feat(phylo): expand genome distance metrics and refactor CLI arguments
Refactor the `phylo` command to support explicit distance metrics (Jaccard, Hamming) and SNP-based pseudo-alignments. Replace implicit metric selection with explicit requirements, such as requiring `--n-sites` for SNP analysis. Add a new `shared-kmers` output option and update documentation for performance characteristics of sparse vs dense formats. - Update `phylo` CLI to support genome-vs-genome distances using k-mer content or SNPs, including options for NJ/UPGMA tree building and data export - Replace `reindex` command with `convert` for in-place index evidence conversion (exact/approx/hybrid) and add `--upgrade-index` to `utils` for missing layer metadata - Refactor `distance_to_compute` logic to remove implicit Jaccard implications for `--nj`/`--upgma` unless `--distance` is specified, and enforce `--n-sites` for `--pseudo-alignment`/`--sankoff` - Add `shared_kmers` method to `Metrics` trait in `src/obikphylo/src/distance.rs` and new `write_shared_kmers` function in `src/obikmer/src/cmd/phylo/shared.rs` for CSV export - Update `PackArgs::dense` documentation to clarify that dense format is faster for column-oriented distance matrices while sparse is better for single-row access - Remove `requires_counts` definition and update assertions in `values.rs` to reflect new distance computation signatures and metric requirements
This commit is contained in:
1 parent
14433e80a5
commit
c4eacb3f72
8 files changed
+126
-109
No files matched your search
+2
-2
@@ -13,11 +13,11 @@
|
|||||||
| `query` | Query an index with sequences and annotate matches |
|
| `query` | Query an index with sequences and annotate matches |
|
||||||
| `dump` | Dump all indexed k-mers as CSV (kmer + per-genome counts or presence); supports the shared [kmer filtering](implementation/filtering.md) system; `--head N` limits output to the first N k-mers |
|
| `dump` | Dump all indexed k-mers as CSV (kmer + per-genome counts or presence); supports the shared [kmer filtering](implementation/filtering.md) system; `--head N` limits output to the first N k-mers |
|
||||||
| `annotate` | Add or update genome metadata from a CSV file; or dump metadata as CSV |
|
| `annotate` | Add or update genome metadata from a CSV file; or dump metadata as CSV |
|
||||||
| `phylo` | Compute pairwise evolutionary-distance proxies between genomes (`--metric jaccard\|mash\|hamming\|bray-curtis\|relfreq-bray-curtis\|euclidean\|relfreq-euclidean\|hellinger\|hellinger-euclidean`); optionally build NJ/UPGMA trees; `--presence-threshold N` sets the minimum count to consider a k-mer present when computing Jaccard/Mash on count indexes (default 1); optionally a central-position SNP/Sankoff calibration with exports for TNT/PhyG/IQ-TREE (see [evolutionary distances](theory/evolutionary_distances.md)) |
|
| `phylo` | Genome-vs-genome distances, trees and SNP-based pseudo-alignments. `--distance` selects either a whole-genome distance computed from k-mer content (`jaccard`, `mash`, `hamming`, `bray-curtis`, `relfreq-bray-curtis`, `euclidean`, `relfreq-euclidean`, `hellinger`, `hellinger-euclidean`; `--presence-threshold N` converts counts to presence for Jaccard/Mash on count indexes; `hamming` is currently refused on count indexes) or a `snp-*` distance (`snp-raw`, `snp-jc`, `snp-k2p`, `snp-k81`, `snp-f81`, `snp-t92`, `snp-tn93`, `snp-tv`; optional `--gamma-shape`) computed from central-position SNPs of k-mer families. `--nj`/`--upgma` build trees (Jaccard if no `--distance`); `--shared-kmers` writes the shared-k-mer count matrix on its own. SNP analyses read the sibling annex, built on demand (`--sibling-annex` forces it), with site selection/sampling options (`--n-sites`, `--quartet`, `--pair-balance`, `--entropy`, `--free-loss`, `--no-ambiguity`/`--only-diploid`, `--session`), a pseudo-alignment export (`--pseudo-alignment`, `--fasta`, `--vcf`) and Sankoff cost calibration with TNT/PhyG/IQ-TREE exports. See [evolutionary distances](theory/evolutionary_distances.md) |
|
||||||
| `unitig` | Build a global de Bruijn graph across all partitions and enumerate its unitigs as FASTA; supports the shared [kmer filtering](implementation/filtering.md) system |
|
| `unitig` | Build a global de Bruijn graph across all partitions and enumerate its unitigs as FASTA; supports the shared [kmer filtering](implementation/filtering.md) system |
|
||||||
| `select` | Project and/or aggregate genome columns into a new or in-place index; the column-axis counterpart of `filter` (see [select](implementation/select.md)) |
