Files
obikmer/doc/implementation/obilayeredmap/index.html
T

1514 lines
48 KiB
HTML
Raw Normal View History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../unitig_evidence/">
<link rel="next" href="../persistent_compact_int_vec/">
<link rel="icon" href="../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.6">
<title>obilayeredmap crate - obikmer</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.484c7ddc.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#obilayeredmap-layered-kmer-index-crate" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="obikmer" class="md-header__button md-logo" aria-label="obikmer" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
obikmer
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
obilayeredmap crate
</span>
</div>
</div>
</div>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="obikmer" class="md-nav__button md-logo" aria-label="obikmer" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
obikmer
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
Theory
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Theory
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../kmers/" class="md-nav__link">
<span class="md-ellipsis">
Kmers and super-kmers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/encoding/" class="md-nav__link">
<span class="md-ellipsis">
DNA encoding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/entropy/" class="md-nav__link">
<span class="md-ellipsis">
Entropy filter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/minimizer/" class="md-nav__link">
<span class="md-ellipsis">
Minimizer selection
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/indexing/" class="md-nav__link">
<span class="md-ellipsis">
Partitioning architecture
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" checked>
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Implementation
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Implementation
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../superkmer/" class="md-nav__link">
<span class="md-ellipsis">
SuperKmer
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../kmer/" class="md-nav__link">
<span class="md-ellipsis">
Kmer
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../chunkreader/" class="md-nav__link">
<span class="md-ellipsis">
Chunk reader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../pipeline/" class="md-nav__link">
<span class="md-ellipsis">
Construction pipeline
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../obipipeline/" class="md-nav__link">
<span class="md-ellipsis">
obipipeline library
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../storage/" class="md-nav__link">
<span class="md-ellipsis">
On-disk storage
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../mphf/" class="md-nav__link">
<span class="md-ellipsis">
MPHF selection
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../unitig_evidence/" class="md-nav__link">
<span class="md-ellipsis">
Unitig evidence encoding
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
obilayeredmap crate
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
obilayeredmap crate
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#purpose" class="md-nav__link">
<span class="md-ellipsis">
Purpose
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#three-usage-modes" class="md-nav__link">
<span class="md-ellipsis">
Three usage modes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mphflayer-autonomous-kmer-slot-mapping" class="md-nav__link">
<span class="md-ellipsis">
MphfLayer — autonomous kmer → slot mapping
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#layerd-layerdata-mphf-payload" class="md-nav__link">
<span class="md-ellipsis">
Layer\&lt;D: LayerData> — MPHF + payload
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#layeredstores-and-aggregation-traits" class="md-nav__link">
<span class="md-ellipsis">
LayeredStore\&lt;S> and aggregation traits
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#on-disk-structure" class="md-nav__link">
<span class="md-ellipsis">
On-disk structure
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#evidence-encoding" class="md-nav__link">
<span class="md-ellipsis">
Evidence encoding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ptr_hash-configuration" class="md-nav__link">
<span class="md-ellipsis">
ptr_hash configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#query-path" class="md-nav__link">
<span class="md-ellipsis">
Query path
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#add-layer-algorithm" class="md-nav__link">
<span class="md-ellipsis">
Add-layer algorithm
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#dependencies" class="md-nav__link">
<span class="md-ellipsis">
Dependencies
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../persistent_compact_int_vec/" class="md-nav__link">
<span class="md-ellipsis">
PersistentCompactIntVec
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../persistent_bit_vec/" class="md-nav__link">
