pair |
| `--min-shared-family N` | Auto-exclude, on top of `--exclude-genome`, any genome whose mean shared-family count against every other genome (see "Family Overlap" below) falls below `N`. Applies only to `--pseudo-alignment`/`--sankoff`/`snp-*` `--distance` — never to the whole-index metrics or their matrix/NJ/UPGMA output | | `--min-shared-family N` | Auto-exclude, on top of `--exclude-genome`, any genome whose mean shared-family count against every other genome (see "Family Overlap" below) falls below `N`. Applies only to `--pseudo-alignment`/`--sankoff`/`snp-*` `--distance` — never to the whole-index distances or their matrix/NJ/UPGMA output |
Neighbor-Joining and UPGMA trees (`--nj`/`--upgma`) are always built from every genome in the index, regardless of `--exclude-genome`/`--min-shared-family`. Neighbor-Joining and UPGMA trees (`--nj`/`--upgma`) are always built from every genome in the index, regardless of `--exclude-genome`/`--min-shared-family`.
## Central-position SNP model ## Central-position SNP model
Requires the sibling annex, built once per index: See [Central-position SNP model](../theory/phylogeny/snp_based/central_snp_model.md) for the family/eligibility definitions. Requires the sibling annex, built once per index:
| Option | Description | | Option | Description |
|---|---| |---|---|
@@ -167,9 +53,7 @@ Requires the sibling annex, built once per index:
| `--sibling-hist` | Print the global family-size histogram (1-4 members) only | | `--sibling-hist` | Print the global family-size histogram (1-4 members) only |
| `--family-overlap` | Write `<prefix>_family_overlap.csv`: for every genome pair, how many variable families both genomes carry a call for | | `--family-overlap` | Write `<prefix>_family_overlap.csv`: for every genome pair, how many variable families both genomes carry a call for |
| `--shannon` | Write `<prefix>_entropy.csv`: per-family Shannon entropy, one row per family, full unsampled scan | | `--shannon` | Write `<prefix>_entropy.csv`: per-family Shannon entropy, one row per family, full unsampled scan |
| `--pseudo-alignment` | Write `<prefix>_alignment.fasta`: a SNP-only pseudo-alignment. Requires `--subsample N` | | `--pseudo-alignment` | Write `<prefix>_alignment.fasta`: a SNP-only pseudo-alignment. Requires `--n-sites N\|all` |
A family is eligible for a genome pair $(i,j)$ only if both genomes carry exactly one of its observed forms (single-copy, unambiguous).
### `--sibling-stats` ### `--sibling-stats`
@@ -182,7 +66,7 @@ A family is eligible for a genome pair $(i,j)$ only if both genomes carry exactl
### Family Overlap ### Family Overlap
`--family-overlap` writes `<prefix>_family_overlap.csv`: header `genome,<label1>,<label2>,...`, one row per genome, cell `[i][j]` = number of variable families (family size ≥ 2) where both genome `i` and genome `j` carry a call. The diagonal is always `0`. Every genome is written, unfiltered by `--exclude-genome`/`--min-shared-family`. `--family-overlap` writes `<prefix>_family_overlap.csv`: header `genome,<label1>,<label2>,...`, one row per genome, cell `[i][j]` = number of variable families (family size ≥ 2) where both genome `i` and genome `j` carry a call. The diagonal is always `0`. Every genome is written, unfiltered by `--exclude-genome`/`--min-shared-family`. With `--no-ambiguity`, a genome carrying several members of a family is not counted as carrying it, as in the alignment; without it, any genome with a call counts. The matrix is stored once per convention, so switching `--no-ambiguity` builds the other one without discarding the first (`--min-shared-family` follows the same convention).
`--min-shared-family N` uses the mean of each genome's own row (excluding the diagonal) against this same matrix as its exclusion statistic. There is no universal value for `N` — inspect `--family-overlap`'s own output to find where the real gap sits in a given genome collection before choosing a threshold. `--min-shared-family N` uses the mean of each genome's own row (excluding the diagonal) against this same matrix as its exclusion statistic. There is no universal value for `N` — inspect `--family-overlap`'s own output to find where the real gap sits in a given genome collection before choosing a threshold.
@@ -192,15 +76,17 @@ A family is eligible for a genome pair $(i,j)$ only if both genomes carry exactl
| Option | Default | Description | | Option | Default | Description |
|---|---|---| |---|---|---|
| `--subsample N` | none (mandatory here) | Target number of families to sample | | `--n-sites N\|all` | none (mandatory here) | Number of families to draw, or `all` to use every variable family that passes the other filters, with no sampling. A number is a target, not a guarantee. |
| `--free-loss` | off | Treat a genome carrying none of a family's observed members as missing data (`?`) instead of `-` | | `--free-loss` | off | Treat a genome carrying none of a family's observed members as missing data (`?`) instead of `-` |
| `--no-ambiguity` | off | Treat a genome carrying more than one member of a family as missing data (`?`) instead of an IUPAC ambiguity code | | `--no-ambiguity` | off | Treat a genome carrying more than one member of a family as missing data (`?`) instead of an IUPAC ambiguity code |
| `--quartet` | off | Keep only the families that can separate two pairs of genomes from each other: at least two distinct called states, each carried by at least two genomes. Which genomes count as carriers follows `--no-ambiguity` |
| `--pair-balance` | off | Favour the families covering the pairs of genomes that share the fewest families across the index, so that every pair is better represented in the sample. Which genomes count as carriers follows `--no-ambiguity` |
| `--entropy MU` | off (`1.0` if only `--entropy-sd` is given) | Center of the entropy band to favor when sampling | | `--entropy MU` | off (`1.0` if only `--entropy-sd` is given) | Center of the entropy band to favor when sampling |
| `--entropy-sd SIGMA` | off (`0.5` if only `--entropy` is given) | Width of that band | | `--entropy-sd SIGMA` | off (`0.5` if only `--entropy` is given) | Width of that band |
## Sampling at scale: `--subsample`, `--shannon`, `--entropy` ## Sampling at scale: `--n-sites`, `--shannon`, `--entropy`
`--subsample`, `--free-loss`, `--no-ambiguity`, `--entropy`/`--entropy-sd` are shared by `--pseudo-alignment`, `--sankoff` (and everything it implies: `--tnt`/`--phyg`/`--iqtree`), and a `snp-*` `--distance` value — one draw feeds all of them in a single invocation. `--subsample` is mandatory for `--pseudo-alignment`/`--sankoff`; for a `snp-*` `--distance` value it is optional (omitted means every non-monomorphic family in the index, not an approximation). `--n-sites`, `--free-loss`, `--no-ambiguity`, `--quartet`, `--pair-balance`, `--entropy`/`--entropy-sd` are shared by `--pseudo-alignment`, `--sankoff` (and everything it implies: `--tnt`/`--phyg`/`--iqtree`), and a `snp-*` `--distance` value — one draw feeds all of them in a single invocation. `--n-sites` is mandatory for `--pseudo-alignment`/`--sankoff`, where it takes either a number of sites or `all`; for a `snp-*` `--distance` value it is optional, and omitting it is the same as `all` (every non-monomorphic family in the index, not an approximation).
Combining `--sankoff` (or `--tnt`/`--phyg`/`--iqtree`) with a `snp-*` `--distance` value in the same command reuses that one draw for both — the distance and the Sankoff calibration/alignment are guaranteed to be computed from the *identical* set of sampled sites, never two independent samples, so the two outputs are directly comparable. This only holds within a single command; running them as two separate `obikmer phylo` invocations draws two independent samples even with the same flags — unless `--session` is used (below). Combining `--sankoff` (or `--tnt`/`--phyg`/`--iqtree`) with a `snp-*` `--distance` value in the same command reuses that one draw for both — the distance and the Sankoff calibration/alignment are guaranteed to be computed from the *identical* set of sampled sites, never two independent samples, so the two outputs are directly comparable. This only holds within a single command; running them as two separate `obikmer phylo` invocations draws two independent samples even with the same flags — unless `--session` is used (below).
@@ -213,13 +99,13 @@ Every invocation, with or without `--session`, draws its own fresh random sample
| `--session DIR` | none | Persist the sample (and, for `--sankoff`, its calibration/alignment) in `DIR` so a later, separate `obikmer phylo` invocation with the exact same selection parameters restores it instead of resampling | | `--session DIR` | none | Persist the sample (and, for `--sankoff`, its calibration/alignment) in `DIR` so a later, separate `obikmer phylo` invocation with the exact same selection parameters restores it instead of resampling |
| `--session-force` | off | With `--session DIR`: overwrite its saved parameters and cached sample instead of erroring out when this run's parameters don't match. No effect without `--session` | | `--session-force` | off | With `--session DIR`: overwrite its saved parameters and cached sample instead of erroring out when this run's parameters don't match. No effect without `--session` |
`DIR` is created if it doesn't exist. If it already holds a sample built with different `--subsample`/`--free-loss`/`--no-ambiguity`/`--exclude-genome`/`--min-shared-family`/`--entropy`/`--entropy-sd` values than this run, the command exits with an error rather than silently using either the old or the new values — pass `--session-force` to discard the old sample and rebuild under the new parameters, or point `--session` at a different directory to keep both. `DIR` is created if it doesn't exist. If it already holds a sample built with different `--n-sites`/`--free-loss`/`--no-ambiguity`/`--quartet`/`--exclude-genome`/`--min-shared-family`/`--entropy`/`--entropy-sd` values than this run, the command exits with an error rather than silently using either the old or the new values — pass `--session-force` to discard the old sample and rebuild under the new parameters, or point `--session` at a different directory to keep both.