|
| `select` | Project and/or aggregate genome columns into a new or in-place index; the column-axis counterpart of `filter` (see [select](implementation/select.md)) |
|
||||||
| `estimate` | Estimate approximate-index parameters (z, evidence bits, FP rates) before indexing |
|
| `estimate` | Estimate approximate-index parameters (z, evidence bits, FP rates) before indexing |
|
||||||
| `reindex` | Convert an index's evidence in-place: exact ↔ approx |
|
| `convert` | Convert an index's evidence representation (exact / approximate / hybrid), in place |
|
||||||
| `utils` | Miscellaneous index utilities: `--new-label NEW=OLD` renames a genome label; `--upgrade-index` adds missing `layer_meta.json` to old indexes |
|
| `utils` | Miscellaneous index utilities: `--new-label NEW=OLD` renames a genome label; `--upgrade-index` adds missing `layer_meta.json` to old indexes |
|
||||||
| `pack` | Pack per-column matrix files into single-file format to reduce query I/O |
|
| `pack` | Pack per-column matrix files into single-file format to reduce query I/O |
|
||||||
|
|
||||||
|
|||||||
@@ -280,7 +280,7 @@ impl KmerIndex {
|
|||||||
/// on-disk formats (`PersistentSparseBitMatrix` for presence,
|
/// on-disk formats (`PersistentSparseBitMatrix` for presence,
|
||||||
/// `PersistentSparseCompactIntMatrix` for counts) — smaller and faster
|
/// `PersistentSparseCompactIntMatrix` for counts) — smaller and faster
|
||||||
/// for single-row access on real, sparse data; column-oriented access
|
/// for single-row access on real, sparse data; column-oriented access
|
||||||
/// (`--metric` distance matrices) is much slower on the sparse format.
|
/// (`phylo --distance` matrices) is much slower on the sparse format.
|
||||||
///
|
///
|
||||||
/// Public — and not moved out of this crate, despite covering the same
|
/// Public — and not moved out of this crate, despite covering the same
|
||||||
/// "maintenance operation on an already-built index" territory as
|
/// "maintenance operation on an already-built index" territory as
|
||||||
|
|||||||
@@ -19,7 +19,7 @@ pub struct PackArgs {
|
|||||||
|
|
||||||
/// Pack presence and count matrices into the dense on-disk format instead
|
/// Pack presence and count matrices into the dense on-disk format instead
|
||||||
/// of the default sparse, deduplicated one. Dense is faster for
|
/// of the default sparse, deduplicated one. Dense is faster for
|
||||||
/// column-oriented access (`--metric` distance matrices); sparse is
|
/// column-oriented access (`phylo --distance` matrices); sparse is
|
||||||
/// smaller and faster for single-row access on real, sparse data.
|
/// smaller and faster for single-row access on real, sparse data.
|
||||||
#[arg(long, default_value_t = false)]
|
#[arg(long, default_value_t = false)]
|
||||||
pub dense: bool,
|
pub dense: bool,
|
||||||
|
|||||||
@@ -40,7 +40,7 @@ Option dependencies
|
|||||||
|
|
||||||
--fasta, --vcf imply --pseudo-alignment
|
--fasta, --vcf imply --pseudo-alignment
|
||||||
--tnt, --phyg, --iqtree imply --sankoff
|
--tnt, --phyg, --iqtree imply --sankoff
|
||||||
--nj, --upgma, --shared-kmers use the Jaccard distance when --distance
|
--nj, --upgma use the Jaccard distance when --distance
|
||||||
is not given
|
is not given
|
||||||
--pseudo-alignment, --sankoff require --n-sites
|
--pseudo-alignment, --sankoff require --n-sites
|
||||||
--session-force requires --session";
|
--session-force requires --session";
|
||||||
|
|||||||
@@ -1,5 +1,6 @@
|
|||||||
mod alignment_out;
|
mod alignment_out;
|
||||||
mod args;
|
mod args;
|
||||||
|
mod shared;
|
||||||
mod values;
|
mod values;
|
||||||
mod iqtree;
|
mod iqtree;
|
||||||
mod phyg;
|
mod phyg;
|
||||||
@@ -22,6 +23,7 @@ use obisys::{Reporter, Stage};
|
|||||||
use tracing::info;
|
use tracing::info;
|
||||||
|
|
||||||
use alignment_out::write_alignment_outputs;
|
use alignment_out::write_alignment_outputs;
|
||||||
|
use shared::write_shared_kmers;
|
||||||
use values::{DistanceArg, NSitesArg, distance_to_compute};
|
use values::{DistanceArg, NSitesArg, distance_to_compute};
|
||||||
use iqtree::write_iqtree;
|
use iqtree::write_iqtree;
|
||||||
use phyg::write_sankoff_phyg;
|
use phyg::write_sankoff_phyg;
|
||||||
@@ -286,7 +288,7 @@ pub fn run(args: PhyloArgs) {
|
|||||||
// different sample per flag — see `obikphylo::siblings::LayerReducer`'s
|
// different sample per flag — see `obikphylo::siblings::LayerReducer`'s
|
||||||
// own module docs).