<span class="md-ellipsis">
PersistentBitVec
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-ellipsis">
Architecture
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Architecture
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../architecture/sequences/invariant/" class="md-nav__link">
<span class="md-ellipsis">
Sequences
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../architecture/index_architecture/" class="md-nav__link">
<span class="md-ellipsis">
Kmer index
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#purpose" class="md-nav__link">
<span class="md-ellipsis">
Purpose
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#three-usage-modes" class="md-nav__link">
<span class="md-ellipsis">
Three usage modes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mphflayer-autonomous-kmer-slot-mapping" class="md-nav__link">
<span class="md-ellipsis">
MphfLayer — autonomous kmer → slot mapping
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#layerd-layerdata-mphf-payload" class="md-nav__link">
<span class="md-ellipsis">
Layer\&lt;D: LayerData> — MPHF + payload
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#layeredstores-and-aggregation-traits" class="md-nav__link">
<span class="md-ellipsis">
LayeredStore\&lt;S> and aggregation traits
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#on-disk-structure" class="md-nav__link">
<span class="md-ellipsis">
On-disk structure
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#evidence-encoding" class="md-nav__link">
<span class="md-ellipsis">
Evidence encoding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ptr_hash-configuration" class="md-nav__link">
<span class="md-ellipsis">
ptr_hash configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#query-path" class="md-nav__link">
<span class="md-ellipsis">
Query path
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#add-layer-algorithm" class="md-nav__link">
<span class="md-ellipsis">
Add-layer algorithm
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#dependencies" class="md-nav__link">
<span class="md-ellipsis">
Dependencies
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="obilayeredmap-layered-kmer-index-crate">obilayeredmap — layered kmer index crate</h1>
<h2 id="purpose">Purpose</h2>
<p><code>obilayeredmap</code> implements a persistent, incrementally extensible kmer index. The index is organised in three levels: <strong>index root → partition → layer</strong>. Each layer covers a disjoint kmer set and wraps a <code>ptr_hash</code> MPHF with associated per-slot data. Adding a new dataset never rebuilds existing layers.</p>
<hr />
<h2 id="three-usage-modes">Three usage modes</h2>
<p>The MPHF + evidence infrastructure is the same for all modes. The <strong>payload</strong> varies.</p>
<table>
<thead>
<tr>
<th>Mode</th>
<th>Description</th>
<th>Payload type</th>
<th>Storage</th>
</tr>
</thead>
<tbody>
<tr>
<td>1. Set</td>
<td>membership test only</td>
<td><code>()</code></td>
<td></td>
</tr>
<tr>
<td>2. Count</td>
<td>occurrences per kmer per sample</td>
<td><code>PersistentCompactIntMatrix</code></td>
<td><code>counts/</code> directory</td>
</tr>
<tr>
<td>3. Presence/absence</td>
<td>which genomes contain each kmer</td>
<td><code>PersistentBitMatrix</code></td>
<td><code>presence/</code> directory</td>
</tr>
</tbody>
</table>
<p>Both <code>PersistentCompactIntMatrix</code> and <code>PersistentBitMatrix</code> come from the <code>obicompactvec</code> crate.</p>
<hr />
<h2 id="mphflayer-autonomous-kmer-slot-mapping">MphfLayer — autonomous kmer → slot mapping</h2>
<p><code>MphfLayer</code> encapsulates the MPHF + evidence + unitig spine for one layer. It is independent of any payload data.</p>
<div class="highlight"><pre><span></span><code><span class="k">pub</span><span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">MphfLayer</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">mphf</span><span class="p">:</span><span class="w"> </span><span class="nc">Mphf</span><span class="p">,</span>
<span class="w"> </span><span class="n">evidence</span><span class="p">:</span><span class="w"> </span><span class="nc">Evidence</span><span class="p">,</span>
<span class="w"> </span><span class="n">unitigs</span><span class="p">:</span><span class="w"> </span><span class="nc">UnitigFileReader</span><span class="p">,</span>
<span class="w"> </span><span class="n">n</span><span class="p">:</span><span class="w"> </span><span class="kt">usize</span><span class="p">,</span><span class="w"> </span><span class="c1">// number of indexed kmers = number of MPHF slots</span>
<span class="p">}</span>
</code></pre></div>
<p>Public API:</p>