A `--sankoff`-family run and a `snp-*` `--distance` run share the same cached sample when pointed at the same `--session DIR` — build it once with either, reuse it from the other, in either order, across separate commands. A `--sankoff`-family run and a `snp-*` `--distance` run share the same cached sample when pointed at the same `--session DIR` — build it once with either, reuse it from the other, in either order, across separate commands.
If a run using `--session` is interrupted (crash, kill, `Ctrl-C`), the next run against the same `--session DIR` resumes from the last automatic checkpoint (roughly every 8 partitions'-worth of sampling progress) instead of starting over. The resumed run's sample is **not** guaranteed to be identical to what an uninterrupted run would have produced past that checkpoint — each process draws its own independent random sequence, same as any two separate invocations do — but nothing already checkpointed is lost, and no work needs redoing beyond that point. If a run using `--session` is interrupted (crash, kill, `Ctrl-C`), the next run against the same `--session DIR` resumes from the last automatic checkpoint (roughly every 8 partitions'-worth of sampling progress) instead of starting over. The resumed run's sample is **not** guaranteed to be identical to what an uninterrupted run would have produced past that checkpoint — each process draws its own independent random sequence, same as any two separate invocations do — but nothing already checkpointed is lost, and no work needs redoing beyond that point.
Without `--subsample`, every variable family (family size ≥ 2) is used. With `--subsample N`, roughly `N` families are kept instead, drawn in proportion to how many candidate families each part of the index actually holds, so the sample stays representative of the whole index. If the index has fewer than `N` candidate families, `--subsample` has no effect. With `--n-sites all` (or, for a `snp-*` `--distance` value, without `--n-sites`), every variable family (family size ≥ 2) that passes the other filters is used. With `--n-sites N`, roughly `N` families are kept instead (see [Sampling design](../theory/phylogeny/snp_based/sampling_design.md) for how the draw stays representative of the whole index). If fewer than `N` candidate families remain, `--n-sites` has no effect.
### `--shannon`: measuring how informative a family is ### `--shannon`: measuring how informative a family is
@@ -227,26 +113,42 @@ Without `--subsample`, every variable family (family size ≥ 2) is used. With `
| Column | Meaning | | Column | Meaning |
|---|---| |---|---|
| `partition` | the index partition that holds the family |
| `layer` | an internal index-layer identifier — stable within one run, not meaningful across indexes | | `layer` | an internal index-layer identifier — stable within one run, not meaningful across indexes |
| `family_idx` | the family's position within that layer | | `family_idx` | the family's position within that layer |
| `entropy15` | Shannon entropy (bits) over the 16 possible states (the 15 non-empty subsets of `{A,C,G,T}`), genomes absent from the family excluded from the count | | `entropy15` | Shannon entropy (bits) over the 16 possible states (the 15 non-empty subsets of `{A,C,G,T}`), genomes absent from the family excluded from the count |
| `entropy4` | Shannon entropy (bits) reduced to the 4 plain bases, kept alongside `entropy15` for comparison | | `entropy4` | Shannon entropy (bits) over the 4 plain bases, computed only over the genomes that carry exactly one member of the family — the genomes that remain informative under `--no-ambiguity`, since a genome carrying several members of a family (paralogous copies) is treated as missing data there. `0` when `n_genomes_unambiguous` is `0` |
| `family_size` | number of distinct central bases observed anywhere in the index for this family (2-4) | | `family_size` | number of distinct central bases observed anywhere in the index for this family (2-4) |
| `n_genomes_present` | how many genomes the entropy was computed over | | `n_genomes_present` | how many genomes the family is present in; `entropy15` is computed over these |
| `n_genomes_unambiguous` | how many of those genomes carry exactly one member of the family; `entropy4` is computed over these |
Run with `--subsample N --shannon` to get a bounded diagnostic sample instead of a full-index pass — useful for choosing `--entropy`/`--entropy-sd` values before a full run. `--shannon` always scans every non-monomorphic family of the whole index; `--n-sites`, `--entropy` and `--entropy-sd` have no effect on it. The output therefore grows with the index, with one row per family, and can reach hundreds of millions of rows (tens of gigabytes) on a large index. Analyse it with a tool that reads the file as a stream (for example DuckDB or Miller) rather than loading it whole. It is nevertheless the right basis for choosing `--entropy`/`--entropy-sd` values, since it gives the complete entropy distribution, including how it varies with `n_genomes_present`, rather than an estimate from a sample.
### `--quartet`: keeping only families that can resolve a tree
A family carried by fewer than four genomes, or whose genomes all share one state except a single variant, fits every tree topology equally well and so tells a tree nothing: to separate two pairs of genomes from each other (`AB|CD`) it takes at least two distinct states, each carried by at least two genomes. `--quartet` restricts the draw to the families that show this pattern. Absence is never a state here: a genome that does not carry the family does not count, with or without `--free-loss`. A genome carrying several members of the family counts as a carrier of its own combination of bases, unless `--no-ambiguity` is given, in which case it is left out, as in the alignment.
The restriction is applied before the draw, from a persisted annex (one bit per variable family, built the first time `--quartet` is used with a given `--no-ambiguity` convention, in one pass shared with the other annexes, and built for both conventions by `--sibling-annex`), then checked exactly on each family drawn, taking `--exclude-genome` into account. The quota given to `--n-sites` is therefore spent only on usable families.
### `--pair-balance`: representing every pair of genomes
Two genomes that are distantly related share few families, so a uniform draw covers such a pair with few sites, far fewer than a close pair: the pairs that matter for the deep branches of a tree are the worst represented. `--pair-balance` compensates. Each family is weighted by the mean, over the pairs of genomes carrying it, of 1 divided by the number of families that pair shares across the whole index (the matrix `--family-overlap` writes): a family carried by a rarely-sharing pair weighs more. It is the mean, not the sum, so a family carried by most genomes — in skimming data often a high-copy region — is not favoured merely for covering many pairs.
Each layer's share of the draw is proportional to the total weight of its families, and a family's chance of being drawn is proportional to its own weight. The weights are persisted (one value per variable family, built the first time `--pair-balance` is used with a given `--no-ambiguity` convention, after the family-overlap matrix it depends on, and by `--sibling-annex` for both conventions). They combine with `--entropy` and `--quartet`: the weight multiplies the entropy kernel, and `--quartet` restricts the families first.
### `--entropy MU` / `--entropy-sd SIGMA`: biasing the sample toward informative families ### `--entropy MU` / `--entropy-sd SIGMA`: biasing the sample toward informative families
By default, `--subsample` draws families uniformly. With `--entropy`/`--entropy-sd`, each family's chance of being kept is instead weighted by how close its own entropy (`entropy15`) is to `MU`, using a Gaussian curve of width `SIGMA` — no hard cutoff. The filter activates as soon as either flag is given; the other defaults to `1.0`/`0.5`. Combine with `--subsample N` (expect somewhat fewer than `N` families kept in practice) or use alone (a soft filter over the whole index, no size target). By default, `--n-sites N` draws families uniformly. With `--entropy`/`--entropy-sd`, each family's chance of being kept is instead weighted by how close its own entropy (`entropy15`) is to `MU`, using a Gaussian curve of width `SIGMA` — no hard cutoff (see [Sampling design](../theory/phylogeny/snp_based/sampling_design.md) for the weighting formula). The filter activates as soon as either flag is given; the other defaults to `1.0`/`0.5`. Combine with `--n-sites N` (expect somewhat fewer than `N` families kept in practice) or use alone (a soft filter over the whole index, no size target).
The first `phylo` run on a given index that uses `--entropy`/`--entropy-sd` pays a one-time extra cost (every candidate family's entropy is computed once and saved alongside the index); later runs, even with different `MU`/`SIGMA`, reuse that saved data. The first `phylo` run on a given index that uses `--entropy`/`--entropy-sd` pays a one-time extra cost (every candidate family's entropy is computed once and saved alongside the index); later runs, even with different `MU`/`SIGMA`, reuse that saved data.
The entropy that weights the draw follows `--no-ambiguity`, so that it describes the same genomes as the alignment. Without the flag, every genome carrying the family counts, and a genome carrying several members of it is a state of its own (`entropy15`). With the flag, only the genomes carrying exactly one member count, since the others become missing data (`entropy4`). The two entropies are saved separately: switching `--no-ambiguity` builds the other one once, without discarding the first, and `--sibling-annex` builds both.
## Sankoff calibration and phylogenetic exports ## Sankoff calibration and phylogenetic exports
| Option | Default | Description | | Option | Default | Description |
|---|---|---| |---|---|---|
| `--sankoff` | off | Calibrate a 16-state parsimony cost matrix and matching pseudo-alignment. Requires `--subsample N` | | `--sankoff` | off | Calibrate a 16-state parsimony cost matrix and matching pseudo-alignment. Requires `--n-sites N\|all` |
| `--sankoff-ratio-ceiling` | `0.5` | Exclude genome pairs whose raw SNP ratio exceeds this value from the base-composition part of the calibration | | `--sankoff-ratio-ceiling` | `0.5` | Exclude genome pairs whose raw SNP ratio exceeds this value from the base-composition part of the calibration |
| `--free-loss` | off | Recode a family's non-detection as the `?` missing-data symbol instead of an ordinary, costed state, throughout `--sankoff` and every export built from it | | `--free-loss` | off | Recode a family's non-detection as the `?` missing-data symbol instead of an ordinary, costed state, throughout `--sankoff` and every export built from it |
| `--tnt` | off | Also write a TNT script (implies `--sankoff`) | | `--tnt` | off | Also write a TNT script (implies `--sankoff`) |
@@ -257,7 +159,7 @@ The first `phylo` run on a given index that uses `--entropy`/`--entropy-sd` pays
### The 16-state model ### The 16-state model
Each family is a character with 16 possible states: one per subset of the 4 possible central bases (including the empty subset). Calibration combines a $5 \times 5$ transition matrix over family cardinality (0-4 observed forms) and a $4 \times 4$ base-substitution matrix from unambiguous single-copy loci, both restricted to genome pairs at or below `--sankoff-ratio-ceiling`, into a row-normalized $16 \times 16$ transition probability matrix $P$, converted to a symmetric cost matrix via $\text{cost}(a,b) = -\ln P(a,b)$. Each family is a character with 16 possible states: one per subset of the 4 possible central bases (including the empty subset). See [The 16-state Sankoff model](../theory/phylogeny/snp_based/sankoff_model.md) for how the calibrated cost matrix is built from cardinality and base-composition transitions.