|
// own module docs).
|
||||||
let sankoff_requested = args.costs.sankoff || args.costs.tnt || args.costs.phyg || args.costs.iqtree;
|
let sankoff_requested = args.costs.sankoff || args.costs.tnt || args.costs.phyg || args.costs.iqtree;
|
||||||
let distance = distance_to_compute(args.dist.distance, args.dist.nj, args.dist.upgma, args.dist.shared_kmers);
|
let distance = distance_to_compute(args.dist.distance, args.dist.nj, args.dist.upgma);
|
||||||
let snp_kind = distance.and_then(DistanceArg::as_snp);
|
let snp_kind = distance.and_then(DistanceArg::as_snp);
|
||||||
let need_alignment = args.alignment_output() || sankoff_requested;
|
let need_alignment = args.alignment_output() || sankoff_requested;
|
||||||
let need_pairwise = sankoff_requested || snp_kind.is_some();
|
let need_pairwise = sankoff_requested || snp_kind.is_some();
|
||||||
@@ -424,11 +426,22 @@ pub fn run(args: PhyloArgs) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// ── Distance computation: classic whole-index metric vs. `snp-*` ───────────
|
// ── Distance computation: classic whole-index metric vs. `snp-*` ───────────
|
||||||
// Nothing below (matrix, shared-kmer matrix, NJ/UPGMA trees) is wanted
|
// Nothing below (distance matrix, NJ/UPGMA trees) is wanted unless a
|
||||||
// unless a distance was asked for (`--distance`) or implied
|
// distance was asked for (`--distance`) or implied (`--nj`/`--upgma`): stop
|
||||||
// (`--nj`/`--upgma`/`--shared-kmers`): stop here rather than compute and
|
// here rather than compute and write a matrix nobody requested.
|
||||||
// write a matrix nobody requested.
|
// `--shared-kmers` alone only asks for its own matrix, not for a distance.
|
||||||
let Some(distance) = distance else {
|
let Some(distance) = distance else {
|
||||||
|
if args.dist.shared_kmers {
|
||||||
|
info!("computing shared k-mer counts for {n} genome(s)");
|
||||||
|
let t = Stage::start("shared_kmers");
|
||||||
|
let shared = cache.shared_kmers(args.dist.presence_threshold).unwrap_or_else(|e| {
|
||||||
|
eprintln!("error computing shared k-mer counts: {e}");
|
||||||
|
std::process::exit(1);
|
||||||
|
});
|
||||||
|
rep.push(t.stop());
|
||||||
|
let kept: Vec<usize> = (0..n).filter(|&i| !exclude_mask[i]).collect();
|
||||||
|
write_shared_kmers(&shared, &labels, &kept, &args.output);
|
||||||
|
}
|
||||||
rep.print();
|
rep.print();
|
||||||
return;
|
return;
|
||||||
};
|
};
|
||||||
@@ -437,7 +450,7 @@ pub fn run(args: PhyloArgs) {
|
|||||||
let (matrix, shared_kmers) = match distance.as_classic() {
|
let (matrix, shared_kmers) = match distance.as_classic() {
|
||||||
Some(metric) => {
|
Some(metric) => {
|
||||||
info!("computing {metric:?} distances for {n} genome(s)");
|
info!("computing {metric:?} distances for {n} genome(s)");
|
||||||
let need_shared = args.dist.shared_kmers || args.dist.nj || args.dist.upgma;
|
let need_shared = args.dist.shared_kmers;
|
||||||
let t = Stage::start("distance");
|
let t = Stage::start("distance");
|
||||||
let result = cache
|
let result = cache
|
||||||
.distance(metric, need_shared, args.dist.presence_threshold)
|
.distance(metric, need_shared, args.dist.presence_threshold)
|
||||||
@@ -521,25 +534,8 @@ pub fn run(args: PhyloArgs) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// ── Shared-kmer matrix → CSV ──────────────────────────────────────────────