<div class="highlight"><pre><span></span><code><span class="k">impl</span><span class="w"> </span><span class="n">MphfLayer</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">open</span><span class="p">(</span><span class="n">dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="bp">Self</span><span class="o">&gt;</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">find</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">kmer</span><span class="p">:</span><span class="w"> </span><span class="nc">CanonicalKmer</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nb">Option</span><span class="o">&lt;</span><span class="kt">usize</span><span class="o">&gt;</span><span class="w"> </span><span class="c1">// Some(slot) or None</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">n</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="p">-&gt;</span><span class="w"> </span><span class="kt">usize</span>
<span class="w"> </span><span class="nc">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">unitig_writer</span><span class="p">(</span><span class="n">dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="n">UnitigFileWriter</span><span class="o">&gt;</span>
<span class="w"> </span><span class="k">pub</span><span class="p">(</span><span class="k">crate</span><span class="p">)</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">build</span><span class="p">(</span>
<span class="w"> </span><span class="n">dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">,</span>
<span class="w"> </span><span class="n">fill_slot</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="k">impl</span><span class="w"> </span><span class="nb">FnMut</span><span class="p">(</span><span class="kt">usize</span><span class="p">,</span><span class="w"> </span><span class="n">CanonicalKmer</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="p">()</span><span class="o">&gt;</span><span class="p">,</span>
<span class="w"> </span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="kt">usize</span><span class="o">&gt;</span>
<span class="p">}</span>
</code></pre></div>
<p><code>find</code> returns <code>Some(slot)</code> only after verifying via evidence that the kmer is actually indexed. It returns <code>None</code> for absent keys (ptr_hash maps any input to a valid slot; evidence verification is the only correct-membership test).</p>
<p><code>build</code> runs two sequential passes over <code>unitigs.bin</code>:</p>
<ol>
<li><strong>Pass 1</strong>: iterate all canonical kmers in parallel via rayon, construct and store <code>mphf.bin</code>. <code>new_from_par_iter</code> avoids materialising a full key <code>Vec</code>.</li>
<li><strong>Pass 2</strong>: iterate again sequentially, fill <code>evidence.bin</code>, call <code>fill_slot(slot, kmer)</code> once per kmer for payload population. A compact <code>n/8</code>-byte seen-bitset verifies MPHF injectivity inline.</li>
</ol>
<p>For empty layers (n = 0), <code>build</code> returns <code>Ok(0)</code> immediately after creating empty <code>mphf.bin</code> and <code>evidence.bin</code>.</p>
<hr />
<h2 id="layerd-layerdata-mphf-payload">Layer\&lt;D: LayerData&gt; — MPHF + payload</h2>
<p><code>Layer&lt;D&gt;</code> pairs an <code>MphfLayer</code> with one payload store.</p>
<div class="highlight"><pre><span></span><code><span class="k">pub</span><span class="w"> </span><span class="k">trait</span><span class="w"> </span><span class="n">LayerData</span><span class="p">:</span><span class="w"> </span><span class="nb">Sized</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">type</span><span class="w"> </span><span class="nc">Item</span><span class="p">;</span>
<span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">open</span><span class="p">(</span><span class="n">layer_dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="bp">Self</span><span class="o">&gt;</span><span class="p">;</span>
<span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">read</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">slot</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">Self</span><span class="p">::</span><span class="n">Item</span><span class="p">;</span>
<span class="p">}</span>
<span class="k">pub</span><span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">Layer</span><span class="o">&lt;</span><span class="n">D</span><span class="p">:</span><span class="w"> </span><span class="nc">LayerData</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">()</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">mphf</span><span class="p">:</span><span class="w"> </span><span class="nc">MphfLayer</span><span class="p">,</span>
<span class="w"> </span><span class="n">data</span><span class="p">:</span><span class="w"> </span><span class="nc">D</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">pub</span><span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">Hit</span><span class="o">&lt;</span><span class="n">T</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">()</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="n">slot</span><span class="p">:</span><span class="w"> </span><span class="kt">usize</span><span class="p">,</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="n">data</span><span class="p">:</span><span class="w"> </span><span class="nc">T</span><span class="p">,</span>
<span class="p">}</span>