`--sankoff` alone writes the cost matrix, the calibration parameters, and a pseudo-alignment recoded so the empty state uses the symbol `0` (never a gap character). It does not run any external tool. `--sankoff` alone writes the cost matrix, the calibration parameters, and a pseudo-alignment recoded so the empty state uses the symbol `0` (never a gap character). It does not run any external tool.
+57
View File
@@ -0,0 +1,57 @@
#!/usr/bin/env bash
# Genome-skimming test bed: re-simulate the benchmark genomes at a low
# coverage, index each specimen, and merge them into one presence index.
#
# Usage: simulate_skim.sh (env: COVERAGE=1 SEED=1 CPUS=...)
#
# The genome → specimen mapping is read from deps.mk (same source of truth
# as the Makefile pipeline); the pipeline's own run/ tree is left untouched.
# Output: run/skim_${COVERAGE}x_s${SEED}/
# simulated_data/<species>/<strain>/reads_R{1,2}.fastq.gz
# specimen_index_presence/<species>--<strain>/
# global_index_presence/
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ISS="${SCRIPT_DIR}/../.venv/bin/iss"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
COVERAGE="${COVERAGE:-1}"
SEED="${SEED:-1}"
READ_LENGTH=150
CPUS="${CPUS:-$(sysctl -n hw.logicalcpu 2>/dev/null || nproc 2>/dev/null || echo 2)}"
OUT="${SCRIPT_DIR}/run/skim_${COVERAGE}x_s${SEED}"
mkdir -p "${OUT}/simulated_data" "${OUT}/specimen_index_presence"
tmp_fasta=$(mktemp "${TMPDIR:-/tmp}/obikmer_skim_XXXXXX.fna")
trap 'rm -f "${tmp_fasta}"' EXIT
# lines of the form run/simulated_data/<species>/<strain>/reads_R1.fastq.gz: run/genomes/<file>
sed -nE 's#^run/simulated_data/([^/]+)/([^/]+)/reads_R1\.fastq\.gz: (run/genomes/[^ ]+)$#\1 \2 \3#p' \
"${SCRIPT_DIR}/deps.mk" | sort -u | while read -r species strain genome; do
specimen="${species}--${strain}"
reads_dir="${OUT}/simulated_data/${species}/${strain}"
index_dir="${OUT}/specimen_index_presence/${specimen}"
mkdir -p "${reads_dir}"
gzip -dc "${SCRIPT_DIR}/${genome}" > "${tmp_fasta}"
genome_size=$(grep -v "^>" "${tmp_fasta}" | tr -d '[:space:]' | wc -c | tr -d ' ')
n_reads=$(python3 -c "import math; print(math.ceil(${COVERAGE} * ${genome_size} / (2 * ${READ_LENGTH})))")
echo "[${specimen}] genome=${genome_size} bp → ${n_reads} read pairs (${COVERAGE}x, seed ${SEED})"
"${ISS}" generate \
--genomes "${tmp_fasta}" --model HiSeq --n_reads "${n_reads}" \
--cpus "${CPUS}" --seed "${SEED}" --compress \
--output "${reads_dir}/reads" 2>/dev/null
rm -f "${reads_dir}"/reads.iss.tmp.*.vcf
"${BINARY}" index --output "${index_dir}" --force --theta 0 \
--label "${specimen}" --meta "species=${species}" \
"${reads_dir}/reads_R1.fastq.gz" "${reads_dir}/reads_R2.fastq.gz" 2>/dev/null
done
mapfile -t sources < <(find "${OUT}/specimen_index_presence" -mindepth 1 -maxdepth 1 -type d | sort)
echo "Merging ${#sources[@]} presence indexes → ${OUT}/global_index_presence"
"${BINARY}" merge --output "${OUT}/global_index_presence" --force --force-presence \
"${sources[@]}" 2>/dev/null
echo "Done: ${OUT}/global_index_presence"
@@ -0,0 +1,6 @@
{
"cells": [],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 5
}
+126
View File
@@ -0,0 +1,126 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "12264929-a50f-435a-a893-070b3f9573d9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(G, k)"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"var('G k')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "30d5efd3-8bdc-4249-ad9d-abf7cad3481a",
"metadata": {},
"outputs": [],
"source": [
"q = 1 / 4^k"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "588770fe-ddf2-49c4-9f1f-df177543c69c",
"metadata": {},
"outputs": [],
"source": [
"P0 = (1-q)^G"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4d52ce3d-88e5-4c10-ae8e-dba268185f7e",
"metadata": {},
"outputs": [],
"source": [
"P1 = 1 - P0"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "91c8cba6-bf05-4694-9598-eae9663e5c82",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"-(-1/4^k + 1)^G + 1"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"P1"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "c29cfeae-9a3c-483e-a007-81df52eef62d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Lambda"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"var('Lambda')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "53028547-57d4-4375-8a26-8ae92309a3c0",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "SageMath 10.9",
"language": "sage",
"name": "sagemath-10.9"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.14.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
+16 -6
View File
@@ -9,7 +9,7 @@ plugins:
- mermaid2: - mermaid2:
- bibtex: - bibtex:
bib_file: UserDocMD/references.bib bib_file: UserDocMD/references.bib
csl_file: UserDocMD/ecology-letters.csl csl_file: UserDocMD/molecular-ecology-modified.csl
enable_inline_citations: false enable_inline_citations: false
markdown_extensions: markdown_extensions:
@@ -31,11 +31,21 @@ nav:
- Home: index.md - Home: index.md
- Installation: installation.md - Installation: installation.md
- Theory: - Theory:
- Kmers and super-kmers: theory/kmers_and_superkmers.md - Kmer indexing:
- DNA encoding: theory/encoding.md - DNA encoding: theory/kmer_indexing/encoding.md
- Low-complexity kmer filter: theory/entropy_filter.md - Kmers: theory/kmer_indexing/kmers.md
- Minimizer selection: theory/minimizer_selection.md - Minimizer selection: theory/kmer_indexing/minimizer_selection.md
- Partitioning and indexing architecture: theory/indexing_architecture.md - Super-kmers: theory/kmer_indexing/superkmers.md
- Partitioning and indexing architecture: theory/kmer_indexing/indexing_architecture.md
- Low-complexity kmer filter: theory/kmer_indexing/entropy_filter.md
- Phylogeny:
- Kmer-based:
- Whole k-mer set distances: theory/phylogeny/kmer_based/kmer_set_distances.md
- SNP-based:
- Central-position SNP model: theory/phylogeny/snp_based/central_snp_model.md
- Gamma rate heterogeneity: theory/phylogeny/snp_based/gamma_rate_heterogeneity.md
- Sankoff model: theory/phylogeny/snp_based/sankoff_model.md
- Sampling design: theory/phylogeny/snp_based/sampling_design.md
- Usage: - Usage:
- superkmer: usage/superkmer.md - superkmer: usage/superkmer.md
- index: usage/index_command.md - index: usage/index_command.md
+4 -1
View File
@@ -36,7 +36,10 @@ nav:
- Entropy filter: theory/entropy.md - Entropy filter: theory/entropy.md
- Minimizer selection: theory/minimizer.md - Minimizer selection: theory/minimizer.md
- Partitioning architecture: theory/indexing.md - Partitioning architecture: theory/indexing.md
- Chance sharing across genomes (discussion): theory/chance_sharing.md
- Central-position SNP distance (discussion): theory/evolutionary_distances.md - Central-position SNP distance (discussion): theory/evolutionary_distances.md
- Sibling partition unification (discussion): theory/sibling_partition_unification.md
- Pair-coverage-biased family sampling (discussion): theory/pair_coverage_sampling.md
- Implementation: - Implementation:
- SuperKmer: implementation/superkmer.md - SuperKmer: implementation/superkmer.md
- Kmer: implementation/kmer.md - Kmer: implementation/kmer.md
@@ -60,7 +63,7 @@ nav:
- Architecture: - Architecture:
- Sequences: architecture/sequences/invariant.md - Sequences: architecture/sequences/invariant.md
- Kmer index: architecture/index_architecture.md - Kmer index: architecture/index_architecture.md
- Sibling annex (discussion): architecture/siblings.md - Sibling annex: architecture/siblings.md
- NUMA-aware worker pools: architecture/numa_worker_pools.md - NUMA-aware worker pools: architecture/numa_worker_pools.md
- NUMA-aware partition runner: architecture/numa_partition_runner.md - NUMA-aware partition runner: architecture/numa_partition_runner.md
+395
View File
@@ -0,0 +1,395 @@
#!/usr/bin/env python3
"""Family overlap and clade-closure ("nesting") of a SNP pseudo-alignment.