|
// ── Shared-kmer matrix → CSV ──────────────────────────────────────────────
|
||||||
if args.dist.shared_kmers {
|
if let Some(shared) = shared_kmers.as_ref().filter(|_| args.dist.shared_kmers) {
|
||||||
if let Some(shared) = &shared_kmers {
|
write_shared_kmers(shared, &labels, &kept, &args.output);
|
||||||
let path = args.output.as_ref()
|
|
||||||
.map(|p| format!("{}_shared.csv", p.display()))
|
|
||||||
.unwrap_or_else(|| "shared.csv".into());
|
|
||||||
let mut f = BufWriter::new(std::fs::File::create(&path).unwrap_or_else(|e| {
|
|
||||||
eprintln!("error creating {path}: {e}");
|
|
||||||
std::process::exit(1);
|
|
||||||
}));
|
|
||||||
write!(f, "genome").unwrap();
|
|
||||||
for &j in &kept { write!(f, ",{}", labels[j]).unwrap(); }
|
|
||||||
writeln!(f).unwrap();
|
|
||||||
for &i in &kept {
|
|
||||||
write!(f, "{}", labels[i]).unwrap();
|
|
||||||
for &j in &kept { write!(f, ",{}", shared[[i, j]]).unwrap(); }
|
|
||||||
writeln!(f).unwrap();
|
|
||||||
}
|
|
||||||
info!("shared-kmer matrix → {path}");
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// ── NJ tree ────────────────────────────────────────────────────────────────
|
// ── NJ tree ────────────────────────────────────────────────────────────────
|
||||||
|
|||||||
@@ -0,0 +1,39 @@
|
|||||||
|
//! `--shared-kmers`: the genome-by-genome matrix of shared k-mer counts.
|
||||||
|
|
||||||
|
use std::fs::File;
|
||||||
|
use std::io::{BufWriter, Write};
|
||||||
|
use std::path::PathBuf;
|
||||||
|
|
||||||
|
use ndarray::Array2;
|
||||||
|
use tracing::info;
|
||||||
|
|
||||||
|
/// Write `shared` (rows and columns of the genomes in `kept` only) as CSV to
|
||||||
|
/// `PREFIX_shared.csv`, or `shared.csv` without a prefix.
|
||||||
|
pub(super) fn write_shared_kmers(
|
||||||
|
shared: &Array2<u64>,
|
||||||
|
labels: &[String],
|
||||||
|
kept: &[usize],
|
||||||
|
output: &Option<PathBuf>,
|
||||||
|
) {
|
||||||
|
let path = output
|
||||||
|
.as_ref()
|
||||||
|
.map(|p| format!("{}_shared.csv", p.display()))
|
||||||
|
.unwrap_or_else(|| "shared.csv".into());
|
||||||
|
let mut f = BufWriter::new(File::create(&path).unwrap_or_else(|e| {
|
||||||
|
eprintln!("error creating {path}: {e}");
|
||||||
|
std::process::exit(1);
|
||||||
|
}));
|
||||||
|
write!(f, "genome").unwrap();
|
||||||
|
for &j in kept {
|
||||||
|
write!(f, ",{}", labels[j]).unwrap();
|
||||||
|
}
|
||||||
|
writeln!(f).unwrap();
|
||||||
|
for &i in kept {
|
||||||
|
write!(f, "{}", labels[i]).unwrap();
|
||||||
|
for &j in kept {
|
||||||
|
write!(f, ",{}", shared[[i, j]]).unwrap();
|
||||||
|
}
|
||||||
|
writeln!(f).unwrap();
|
||||||
|
}
|
||||||
|
info!("shared-kmer matrix → {path}");
|
||||||
|
}
|
||||||
@@ -99,16 +99,12 @@ pub enum DistanceArg {
|
|||||||
}
|
}
|
||||||
|
|
||||||
/// The distance matrix this invocation must compute, if any: the one asked for
|
/// The distance matrix this invocation must compute, if any: the one asked for
|
||||||
/// with `--distance`, else `jaccard` when `--nj`, `--upgma` or
|
/// with `--distance`, else `jaccard` when `--nj` or `--upgma` needs a matrix to
|
||||||
/// `--shared-kmers` needs a matrix to work from, else none — a matrix is never
|
/// work from, else none — a matrix is never computed (nor written) just
|
||||||
/// computed (nor written) just because nothing said otherwise.