</code></pre></div>
<p><code>LayerData</code> covers the <strong>read path only</strong> (<code>open</code> + <code>read</code>). Build signatures differ between modes and are not in the trait.</p>
<table>
<thead>
<tr>
<th>Type</th>
<th><code>Item</code></th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>()</code></td>
<td><code>()</code></td>
<td>mode 1 — membership only</td>
</tr>
<tr>
<td><code>PersistentCompactIntMatrix</code></td>
<td><code>Box&lt;[u32]&gt;</code></td>
<td>mode 2 — count matrix (one u32 per column per slot)</td>
</tr>
<tr>
<td><code>PersistentBitMatrix</code></td>
<td><code>Box&lt;[bool]&gt;</code></td>
<td>mode 3 — presence matrix (one bit per genome per slot)</td>
</tr>
</tbody>
</table>
<p><strong>Build signatures:</strong></p>
<div class="highlight"><pre><span></span><code><span class="c1">// mode 1</span>
<span class="k">impl</span><span class="w"> </span><span class="n">Layer</span><span class="o">&lt;</span><span class="p">()</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">build</span><span class="p">(</span><span class="n">out_dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="kt">usize</span><span class="o">&gt;</span>
<span class="p">}</span>
<span class="c1">// mode 2</span>
<span class="k">impl</span><span class="w"> </span><span class="n">Layer</span><span class="o">&lt;</span><span class="n">PersistentCompactIntMatrix</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">build</span><span class="p">(</span><span class="n">out_dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">,</span><span class="w"> </span><span class="n">count_of</span><span class="p">:</span><span class="w"> </span><span class="nc">impl</span><span class="w"> </span><span class="nb">Fn</span><span class="p">(</span><span class="n">CanonicalKmer</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="kt">u32</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="kt">usize</span><span class="o">&gt;</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">build_from_map</span><span class="p">(</span><span class="n">out_dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">,</span><span class="w"> </span><span class="n">counts</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">HashMap</span><span class="o">&lt;</span><span class="n">CanonicalKmer</span><span class="p">,</span><span class="w"> </span><span class="kt">u32</span><span class="o">&gt;</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="kt">usize</span><span class="o">&gt;</span>
<span class="p">}</span>
<span class="c1">// mode 3</span>
<span class="k">impl</span><span class="w"> </span><span class="n">Layer</span><span class="o">&lt;</span><span class="n">PersistentBitMatrix</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">build_presence</span><span class="p">(</span>
<span class="w"> </span><span class="n">out_dir</span><span class="p">:</span><span class="w"> </span><span class="kp">&amp;</span><span class="nc">Path</span><span class="p">,</span>
<span class="w"> </span><span class="n">n_genomes</span><span class="p">:</span><span class="w"> </span><span class="kt">usize</span><span class="p">,</span>
<span class="w"> </span><span class="n">present_in</span><span class="p">:</span><span class="w"> </span><span class="nc">impl</span><span class="w"> </span><span class="nb">Fn</span><span class="p">(</span><span class="n">CanonicalKmer</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="kt">bool</span><span class="p">,</span>
<span class="w"> </span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">OLMResult</span><span class="o">&lt;</span><span class="kt">usize</span><span class="o">&gt;</span>
<span class="p">}</span>
</code></pre></div>
<p>All build impls delegate MPHF + evidence construction to <code>MphfLayer::build</code> via a mode-specific <code>fill_slot</code> callback. Mode 2 pre-reads <code>n_kmers</code> from <code>unitigs.bin</code> to size the <code>PersistentCompactIntMatrixBuilder</code> before calling <code>MphfLayer::build</code>. Mode 3 does the same for <code>PersistentBitMatrixBuilder</code>.</p>
<hr />
<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>
<div class="highlight"><pre><span></span><code><span class="k">pub</span><span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">LayeredStore</span><span class="o">&lt;</span><span class="n">S</span><span class="o">&gt;</span><span class="p">(</span><span class="k">pub</span><span class="w"> </span><span class="nb">Vec</span><span class="o">&lt;</span><span class="n">S</span><span class="o">&gt;</span><span class="p">);</span>
<span class="k">impl</span><span class="o">&lt;</span><span class="n">S</span><span class="p">:</span><span class="w"> </span><span class="nc">ColumnWeights</span><span class="o">&gt;</span><span class="w"> </span><span class="n">ColumnWeights</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="n">LayeredStore</span><span class="o">&lt;</span><span class="n">S</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span><span class="w"> </span><span class="err"></span><span class="w"> </span><span class="p">}</span><span class="w"> </span><span class="c1">// Σ col_weights across inner stores</span>