Each alignment column is one family; a genome "carries a call" at a column
when its character is not an absence symbol (default '-' and '?').
Outputs (prefix given by -o):
<prefix>_family_overlap.csv genome x genome matrix: number of columns where
both genomes carry a call (diagonal = 0, same
convention as `obikmer phylo --family-overlap`)
<prefix>_nesting.csv per clade-size stratum: how closed the families
are under the tree
Nesting measure: for a family carried by the genome set S, let C(S) be the
smallest tree clade containing S. completeness = |S| / |C(S)|. A value of 1
means the family is clade-closed (every genome of the clade carries it); low
values mean dropout or patchy conservation inside the clade.
The tree is rooted as written in the Newick file unless --outgroup is given
(rooted at the neighbour of that tip, which then becomes a child of the root).
Optional lift test (--lift-test): do families covering a rare pair (A,B) also
cover an abundant pair (A,C) more often than the margins alone imply? For each
genome A, B ranges over its --lift-frac rarest partners and C over its most
abundant ones (ranked on pair overlap). Statistics, on a random column subsample:
T = mean over triples of O_ABC / O_AB = P(C | A,B)
L = sum n_A * O_ABC / sum O_AB * O_AC (lift; 1 if B,C independent given A)
Null: curveball swap randomisation of the genome x family presence matrix, which
preserves every genome's family count and every family's size exactly. Each null
replicate re-selects the rare/abundant partners from its own overlaps, so the
selection procedure is identical to the observed one.
Optional quartet test (--quartet-test): does flattening pair overlaps also flatten
quartet coverage? --quartets N genome quartets are drawn uniformly; for each, the
number of columns where all four genomes carry a call is counted exactly. Reported
per stratum of the quartet's depth (size of the smallest tree clade containing the
four genomes): count distribution, share of uncovered quartets, and the ratio of the
4-way count to the smallest of the six pair overlaps (1 = perfect nesting; the pair
overlap is an upper bound of the 4-way count).
Usage
-----
pseudo_alignment_nesting.py ALIGNMENT.fasta TREEFILE -o prefix
[--outgroup LABEL] [--absent '-?'] [--chunk 131072]
[--quartet-test [--quartets 20000]]
[--lift-test [--lift-columns 200000] [--lift-frac 0.1]
[--null-reps 20] [--trades 5000] [--seed N]]
"""
import argparse
import sys
import numpy as np
def read_fasta_presence(path, absent):
"""Return (labels, packed presence bits per genome, alignment length)."""
absent_lut = np.zeros(256, dtype=bool)
for ch in absent:
absent_lut[ord(ch)] = True
labels, packed, length = [], [], None
def flush(parts):
nonlocal length
seq = np.frombuffer(b"".join(parts), dtype=np.uint8)
if length is None:
length = len(seq)
elif len(seq) != length:
sys.exit(f"{labels[-1]}: length {len(seq)} != {length}")
packed.append(np.packbits(~absent_lut[seq]))
parts = None
with open(path, "rb") as fh:
for line in fh:
if line.startswith(b">"):
if parts is not None:
flush(parts)
labels.append(line[1:].split()[0].decode())
parts = []
else:
parts.append(line.strip())
if parts is not None:
flush(parts)
return labels, np.vstack(packed), length
def parse_newick(text):
"""Parse Newick into (names, parent, length) arrays; internal labels ignored."""
names, parent, length = [], [], []
stack, cur = [], None
i, n = 0, len(text)
def new_node():
names.append(None)
parent.append(-1)
length.append(0.0)
return len(names) - 1
while i < n:
c = text[i]
if c in " \n\r\t":
i += 1
elif c == "(":
if stack:
node = stack[-1] # the placeholder child becomes this internal node
else:
node = new_node()
stack.append(node)
cur = None
i += 1
child = new_node()
parent[child] = node
stack.append(child)
elif c == ",":
stack.pop()
child = new_node()
parent[child] = stack[-1]
stack.append(child)
i += 1
elif c == ")":
stack.pop()
cur = stack[-1]
i += 1
j = i
while j < n and text[j] not in ":,);":
j += 1
i = j # internal label (support values) discarded
elif c == ":":
j = i + 1
while j < n and text[j] not in ",);":
j += 1
length[stack[-1] if cur is None else cur] = float(text[i + 1:j])
cur = None
i = j
elif c == ";":
break
else:
j = i
while j < n and text[j] not in ":,);":
j += 1
names[stack[-1]] = text[i:j]
i = j
return names, parent, length
def leaf_order_matrices(names, parent, length, outgroup):
"""DFS leaf order plus LCA-clade-size and patristic matrices in that order."""
adj = [[] for _ in names]
for v, p in enumerate(parent):
if p >= 0:
adj[v].append((p, length[v]))
adj[p].append((v, length[v]))
root = next(v for v, p in enumerate(parent) if p < 0)
if outgroup is not None:
tip = names.index(outgroup)
root = adj[tip][0][0]
order, depth, children = [], {root: 0.0}, {}
stack, seen = [root], {root}
while stack:
v = stack.pop()
kids = [(u, w) for u, w in adj[v] if u not in seen]
for u, w in kids:
seen.add(u)
depth[u] = depth[v] + w
children[v] = [u for u, _ in kids]
stack.extend(reversed(children[v]))
order.append(v)
leaves = [v for v in order if not children[v]]
rank = {v: r for r, v in enumerate(leaves)}
n = len(leaves)
span = {}
for v in reversed(order):
span[v] = (rank[v], rank[v] + 1) if not children[v] else (
span[children[v][0]][0], span[children[v][-1]][1])
clade = np.ones((n, n), dtype=np.int32)
lca_depth = np.zeros((n, n))
for v in order:
kids = children[v]
for a in range(len(kids)):
for b in range(a + 1, len(kids)):
(a0, a1), (b0, b1) = span[kids[a]], span[kids[b]]
size = span[v][1] - span[v][0]
clade[a0:a1, b0:b1] = clade[b0:b1, a0:a1] = size
lca_depth[a0:a1, b0:b1] = lca_depth[b0:b1, a0:a1] = depth[v]
leaf_depth = np.array([depth[v] for v in leaves])
patristic = leaf_depth[:, None] + leaf_depth[None, :] - 2 * lca_depth
return [names[v] for v in leaves], clade, patristic
def lift_stats(pres, frac):
"""(L, T) for the rare/abundant partner triples of every genome (see module doc)."""
n = pres.shape[0]
pf = pres.astype(np.float32)
overlap = pf @ pf.T
k = max(1, round(frac * (n - 1)))
num = den = ratio_sum = 0.0
n_ratio = 0
for a in range(n):
order = [j for j in np.argsort(overlap[a], kind="stable") if j != a]
rare, abundant = order[:k], order[-k:]
cols = pres[a]
n_a = float(cols.sum())
if n_a == 0:
continue
o_abc = pf[rare][:, cols] @ pf[abundant][:, cols].T
o_ab, o_ac = overlap[a, rare].astype(np.float64), overlap[a, abundant].astype(np.float64)
num += n_a * float(o_abc.sum())
den += float((o_ab[:, None] * o_ac[None, :]).sum())
ok = o_ab > 0
ratio_sum += float((o_abc[ok] / o_ab[ok, None]).sum())
n_ratio += int(ok.sum()) * k
return num / den, ratio_sum / n_ratio
def curveball(pres, trades, rng):
"""In-place curveball trades: preserve every row sum and every column sum."""
n = pres.shape[0]
for _ in range(trades):
i, j = rng.choice(n, size=2, replace=False)
a, b = pres[i], pres[j]
diff = np.flatnonzero(a ^ b)
k = int((a & ~b).sum())
diff = rng.permutation(diff)
a[diff] = False
b[diff] = False
a[diff[:k]] = True
b[diff[k:]] = True
def quartet_test(packed, overlap, tree_rank, clade, n_quartets, bin_edges, rng):
"""Exact 4-way co-presence counts for random genome quartets.
Returns (counts, ratio_to_min_pair, depth_stratum), one entry per quartet.
"""
n = packed.shape[0]
quartets = np.argpartition(rng.random((n_quartets, n)), 3, axis=1)[:, :4]
counts = np.zeros(n_quartets, dtype=np.int64)
block = 2048 # bytes of packed columns per pass: bounds the (Q, block) gathers
for a in range(0, packed.shape[1], block):
blk = packed[:, a:a + block]
acc = blk[quartets[:, 0]] & blk[quartets[:, 1]]
acc &= blk[quartets[:, 2]]
acc &= blk[quartets[:, 3]]
counts += np.bitwise_count(acc).sum(axis=1, dtype=np.int64)
pair_min = np.full(n_quartets, np.iinfo(np.int64).max)
for x in range(4):
for y in range(x + 1, 4):
pair_min = np.minimum(pair_min, overlap[quartets[:, x], quartets[:, y]])
ranks = tree_rank[quartets]
csize = clade[ranks.min(axis=1), ranks.max(axis=1)]
stratum = np.searchsorted(bin_edges, csize, side="right") - 1
return counts, counts / np.maximum(pair_min, 1), stratum
def main():
ap = argparse.ArgumentParser(description=__doc__.split("\n\n")[0])
ap.add_argument("alignment")
ap.add_argument("treefile")
ap.add_argument("-o", "--output", required=True, help="output file prefix")
ap.add_argument("--outgroup", help="tip label to root the tree on")
ap.add_argument("--absent", default="-?", help="absence symbols (default '-?')")