|
/// because nothing said otherwise. `--shared-kmers` asks for its own matrix,
|
||||||
pub fn distance_to_compute(
|
/// not for a distance.
|
||||||
distance: Option<DistanceArg>,
|
pub fn distance_to_compute(distance: Option<DistanceArg>, nj: bool, upgma: bool) -> Option<DistanceArg> {
|
||||||
nj: bool,
|
distance.or_else(|| (nj || upgma).then_some(DistanceArg::Jaccard))
|
||||||
upgma: bool,
|
|
||||||
shared_kmers: bool,
|
|
||||||
) -> Option<DistanceArg> {
|
|
||||||
distance.or_else(|| (nj || upgma || shared_kmers).then_some(DistanceArg::Jaccard))
|
|
||||||
}
|
}
|
||||||
|
|
||||||
#[cfg(test)]
|
#[cfg(test)]
|
||||||
@@ -117,27 +113,24 @@ mod distance_tests {
|
|||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
fn nothing_asked_nothing_computed() {
|
fn nothing_asked_nothing_computed() {
|
||||||
assert!(distance_to_compute(None, false, false, false).is_none());
|
assert!(distance_to_compute(None, false, false).is_none());
|
||||||
}
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
fn tree_and_shared_kmer_outputs_imply_jaccard() {
|
fn tree_outputs_imply_jaccard() {
|
||||||
for (nj, upgma, shared) in [(true, false, false), (false, true, false), (false, false, true)] {
|
for (nj, upgma) in [(true, false), (false, true)] {
|
||||||
assert!(matches!(
|
assert!(matches!(distance_to_compute(None, nj, upgma), Some(DistanceArg::Jaccard)));
|
||||||
distance_to_compute(None, nj, upgma, shared),
|
|
||||||
Some(DistanceArg::Jaccard)
|
|
||||||
));
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
fn an_explicit_distance_wins() {
|
fn an_explicit_distance_wins() {
|
||||||
assert!(matches!(
|
assert!(matches!(
|
||||||
distance_to_compute(Some(DistanceArg::Mash), true, true, true),
|
distance_to_compute(Some(DistanceArg::Mash), true, true),
|
||||||
Some(DistanceArg::Mash)
|
Some(DistanceArg::Mash)
|
||||||
));
|
));
|
||||||
assert!(matches!(
|
assert!(matches!(
|
||||||
distance_to_compute(Some(DistanceArg::SnpJc), false, false, false),
|
distance_to_compute(Some(DistanceArg::SnpJc), false, false),
|
||||||
Some(DistanceArg::SnpJc)
|
Some(DistanceArg::SnpJc)
|
||||||
));
|
));
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -51,20 +51,6 @@ pub struct DistanceOutput {
|
|||||||
pub shared_kmers: Option<Array2<u64>>,
|
pub shared_kmers: Option<Array2<u64>>,
|
||||||
}
|
}
|
||||||
|
|
||||||
impl DistanceMetric {
|
|
||||||
pub fn requires_counts(self) -> bool {
|
|
||||||
matches!(
|
|
||||||
self,
|
|
||||||
DistanceMetric::BrayCurtis
|
|
||||||
| DistanceMetric::RelfreqBrayCurtis
|
|
||||||
| DistanceMetric::Euclidean
|
|
||||||
| DistanceMetric::RelfreqEuclidean
|
|
||||||
| DistanceMetric::Hellinger
|
|
||||||
| DistanceMetric::HellingerEuclidean
|
|
||||||
)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// ── Aggregators — bounded parallel reduction of every cached layer's own
|
// ── Aggregators — bounded parallel reduction of every cached layer's own
|
||||||
// partial (of the wanted content kind) into one global partial, then handed
|
// partial (of the wanted content kind) into one global partial, then handed
|
||||||
// off to `CountPartials`/`BitPartials`'s own provided finalisation methods.
|
// off to `CountPartials`/`BitPartials`'s own provided finalisation methods.