<span class="k">impl</span><span class="o">&lt;</span><span class="n">S</span><span class="p">:</span><span class="w"> </span><span class="nc">CountPartials</span><span class="o">&gt;</span><span class="w"> </span><span class="n">CountPartials</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="n">LayeredStore</span><span class="o">&lt;</span><span class="n">S</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span><span class="w"> </span><span class="err"></span><span class="w"> </span><span class="p">}</span><span class="w"> </span><span class="c1">// element-wise Σ partials</span>
<span class="k">impl</span><span class="o">&lt;</span><span class="n">S</span><span class="p">:</span><span class="w"> </span><span class="nc">BitPartials</span><span class="o">&gt;</span><span class="w"> </span><span class="n">BitPartials</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="n">LayeredStore</span><span class="o">&lt;</span><span class="n">S</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span><span class="w"> </span><span class="err"></span><span class="w"> </span><span class="p">}</span><span class="w"> </span><span class="c1">// element-wise Σ partials</span>
</code></pre></div>
<p>Because blanket impls compose, <code>LayeredStore&lt;LayeredStore&lt;S&gt;&gt;</code> automatically inherits all three traits when <code>S</code> does — providing the partitioned level without a separate type.</p>
<p><strong>Aggregation hierarchy:</strong></p>
<div class="highlight"><pre><span></span><code>PersistentCompactIntMatrix implements CountPartials
LayeredStore&lt;PersistentCompactIntMatrix&gt; via blanket impl (one partition)
LayeredStore&lt;LayeredStore&lt;&gt;&gt; via blanket impl (partitioned index)
</code></pre></div>
<p><strong>Leaf implementors</strong> (in <code>obicompactvec</code>):</p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Traits</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>PersistentCompactIntMatrix</code></td>
<td><code>ColumnWeights</code> (via <code>sum()</code>) + <code>CountPartials</code></td>
</tr>
<tr>
<td><code>PersistentBitMatrix</code></td>
<td><code>ColumnWeights</code> (via <code>count_ones()</code>) + <code>BitPartials</code></td>
</tr>
</tbody>
</table>
<p><code>PersistentCompactIntVec</code> and <code>PersistentBitVec</code> do not implement these traits — they are single-column primitives, not matrix-level aggregators.</p>
<p>See <a href="../../architecture/index_architecture/">Kmer index architecture</a> for the full trait API and the two-pass normalised-metric pattern.</p>
<hr />
<h2 id="on-disk-structure">On-disk structure</h2>
<div class="highlight"><pre><span></span><code>index_root/ ← LayeredMap (collection)
meta.json
part_00000/ ← Partition
layer_0/ ← Layer
mphf.bin — ptr_hash MPHF (epserde format)
unitigs.bin — packed 2-bit nucleotide sequences
unitigs.bin.idx — UIDX index: n_unitigs, n_kmers, seqls[], packed_offsets[]
evidence.bin — n × u32, each = (chunk_id: 25 bits | rank: 7 bits), LE
counts/ [mode 2] PersistentCompactIntMatrix
meta.json {&quot;n&quot;: N, &quot;n_cols&quot;: 1}
col_000000.pciv
presence/ [mode 3] PersistentBitMatrix
meta.json {&quot;n&quot;: N, &quot;n_cols&quot;: G}
col_000000.pbiv
layer_1/
part_00001/
</code></pre></div>
<p><strong>Partition</strong> (<code>part_XXXXX/</code>): all kmers whose canonical minimiser hashes to this bucket. Partitions are independent and can be processed in parallel.</p>
<p><strong>Layer</strong> (<code>layer_N/</code>): one <code>MphfLayer</code> plus optional payload. Layer 0 covers dataset A; layer 1 covers kmers in B absent from A; etc. Layers within a partition are always disjoint.</p>
<hr />
<h2 id="evidence-encoding">Evidence encoding</h2>
<p><code>evidence.bin</code> is a flat <code>[u32; n]</code> array with no header. Each u32 encodes one slot:</p>
<div class="highlight"><pre><span></span><code>bits [31:7] = chunk_id (25 bits) — index of the unitig chunk
bits [6:0] = rank (7 bits) — kmer index within the chunk (0-based)
</code></pre></div>
<p>Decoding: <code>chunk_id = raw &gt;&gt; 7</code>, <code>rank = raw &amp; 0x7F</code>. Reconstructing the kmer: read k nucleotides at position <code>rank</code> within unitig <code>chunk_id</code>.</p>
<p>For k=31, m=11, the observed maximum is ~46 kmers per chunk — well within the 127-kmer u7 capacity. The structural maximum from superkmer construction is k m + 1 = 21 kmers/unitig; longer unitigs arise from paths spanning more than one superkmer.</p>
<hr />
<h2 id="ptr_hash-configuration">ptr_hash configuration</h2>
<div class="highlight"><pre><span></span><code><span class="k">type</span><span class="w"> </span><span class="nc">Mphf</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">PtrHash</span><span class="o">&lt;</span>