ap.add_argument("--chunk", type=int, default=131072,
help="columns per chunk, multiple of 8 (default 131072)")
ap.add_argument("--quartet-test", action="store_true",
help="measure exact 4-way coverage of random genome quartets")
ap.add_argument("--quartets", type=int, default=20000,
help="number of random quartets (default 20000)")
ap.add_argument("--lift-test", action="store_true",
help="run the margin-preserving lift test (see module doc)")
ap.add_argument("--lift-columns", type=int, default=200000,
help="random columns used by the lift test (default 200000)")
ap.add_argument("--lift-frac", type=float, default=0.1,
help="fraction of partners ranked rare / abundant (default 0.1)")
ap.add_argument("--null-reps", type=int, default=20)
ap.add_argument("--trades", type=int, default=5000,
help="curveball trades between replicates, also burn-in (default 5000)")
ap.add_argument("--seed", type=int, default=None)
args = ap.parse_args()
if args.chunk % 8:
sys.exit("--chunk must be a multiple of 8")
rng = np.random.default_rng(args.seed)
labels, packed, length = read_fasta_presence(args.alignment, args.absent)
keep_p = min(1.0, args.lift_columns / length) if args.lift_test else 0.0
sampled = []
with open(args.treefile) as fh:
names, parent, blen = parse_newick(fh.read())
leaf_labels, clade, patristic = leaf_order_matrices(names, parent, blen, args.outgroup)
if set(leaf_labels) != set(labels):
sys.exit("tree tips and alignment records differ")
n = len(labels)
tree_row = np.array([labels.index(l) for l in leaf_labels]) # tree rank -> alignment row
bin_edges = np.array([2, 3, 5, 9, 17, 33, 65, 129, n + 1]) # clade-size strata
nb = len(bin_edges) - 1
cnt = np.zeros(nb, dtype=np.int64)
closed = np.zeros(nb, dtype=np.int64)
sum_ratio = np.zeros(nb)
sum_missing = np.zeros(nb)
overlap = np.zeros((n, n), dtype=np.int64)
n_cols_lt2 = 0
for a in range(0, length, args.chunk):
b = min(a + args.chunk, length)
pres = np.unpackbits(packed[:, a // 8:(b + 7) // 8], axis=1)[:, :b - a]
if keep_p:
sampled.append(pres[:, rng.random(b - a) < keep_p].astype(bool))
overlap += np.rint(pres.astype(np.float32) @ pres.astype(np.float32).T).astype(np.int64)
t = pres[tree_row]
size = t.sum(axis=0)
keep = size >= 2
n_cols_lt2 += int((~keep).sum())
t, size = t[:, keep], size[keep]
lo = t.argmax(axis=0)
hi = n - 1 - t[::-1].argmax(axis=0)
csize = clade[lo, hi]
stratum = np.searchsorted(bin_edges, csize, side="right") - 1
cnt += np.bincount(stratum, minlength=nb)
closed += np.bincount(stratum, weights=(size == csize), minlength=nb).astype(np.int64)
sum_ratio += np.bincount(stratum, weights=size / csize, minlength=nb)
sum_missing += np.bincount(stratum, weights=csize - size, minlength=nb)
np.fill_diagonal(overlap, 0)
with open(f"{args.output}_family_overlap.csv", "w") as fh:
fh.write("genome," + ",".join(labels) + "\n")
for l, row in zip(labels, overlap):
fh.write(l + "," + ",".join(map(str, row)) + "\n")
with open(f"{args.output}_nesting.csv", "w") as fh:
fh.write("clade_size_min,clade_size_max,n_families,mean_completeness,"
"frac_clade_closed,mean_missing_in_clade\n")
for k in range(nb):
if cnt[k]:
fh.write(f"{bin_edges[k]},{bin_edges[k + 1] - 1},{cnt[k]},"
f"{sum_ratio[k] / cnt[k]:.4f},{closed[k] / cnt[k]:.4f},"
f"{sum_missing[k] / cnt[k]:.3f}\n")
off = overlap[np.triu_indices(n, 1)]
print(f"genomes={n} columns={length} (columns with <2 calls skipped for nesting: {n_cols_lt2})")
print(f"overlap off-diagonal: min={off.min()} median={int(np.median(off))} "
f"max={off.max()} CV={off.std() / off.mean():.3f}")
tot = cnt.sum()
print(f"clade-closed families: {closed.sum()}/{tot} ({closed.sum() / tot:.3f}); "
f"mean completeness {sum_ratio.sum() / tot:.3f}")
print(f"wrote {args.output}_family_overlap.csv and {args.output}_nesting.csv")
if args.quartet_test:
tree_rank = np.empty(n, dtype=np.int64)
tree_rank[tree_row] = np.arange(n)
counts, ratio, stratum = quartet_test(
packed, overlap, tree_rank, clade, args.quartets, bin_edges, rng)
print(f"quartet test: {args.quartets} random quartets over {length} columns")
q = np.quantile(counts, [0, .01, .1, .5, .9, .99, 1])
print("4-way count quantiles 0/1/10/50/90/99/100 %: " + " ".join(f"{v:.0f}" for v in q)
+ f"; uncovered: {(counts == 0).mean():.4f}; CV={counts.std() / max(counts.mean(), 1e-9):.2f}")
with open(f"{args.output}_quartets.csv", "w") as fh:
fh.write("depth_clade_min,depth_clade_max,n_quartets,median_count,q10_count,"
"frac_uncovered,median_ratio_to_min_pair\n")
for k in range(nb):
m = stratum == k
if m.any():
c = counts[m]
fh.write(f"{bin_edges[k]},{bin_edges[k + 1] - 1},{int(m.sum())},{np.median(c):.0f},"
f"{np.quantile(c, .1):.0f},{(c == 0).mean():.4f},{np.median(ratio[m]):.4f}\n")
print(f"wrote {args.output}_quartets.csv")
if args.lift_test:
pres = np.ascontiguousarray(np.hstack(sampled))
print(f"lift test on {pres.shape[1]} columns, {args.null_reps} null replicates")
rows = [("observed",) + lift_stats(pres, args.lift_frac)]
curveball(pres, args.trades, rng) # burn-in
for r in range(args.null_reps):
rows.append((f"null{r + 1}",) + lift_stats(pres, args.lift_frac))
curveball(pres, args.trades, rng)
with open(f"{args.output}_lift_test.csv", "w") as fh:
fh.write("replicate,L,T\n")
for name, l, t in rows:
fh.write(f"{name},{l:.6f},{t:.6f}\n")
for idx, label in ((1, "L (lift)"), (2, "T = P(C|A,B)")):
obs = rows[0][idx]
null = np.array([r[idx] for r in rows[1:]])
p = (1 + (null >= obs).sum()) / (1 + len(null))
print(f"{label}: observed={obs:.4f} null mean={null.mean():.4f} "
f"sd={null.std(ddof=1):.4f} z={(obs - null.mean()) / null.std(ddof=1):.1f} "
f"p(null>=obs)={p:.3f}")
print(f"wrote {args.output}_lift_test.csv")
if __name__ == "__main__":
main()
+12 -2
View File
@@ -98,6 +98,15 @@ version = "1.0.104"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "330a5ed07fa54e4702c9d6c4174f74427fc0ef6e214bbd677ae50a5099946470" checksum = "330a5ed07fa54e4702c9d6c4174f74427fc0ef6e214bbd677ae50a5099946470"
[[package]]
name = "approx"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cab112f0a86d568ea0e627cc1d6be74a1e9cd55214684db5561995f6dad897c6"
dependencies = [
"num-traits",
]
[[package]] [[package]]
name = "arbitrary-chunks" name = "arbitrary-chunks"
version = "0.4.1" version = "0.4.1"
@@ -1523,7 +1532,7 @@ dependencies = [
[[package]] [[package]]
name = "obikmer" name = "obikmer"
version = "1.3.5" version = "1.3.6"
dependencies = [ dependencies = [
"clap", "clap",
"csv", "csv",
@@ -1585,7 +1594,6 @@ dependencies = [
"obikindex", "obikindex",
"obikindexer", "obikindexer",
"obikseq", "obikseq",
"obiksession",
"obipipeline", "obipipeline",
"obiread", "obiread",
"obiskbuilder", "obiskbuilder",
@@ -1665,8 +1673,10 @@ dependencies = [
name = "obiksession" name = "obiksession"
version = "0.1.0" version = "0.1.0"
dependencies = [ dependencies = [
"approx",
"memmap2", "memmap2",
"obisys", "obisys",
"serde",
"tempfile", "tempfile",
"tracing", "tracing",
"xxhash-rust", "xxhash-rust",
+1 -1
View File
@@ -1,6 +1,6 @@
[package] [package]
name = "obikmer" name = "obikmer"
version = "1.3.5" version = "1.3.6"
edition = "2024" edition = "2024"
[[bin]] [[bin]]
+70 -22
View File
@@ -32,11 +32,42 @@ fn parse_gamma_shape(s: &str) -> Result<GammaShapeArg, String> {
.map_err(|_| format!("invalid --gamma-shape value {s:?}: expected a positive number or \"auto\"/\"estimate\"")) .map_err(|_| format!("invalid --gamma-shape value {s:?}: expected a positive number or \"auto\"/\"estimate\""))
} }
/// `--n-sites` CLI value: a number of sites to draw, or `all` for every site
/// — the draw then keeps every variable family that passes the other filters,
/// with no sampling involved. Its own tiny type (like [`GammaShapeArg`]) so
/// the two cases stay distinct up to the call that needs the target, instead
/// of an in-band sentinel (a negative number, `0`, ...) that a typo could hit.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum NSitesArg {
All,
N(usize),
}
impl NSitesArg {
/// The target to hand to the sampler: `None` = exhaustive.