<span class="w"> </span><span class="kt">u64</span><span class="p">,</span><span class="w"> </span><span class="c1">// key type: canonical kmer raw encoding</span>
<span class="w"> </span><span class="n">CubicEps</span><span class="p">,</span><span class="w"> </span><span class="c1">// bucket fn: 2.4 bits/key, λ=3.5, α=0.99</span>
<span class="w"> </span><span class="n">CachelineEfVec</span><span class="o">&lt;</span><span class="nb">Vec</span><span class="o">&lt;</span><span class="n">CachelineEf</span><span class="o">&gt;&gt;</span><span class="p">,</span><span class="w"> </span><span class="c1">// remap: 11.6 bits/entry (Elias-Fano)</span>
<span class="w"> </span><span class="n">Xx64</span><span class="p">,</span><span class="w"> </span><span class="c1">// hasher: XXH3-64 with seed</span>
<span class="w"> </span><span class="nb">Vec</span><span class="o">&lt;</span><span class="kt">u8</span><span class="o">&gt;</span><span class="p">,</span><span class="w"> </span><span class="c1">// pilots</span>
<span class="o">&gt;</span><span class="p">;</span>
</code></pre></div>
<p><code>Xx64</code> is chosen over <code>FxHash</code> because canonical kmer raw values are left-aligned u64 with structural zeros in the low bits (42 zeros for k=11, 2 zeros for k=31), which single-multiply hashes distribute poorly.</p>
<p><code>CubicEps</code> with <code>PtrHashParams::&lt;CubicEps&gt;::default()</code> (λ=3.5) is a balanced tradeoff: 2× slower construction than <code>Linear/λ=3.0</code>, 20% less space.</p>
<hr />
<h2 id="query-path">Query path</h2>
<div class="highlight"><pre><span></span><code><span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">query</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">kmer</span><span class="p">:</span><span class="w"> </span><span class="nc">CanonicalKmer</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nb">Option</span><span class="o">&lt;</span><span class="n">Hit</span><span class="o">&lt;</span><span class="n">D</span><span class="p">::</span><span class="n">Item</span><span class="o">&gt;&gt;</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="bp">self</span><span class="p">.</span><span class="n">mphf</span><span class="p">.</span><span class="n">find</span><span class="p">(</span><span class="n">kmer</span><span class="p">).</span><span class="n">map</span><span class="p">(</span><span class="o">|</span><span class="n">slot</span><span class="o">|</span><span class="w"> </span><span class="n">Hit</span><span class="w"> </span><span class="p">{</span><span class="w"> </span><span class="n">slot</span><span class="p">,</span><span class="w"> </span><span class="n">data</span><span class="p">:</span><span class="w"> </span><span class="nc">self</span><span class="p">.</span><span class="n">data</span><span class="p">.</span><span class="n">read</span><span class="p">(</span><span class="n">slot</span><span class="p">)</span><span class="w"> </span><span class="p">})</span>
<span class="p">}</span>
</code></pre></div>
<p><code>MphfLayer::find</code> probes the MPHF, decodes evidence, and verifies the kmer — returning <code>Some(slot)</code> on match, <code>None</code> otherwise. <code>data.read(slot)</code> is called only on a confirmed hit.</p>
<p>In <code>LayeredMap</code>, layers are probed in order; the first match wins. Expected probe depth: 1 for kmers in layer 0.</p>
<hr />
<h2 id="add-layer-algorithm">Add-layer algorithm</h2>
<p>When adding dataset B to an existing index:</p>
<ol>
<li>For each partition, probe existing layers for kmers of B routed to that partition.</li>
<li>Collect kmers absent from all layers → <code>B \ index</code>.</li>
<li>Write <code>B \ index</code> to a new <code>unitigs.bin</code> via <code>MphfLayer::unitig_writer</code>.</li>
<li>Call <code>Layer&lt;D&gt;::build</code> on the new directory.</li>
<li>Update <code>meta.json</code>.</li>
</ol>
<p>Each partition's new layer is built independently; the operation is fully parallel across partitions.</p>
<hr />
<h2 id="dependencies">Dependencies</h2>
<table>
<thead>
<tr>
<th>crate</th>
<th>role</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>ptr_hash 1.1</code></td>
<td>MPHF per layer</td>
</tr>
<tr>
<td><code>cacheline-ef 1.1</code></td>
<td>compact remap inside ptr_hash</td>
</tr>
<tr>
<td><code>epserde 0.8</code></td>
<td>zero-copy MPHF serialisation</td>
</tr>
<tr>
<td><code>memmap2 0.9</code></td>
<td>mmap of evidence and payload files</td>
</tr>
<tr>
<td><code>obiskio</code></td>
<td>unitig file writer/reader</td>
</tr>
<tr>
<td><code>obicompactvec</code></td>
<td>payload types + aggregation traits</td>
</tr>
<tr>
<td><code>rayon 1</code></td>
<td>parallel MPHF construction pass</td>
</tr>
<tr>
<td><code>ndarray 0.16</code></td>
<td>aggregation output arrays</td>
</tr>
</tbody>
</table>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"annotate": null, "base": "../..", "features": [], "search": "../../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.79ae519e.min.js"></script>
<script src="https://unpkg.com/mathjax@3/es5/tex-mml-chtml.js"></script>
</body>
</html>