pub fn target(self) -> Option<usize> {
match self {
NSitesArg::All => None,
NSitesArg::N(n) => Some(n),
}
}
}
fn parse_n_sites(s: &str) -> Result<NSitesArg, String> {
if s.eq_ignore_ascii_case("all") {
return Ok(NSitesArg::All);
}
s.parse::<usize>()
.map(NSitesArg::N)
.map_err(|_| format!("invalid --n-sites value {s:?}: expected a non-negative integer or \"all\""))
}
/// `--distance` value — either one of `obikphylo::DistanceMetric`'s /// `--distance` value — either one of `obikphylo::DistanceMetric`'s
/// whole-index metrics (routed to `IndexCache::distance`) or one of /// whole-index metrics (routed to `IndexCache::distance`) or one of
/// `obikphylo::SnpDistanceKind`'s `snp-*` corrections (routed to /// `obikphylo::SnpDistanceKind`'s `snp-*` corrections (routed to
/// `SiblingExt::snp_distance`, the sibling-annex pipeline) — two genuinely /// `obikphylo::siblings::distance_matrix`, over a tally built by
/// different code paths behind one CLI vocabulary, see /// `sampled_scan`/`PairwiseReducer`, the sibling-annex pipeline) — two
/// genuinely different code paths behind one CLI vocabulary, see
/// `DevDocMD/theory/evolutionary_distances.md`, "`--distance` unification". /// `DevDocMD/theory/evolutionary_distances.md`, "`--distance` unification".
#[derive(clap::ValueEnum, Clone, Copy, Debug)] #[derive(clap::ValueEnum, Clone, Copy, Debug)]
pub enum DistanceArg { pub enum DistanceArg {
@@ -107,7 +138,7 @@ impl DistanceArg {
/// (classic metrics + `snp-*` corrections/NJ/UPGMA), annex construction /// (classic metrics + `snp-*` corrections/NJ/UPGMA), annex construction
/// (`--sibling-annex`), annex diagnostics (`--sibling-stats`, /// (`--sibling-annex`), annex diagnostics (`--sibling-stats`,
/// `--sibling-hist`), entropy reporting (`--shannon`), SNP pseudo-alignment /// `--sibling-hist`), entropy reporting (`--shannon`), SNP pseudo-alignment
/// sampling (`--pseudo-alignment`, `--subsample`, `--free-loss`, /// sampling (`--pseudo-alignment`, `--n-sites`, `--free-loss`,
/// `--no-ambiguity`, `--entropy`/`--entropy-sd`), Sankoff cost-matrix /// `--no-ambiguity`, `--entropy`/`--entropy-sd`), Sankoff cost-matrix
/// calibration (`--sankoff`, `--sankoff-ratio-ceiling`) and its TNT/PhyG/ /// calibration (`--sankoff`, `--sankoff-ratio-ceiling`) and its TNT/PhyG/
/// IQ-TREE exports (`--tnt`, `--phyg`, `--iqtree`/`--iqtree-min-freq`, /// IQ-TREE exports (`--tnt`, `--phyg`, `--iqtree`/`--iqtree-min-freq`,
@@ -121,10 +152,10 @@ pub struct PhyloArgs {
/// Exclude a genome (by its exact label) — from `--pseudo-alignment`'s /// Exclude a genome (by its exact label) — from `--pseudo-alignment`'s
/// sampling (a family whose only polymorphism lived in an excluded /// sampling (a family whose only polymorphism lived in an excluded
/// genome is discarded during sampling, not filtered afterward — see /// genome is discarded during sampling, not filtered afterward — see
/// `obikphylo::siblings::extensions::SiblingExt::snp_pseudo_alignment`'s /// `obikphylo::siblings::sampled_scan`'s own docs) and from the
/// own docs) and from the distance matrix / shared-kmer matrix CSV /// distance matrix / shared-kmer matrix CSV output (row and column
/// output (row and column both dropped; the underlying computation /// both dropped; the underlying computation itself is unaffected).
/// itself is unaffected). Repeatable. /// Repeatable.
#[arg(long = "exclude-genome", value_name = "LABEL")] #[arg(long = "exclude-genome", value_name = "LABEL")]
pub exclude_genome: Vec<String>, pub exclude_genome: Vec<String>,
@@ -179,27 +210,25 @@ pub struct PhyloArgs {
/// Write a per-family Shannon entropy report (CSV) — requires an /// Write a per-family Shannon entropy report (CSV) — requires an
/// already-built sibling annex (`--sibling-annex` first, in this /// already-built sibling annex (`--sibling-annex` first, in this
/// invocation or an earlier one). Always a full, unsampled scan of /// invocation or an earlier one). Always a full, unsampled scan of
/// every family (`--subsample`/`--entropy`/`--entropy-sd` below only /// every family (`--n-sites`/`--entropy`/`--entropy-sd` below only
/// apply to `--pseudo-alignment`, not this). /// apply to `--pseudo-alignment`, not this).
#[arg(long)] #[arg(long)]
pub shannon: bool, pub shannon: bool,
/// Write a SNP-only pseudo-alignment (FASTA) — requires /// Write a SNP-only pseudo-alignment (FASTA) — requires
/// `--subsample <N>` and an already-built sibling annex /// `--n-sites <N|all>` and an already-built sibling annex
/// (`--sibling-annex` first, in this invocation or an earlier one). /// (`--sibling-annex` first, in this invocation or an earlier one).
#[arg(long)] #[arg(long)]
pub pseudo_alignment: bool, pub pseudo_alignment: bool,
/// Target number of variable sites to sample index-wide for /// Number of variable sites to draw index-wide, or `all` for every site
/// `--pseudo-alignment`/`--sankoff` (mandatory for both) and for a /// that passes the other filters (no sampling then). Mandatory for
/// `snp-*` `--distance` value (optional there: omitted means exhaustive /// `--pseudo-alignment`/`--sankoff`; optional for a `snp-*`
/// — every non-monomorphic minorant of the whole index, not an /// `--distance` value, where omitting it also means every site. A
/// approximation, see `obikphylo::siblings::SiblingExt::snp_distance`'s /// number is a target, not a guarantee (proportional per-layer
/// own docs) — a target, not a guarantee when given (proportional /// sampling; see `obikphylo::siblings::sampled_scan`'s own docs).
/// per-layer sampling; see #[arg(long = "n-sites", value_name = "N|all", value_parser = parse_n_sites)]
/// `obikphylo::siblings::SiblingExt::snp_pseudo_alignment`'s own docs). pub n_sites: Option<NSitesArg>,
#[arg(long)]
pub subsample: Option<usize>,
/// In `--pseudo-alignment`, treat a genome carrying none of a family's /// In `--pseudo-alignment`, treat a genome carrying none of a family's
/// observed members (`∅`) as missing data (`?`) rather than a real /// observed members (`∅`) as missing data (`?`) rather than a real
@@ -213,6 +242,24 @@ pub struct PhyloArgs {
#[arg(long)] #[arg(long)]
pub no_ambiguity: bool, pub no_ambiguity: bool,
/// In `--pseudo-alignment`/`--sankoff`/`snp-*` `--distance`, keep only
/// the families that can separate two pairs of genomes from each other
/// (a bipartition): at least two distinct called states, each carried
/// by at least two genomes. A singleton variant, or a family carried by
/// fewer than four genomes, fits every topology and tells a tree
/// nothing. Which genomes count as carriers follows `--no-ambiguity`.
#[arg(long)]
pub quartet: bool,
/// In `--pseudo-alignment`/`--sankoff`/`snp-*` `--distance`, favour the
/// families that cover the pairs of genomes sharing the fewest families
/// across the index: each family is weighted by the mean, over the pairs
/// of genomes carrying it, of 1 / (number of families the pair shares).
/// Evens out how well each pair of genomes is represented in the sample.
/// Which genomes count as carriers follows `--no-ambiguity`.
#[arg(long)]
pub pair_balance: bool,
/// Entropy-biased sampling target (Gaussian kernel mean) for /// Entropy-biased sampling target (Gaussian kernel mean) for
/// `--pseudo-alignment` — activates biasing as soon as this or /// `--pseudo-alignment` — activates biasing as soon as this or
/// `--entropy-sd` is given; the other defaults to 1.0/0.5. /// `--entropy-sd` is given; the other defaults to 1.0/0.5.
@@ -227,7 +274,7 @@ pub struct PhyloArgs {
/// Persist the `snp-*` `--distance` sample (the pairwise substitution /// Persist the `snp-*` `--distance` sample (the pairwise substitution
/// tally) in `DIR` across separate `obikmer phylo` invocations: a later /// tally) in `DIR` across separate `obikmer phylo` invocations: a later
/// run against the same index with the exact same /// run against the same index with the exact same
/// `--subsample`/`--free-loss`/`--no-ambiguity`/`--exclude-genome`/ /// `--n-sites`/`--free-loss`/`--no-ambiguity`/`--quartet`/`--exclude-genome`/
/// `--min-shared-family`/`--entropy`/`--entropy-sd` restores it instead /// `--min-shared-family`/`--entropy`/`--entropy-sd` restores it instead
/// of resampling. `DIR` is created if it doesn't exist. If it already /// of resampling. `DIR` is created if it doesn't exist. If it already
/// holds a sample built under *different* selection parameters, this /// holds a sample built under *different* selection parameters, this
@@ -247,7 +294,7 @@ pub struct PhyloArgs {
/// Calibrate a 16-state Sankoff cost matrix (and its matching /// Calibrate a 16-state Sankoff cost matrix (and its matching
/// pseudo-alignment) from an already-built sibling annex — requires /// pseudo-alignment) from an already-built sibling annex — requires
/// `--subsample <N>`, and shares `--free-loss`/`--no-ambiguity`/ /// `--n-sites <N|all>`, and shares `--free-loss`/`--no-ambiguity`/`--quartet`/
/// `--entropy`/`--entropy-sd` with `--pseudo-alignment` (one draw, same /// `--entropy`/`--entropy-sd` with `--pseudo-alignment` (one draw, same
/// selection feeds both the alignment and every calibration tally). /// selection feeds both the alignment and every calibration tally).
#[arg(long)] #[arg(long)]
@@ -329,7 +376,8 @@ pub struct PhyloArgs {
/// the central-position SNP substitution spectrum (`snp-raw`, `snp-jc`, /// the central-position SNP substitution spectrum (`snp-raw`, `snp-jc`,
/// `snp-k2p`, `snp-k81`, `snp-f81`, `snp-t92`, `snp-tn93`, `snp-tv`) — /// `snp-k2p`, `snp-k81`, `snp-f81`, `snp-t92`, `snp-tn93`, `snp-tv`) —
/// the latter route to a different computation entirely /// the latter route to a different computation entirely
/// (`SiblingExt::snp_distance`, requires `--sibling-annex` first; see /// (`obikphylo::siblings::sampled_scan` + `distance_matrix`, requires
/// `--sibling-annex` first; see
/// `DevDocMD/theory/evolutionary_distances.md`, "`--distance` /// `DevDocMD/theory/evolutionary_distances.md`, "`--distance`
/// unification" for the full catalog and why LogDet/Tajima-Nei/F84/ /// unification" for the full catalog and why LogDet/Tajima-Nei/F84/
/// HKY85 aren't offered yet). /// HKY85 aren't offered yet).
+100 -138
View File
@@ -11,56 +11,20 @@ use std::sync::Arc;
use obikidxcache::index_cache::IndexCache; use obikidxcache::index_cache::IndexCache;
use obikindex::KmerIndex; use obikindex::KmerIndex;
use obikphylo::siblings::{ use obikphylo::siblings::{
EntropyBias, GammaShape, SiblingExt, cardinality_transition_probs, EntropyBias, GammaShape, SamplingSpec, SiblingExt, cardinality_transition_probs,
composition_transition_probs, pairwise_cost_matrix, composition_transition_probs, pairwise_cost_matrix,
}; };
use obikphylo::{Metrics, neighbor_joining, upgma}; use obikphylo::{Metrics, neighbor_joining, upgma};
use obisys::{Reporter, Stage}; use obisys::{Reporter, Stage};
use tracing::info; use tracing::info;
use args::NSitesArg;
use iqtree::write_iqtree; use iqtree::write_iqtree;
use phyg::write_sankoff_phyg; use phyg::write_sankoff_phyg;
use phylip::write_phylip_relaxed; use phylip::write_phylip_relaxed;
use sankoff::{write_sankoff_alignment_fasta, write_sankoff_matrix_csv, write_sankoff_params}; use sankoff::{write_sankoff_alignment_fasta, write_sankoff_matrix_csv, write_sankoff_params};
use tnt::write_sankoff_tnt; use tnt::write_sankoff_tnt;
/// Deterministic byte encoding of the `snp-*` `--distance` selection
/// parameters, for `obiksession::Session::open`'s params-conflict check.
/// `obiksession` treats this as an opaque blob (see its own crate docs) —
/// only this module needs to know the layout, and only well enough to
/// produce/compare it, never to pretty-print a per-field diff (v1 keeps
/// the conflict message generic rather than decoding both sides field by
/// field — see its use in `run` below).
fn session_params_blob(
n: Option<usize>,
free_loss: bool,
no_ambiguity: bool,
excluded: &[bool],
entropy_bias: Option<EntropyBias>,
) -> Vec<u8> {
let mut buf = Vec::new();
match n {
Some(v) => {
buf.push(1);
buf.extend_from_slice(&(v as u64).to_le_bytes());
}
None => buf.push(0),
}
buf.push(free_loss as u8);
buf.push(no_ambiguity as u8);
buf.extend_from_slice(&(excluded.len() as u64).to_le_bytes());
buf.extend(excluded.iter().map(|&b| b as u8));
match entropy_bias {
Some(EntropyBias { mu, sigma }) => {
buf.push(1);
buf.extend_from_slice(&mu.to_le_bytes());
buf.extend_from_slice(&sigma.to_le_bytes());
}
None => buf.push(0),
}
buf
}
pub use args::PhyloArgs; pub use args::PhyloArgs;
pub fn run(args: PhyloArgs) { pub fn run(args: PhyloArgs) {
@@ -82,10 +46,10 @@ pub fn run(args: PhyloArgs) {
let n = labels.len(); let n = labels.len();
// ── Genome exclusion (`--exclude-genome`) ─────────────────────────────────── // ── Genome exclusion (`--exclude-genome`) ───────────────────────────────────
// Resolved once, up front: `snp_pseudo_alignment` needs it baked into // Resolved once, up front: `sampled_scan` needs it baked into sampling
// sampling itself (see its own docs), and the distance/shared-kmer CSV // itself (see its own docs), and the distance/shared-kmer CSV writers
// writers below just skip these rows/columns at write time — the // below just skip these rows/columns at write time — the underlying
// underlying `cache.distance(...)` computation is unaffected either way. // `cache.distance(...)` computation is unaffected either way.
let exclude_mask: Vec<bool> = { let exclude_mask: Vec<bool> = {
let mut mask = vec![false; n]; let mut mask = vec![false; n];
for label in &args.exclude_genome { for label in &args.exclude_genome {
@@ -191,7 +155,7 @@ pub fn run(args: PhyloArgs) {
// ── Family Overlap matrix (`--family-overlap`) ────────────────────────────── // ── Family Overlap matrix (`--family-overlap`) ──────────────────────────────
if args.family_overlap { if args.family_overlap {
let t = Stage::start("family_overlap"); let t = Stage::start("family_overlap");
let overlap = cache.family_overlap().unwrap_or_else(|e| { let overlap = cache.family_overlap(args.no_ambiguity).unwrap_or_else(|e| {
eprintln!("error computing family overlap: {e}"); eprintln!("error computing family overlap: {e}");
std::process::exit(1); std::process::exit(1);
}); });
@@ -238,7 +202,7 @@ pub fn run(args: PhyloArgs) {
// `args::PhyloArgs::min_shared_family`'s own docs on why). // `args::PhyloArgs::min_shared_family`'s own docs on why).
let snp_exclude_mask: Vec<bool> = match args.min_shared_family { let snp_exclude_mask: Vec<bool> = match args.min_shared_family {
Some(threshold) => { Some(threshold) => {
let overlap = cache.family_overlap().unwrap_or_else(|e| { let overlap = cache.family_overlap(args.no_ambiguity).unwrap_or_else(|e| {
eprintln!("error computing family overlap: {e}"); eprintln!("error computing family overlap: {e}");
std::process::exit(1); std::process::exit(1);
}); });
@@ -272,64 +236,92 @@ pub fn run(args: PhyloArgs) {
} else { } else {
None None
}; };
let sampling = SamplingSpec {
free_loss: args.free_loss,
no_ambiguity: args.no_ambiguity,
quartet: args.quartet,
pair_balance: args.pair_balance,
entropy_bias,
};
// ── `--session`: persist the snp-* sample across separate invocations ── // ── `--session` ──────────────────────────────────────────────────────────
// Only covers `snp-*` `--distance` today (see `--session`'s own docs); // Temporarily unavailable: the per-driver checkpoint/resume plumbing
// `None` when `--session` isn't given, matching today's always-resample // it relied on (`algorithms::session_cache`) was removed along with
// default exactly. // the three independent sampling drivers it patched over (see
let session = args.session.as_ref().map(|dir| { // `algorithms::scan`'s own module docs) — persistence needs to be
let params = session_params_blob( // rebuilt on top of the new single `sampled_scan` trunk instead of
args.subsample, // silently becoming a no-op.
args.free_loss, if args.session.is_some() {
args.no_ambiguity, eprintln!(
&snp_exclude_mask, "error: --session is temporarily unavailable (being rebuilt on top of the unified \
entropy_bias, sampling trunk) — rerun without --session/--session-force"
); );
match obiksession::Session::open(dir, &params, args.session_force) { std::process::exit(1);
Ok(Ok(session)) => { }
match session.outcome() {
obiksession::SessionOutcome::Created => { // ── Sampled SNP scan (`--pseudo-alignment`, Sankoff group, `snp-*` `--distance`) ──
info!("--session {}: starting fresh", dir.display()); // All three consume exactly the same selection parameters
} // (`--n-sites`/`--free-loss`/`--no-ambiguity`/`--quartet`/`--exclude-genome`/
obiksession::SessionOutcome::Reused => { // `--min-shared-family`/`--entropy`/`--entropy-sd`), and must draw from
info!("--session {}: found, will reuse its cached sample if present", dir.display()); // the *same* random sample when combined in one invocation — so
} // whichever of them are requested here share exactly one
} // `sampled_scan` call, each contributing only the reducer(s) it needs,
session // instead of each running its own scan (which used to silently draw a
} // different sample per flag — see `obikphylo::siblings::LayerReducer`'s
Ok(Err(_conflict)) => { // own module docs).
eprintln!( let sankoff_requested = args.sankoff || args.tnt || args.phyg || args.iqtree;
"error: --session {} was built with different selection parameters \ let snp_kind = args.distance.as_snp();
(--subsample/--free-loss/--no-ambiguity/--exclude-genome/--min-shared-family/\ let need_alignment = args.pseudo_alignment || sankoff_requested;
--entropy/--entropy-sd) than this run — pass --session-force to discard its \ let need_pairwise = sankoff_requested || snp_kind.is_some();
cached sample and start fresh, or point --session at a different directory", // `None` = every site (`--n-sites all`, or `--n-sites` omitted where it is optional)
dir.display() let target = args.n_sites.and_then(NSitesArg::target);
);
std::process::exit(1); if args.pseudo_alignment && args.n_sites.is_none() {
} eprintln!("error: --pseudo-alignment requires --n-sites <N|all>");
Err(e) => { std::process::exit(1);
eprintln!("error opening --session {}: {e}", dir.display()); }
std::process::exit(1); if sankoff_requested && args.n_sites.is_none() {
} eprintln!("error: --sankoff requires --n-sites <N|all>");
std::process::exit(1);
}
let mut alignment_reducer =
need_alignment.then(|| obikphylo::siblings::AlignmentReducer::new(&cache, &snp_exclude_mask));
let mut pairwise_reducer = need_pairwise.then(|| obikphylo::siblings::PairwiseReducer::new(n));
if need_alignment || need_pairwise {
let mut reducers: Vec<&mut dyn obikphylo::siblings::LayerReducer> = Vec::new();
if let Some(r) = alignment_reducer.as_mut() {
reducers.push(r);
}
if let Some(r) = pairwise_reducer.as_mut() {
reducers.push(r);
} }
});
// ── SNP pseudo-alignment (`--pseudo-alignment`) ───────────────────────────── info!(
if args.pseudo_alignment { "sampling SNP sites{}",
let Some(subsample_n) = args.subsample else { match target {
eprintln!("error: --pseudo-alignment requires --subsample <N>"); Some(n) => format!(" (target {n} site(s))"),
std::process::exit(1); None => " (exhaustive)".into(),
}; }
);
info!("sampling SNP pseudo-alignment (target {subsample_n} site(s))"); let t = Stage::start("sampled_scan");
let t = Stage::start("pseudo_alignment"); obikphylo::siblings::sampled_scan(&cache, target, sampling, &snp_exclude_mask, &mut reducers)
let alignment = cache
.snp_pseudo_alignment(subsample_n, args.free_loss, args.no_ambiguity, &snp_exclude_mask, entropy_bias)
.unwrap_or_else(|e| { .unwrap_or_else(|e| {
eprintln!("error building pseudo-alignment: {e}"); eprintln!("error sampling SNP sites: {e}");
std::process::exit(1); std::process::exit(1);
}); });
rep.push(t.stop()); rep.push(t.stop());
}
// Finished once here (not left as reducers) so `--pseudo-alignment`
// and the Sankoff group can each read it below without fighting over
// which one consumes it — see `SankoffBundle::finish`'s own docs.
let alignment = alignment_reducer.map(obikphylo::siblings::AlignmentReducer::finish);
// ── SNP pseudo-alignment (`--pseudo-alignment`) ─────────────────────────────
if args.pseudo_alignment {
let alignment = alignment.as_ref().expect("scanned above: need_alignment");
let path = args.output.as_ref() let path = args.output.as_ref()
.map(|p| format!("{}_alignment.fasta", p.display())) .map(|p| format!("{}_alignment.fasta", p.display()))
@@ -350,33 +342,17 @@ pub fn run(args: PhyloArgs) {
// `snp-*` `--distance` branch below can reuse its already-sampled // `snp-*` `--distance` branch below can reuse its already-sampled
// tally instead of resampling — see `SankoffBundle::snp_distance`'s own // tally instead of resampling — see `SankoffBundle::snp_distance`'s own
// docs for why that's required for correctness, not just speed, when // docs for why that's required for correctness, not just speed, when
// both are requested in the same invocation (they always share the // both are requested in the same invocation.
// same `n`/`free_loss`/`no_ambiguity`/excluded-set/`entropy_bias`: the
// CLI has no way to give them different values in one run).
let mut bundle = None; let mut bundle = None;
if args.sankoff || args.tnt || args.phyg || args.iqtree { if sankoff_requested {
let Some(subsample_n) = args.subsample else { let alignment = alignment.clone().expect("scanned above: need_alignment");
eprintln!("error: --sankoff requires --subsample <N>"); let pairwise = pairwise_reducer.take().expect("scanned above: need_pairwise");
std::process::exit(1); let b = obikphylo::siblings::SankoffBundle::finish(
}; alignment,
pairwise,
info!("sampling Sankoff calibration bundle (target {subsample_n} site(s))"); args.sankoff_ratio_ceiling,
let t = Stage::start("sankoff_bundle"); &snp_exclude_mask,
let b = cache );
.sankoff_bundle(
subsample_n,
args.free_loss,
args.no_ambiguity,
&snp_exclude_mask,
entropy_bias,
args.sankoff_ratio_ceiling,
session.as_ref(),
)
.unwrap_or_else(|e| {
eprintln!("error computing Sankoff calibration bundle: {e}");
std::process::exit(1);
});
rep.push(t.stop());
let p_card = cardinality_transition_probs(&b.cardinality_tally); let p_card = cardinality_transition_probs(&b.cardinality_tally);
let p_comp = composition_transition_probs(&b.base_pair_tally); let p_comp = composition_transition_probs(&b.base_pair_tally);
@@ -441,7 +417,7 @@ pub fn run(args: PhyloArgs) {
eprintln!("error: --shared-kmers has no meaning for a snp-* --distance value"); eprintln!("error: --shared-kmers has no meaning for a snp-* --distance value");
std::process::exit(1); std::process::exit(1);
} }
let kind = args.distance.as_snp().expect("DistanceArg is always classic or snp"); let kind = snp_kind.expect("DistanceArg is always classic or snp");
let gamma_shape = args.gamma_shape.map_or(GammaShape::Disabled, Into::into); let gamma_shape = args.gamma_shape.map_or(GammaShape::Disabled, Into::into);
let t = Stage::start("snp_distance"); let t = Stage::start("snp_distance");
let matrix = match &bundle { let matrix = match &bundle {
@@ -453,23 +429,9 @@ pub fn run(args: PhyloArgs) {
b.snp_distance(kind, gamma_shape) b.snp_distance(kind, gamma_shape)
} }
None => { None => {
info!( info!("computing {kind:?} SNP distance for {n} genome(s) (reusing the sampled scan above)");
"computing {kind:?} SNP distance for {n} genome(s){}", let (tally, dispersion) = pairwise_reducer.take().expect("scanned above: need_pairwise").finish();
match args.subsample { obikphylo::siblings::distance_matrix(&tally, &dispersion, kind, gamma_shape)
Some(n) => format!(" (subsampled, target {n} site(s))"),
None => " (exhaustive)".into(),
}
);
cache.snp_distance(
kind,
args.subsample,
args.free_loss,
args.no_ambiguity,
&snp_exclude_mask,
entropy_bias,
gamma_shape,
session.as_ref(),
)
} }
} }
.unwrap_or_else(|e| { .unwrap_or_else(|e| {
+3 -3
View File
@@ -1,5 +1,5 @@
//! Output writers for `--sankoff` — no calibration logic here, just //! Output writers for `--sankoff` — no calibration logic here, just
//! formatting: `obikphylo::siblings::SiblingExt::sankoff_bundle` and the //! formatting: `obikphylo::siblings::SankoffBundle::finish` and the
//! `cardinality_transition_probs`/`composition_transition_probs`/ //! `cardinality_transition_probs`/`composition_transition_probs`/
//! `pairwise_cost_matrix` calibration functions do all the actual work in //! `pairwise_cost_matrix` calibration functions do all the actual work in
//! `mod.rs`, this module only serialises their results. //! `mod.rs`, this module only serialises their results.
@@ -13,8 +13,8 @@ use tracing::info;
// ── Sankoff pseudo-alignment → FASTA ──────────────────────────────────────── // ── Sankoff pseudo-alignment → FASTA ────────────────────────────────────────
// //
// Same data as `--pseudo-alignment`'s output (`SnpAlignment`/ // Same data as `--pseudo-alignment`'s own output (`SnpAlignment`, built by
// `snp_pseudo_alignment`), re-coded so its symbols match the accompanying // `AlignmentReducer`), re-coded so its symbols match the accompanying
// `--sankoff` matrix output exactly: `0` for the empty/absent state instead // `--sankoff` matrix output exactly: `0` for the empty/absent state instead
// of `-`, which TNT/PhyG would otherwise read as their own gap character // of `-`, which TNT/PhyG would otherwise read as their own gap character
// rather than our "family absent" state. Unless `free_loss` (`--free-loss`) // rather than our "family absent" state. Unless `free_loss` (`--free-loss`)
-1
View File
@@ -12,7 +12,6 @@ obicompactvec = { path = "../obicompactvec" }
obikidxcache = { path = "../obikidxcache" } obikidxcache = { path = "../obikidxcache" }
obiskbuilder = { path = "../obiskbuilder" } obiskbuilder = { path = "../obiskbuilder" }
obipipeline = { path = "../obipipeline" } obipipeline = { path = "../obipipeline" }
obiksession = { path = "../obiksession" }
kodama = "0.3.0" kodama = "0.3.0"
memmap2 = "0.9" memmap2 = "0.9"
ndarray = "0.17" ndarray = "0.17"
Loaded 100 of 147 files, more files were not shown because too many files have changed in this diff. Show more