|
||||||
@@ -188,10 +174,33 @@ impl BitPartials for AggregatedBit<'_> {
|
|||||||
/// extension trait in this codebase.
|
/// extension trait in this codebase.
|
||||||
pub trait Metrics {
|
pub trait Metrics {
|
||||||
fn distance(&self, metric: DistanceMetric, shared_kmers: bool, presence_threshold: u32) -> OKIResult<DistanceOutput>;
|
fn distance(&self, metric: DistanceMetric, shared_kmers: bool, presence_threshold: u32) -> OKIResult<DistanceOutput>;
|
||||||
|
|
||||||
|
/// Genome-by-genome matrix of the number of k-mers shared by each pair of
|
||||||
|
/// genomes — on a count index a k-mer is present when its count reaches
|
||||||
|
/// `presence_threshold`. Independent of any distance: nothing else is
|
||||||
|
/// computed.
|
||||||
|
fn shared_kmers(&self, presence_threshold: u32) -> OKIResult<Array2<u64>>;
|
||||||
}
|
}
|
||||||
|
|
||||||
impl Metrics for IndexCache {
|
impl Metrics for IndexCache {
|
||||||
|
fn shared_kmers(&self, presence_threshold: u32) -> OKIResult<Array2<u64>> {
|
||||||
|
let n_genomes = self.meta().genomes().len();
|
||||||
|
if n_genomes < 2 {
|
||||||
|
return Err(OKIError::InvalidInput(
|
||||||
|
"shared k-mer counts require at least 2 genomes in the index".into(),
|
||||||
|
));
|
||||||
|
}
|
||||||
|
let (inter, _union) = if self.meta().config().with_counts {
|
||||||
|
AggregatedCount { cache: self, n_genomes }.partial_threshold_jaccard(presence_threshold)
|
||||||
|
} else {
|
||||||
|
AggregatedBit { cache: self, n_genomes }.partial_jaccard()
|
||||||
|
};
|
||||||
|
Ok(inter)
|
||||||
|
}
|
||||||
|
|
||||||
fn distance(&self, metric: DistanceMetric, shared_kmers: bool, presence_threshold: u32) -> OKIResult<DistanceOutput> {
|
fn distance(&self, metric: DistanceMetric, shared_kmers: bool, presence_threshold: u32) -> OKIResult<DistanceOutput> {
|
||||||
|
use DistanceMetric::*;
|
||||||
|
|
||||||
let n_genomes = self.meta().genomes().len();
|
let n_genomes = self.meta().genomes().len();
|
||||||
if n_genomes < 2 {
|
if n_genomes < 2 {
|
||||||
return Err(OKIError::InvalidInput(
|
return Err(OKIError::InvalidInput(
|
||||||
@@ -199,64 +208,44 @@ impl Metrics for IndexCache {
|
|||||||
));
|
));
|
||||||
}
|
}
|
||||||
|
|
||||||
let use_counts = self.meta().config().with_counts;
|
|
||||||
if metric.requires_counts() && !use_counts {
|
|
||||||
return Err(OKIError::InvalidInput(format!(
|
|
||||||
"{metric:?} requires a count index (with_counts = true)"
|
|
||||||
)));
|
|
||||||
}
|
|
||||||
|
|
||||||
let kmer_size = self.meta().config().kmer_size;
|
let kmer_size = self.meta().config().kmer_size;
|
||||||
|
let use_counts = self.meta().config().with_counts;
|
||||||
|
let count = AggregatedCount { cache: self, n_genomes };
|
||||||
|
let bit = AggregatedBit { cache: self, n_genomes };
|
||||||
|
|
||||||
if use_counts {
|
// One construction decides both what the index can serve and how:
|
||||||
let agg = AggregatedCount { cache: self, n_genomes };
|
// the six count-based distances need a count index, Hamming needs a
|
||||||
|
// presence/absence one, Jaccard and Mash work on either.
|
||||||
let matrix = match metric {
|
let matrix = match (use_counts, metric) {
|
||||||
DistanceMetric::BrayCurtis => agg.bray_dist_matrix(),
|
(true, BrayCurtis) => count.bray_dist_matrix(),
|
||||||
DistanceMetric::RelfreqBrayCurtis => agg.relfreq_bray_dist_matrix(),
|
(true, RelfreqBrayCurtis) => count.relfreq_bray_dist_matrix(),
|
||||||
DistanceMetric::Euclidean => agg.euclidean_dist_matrix(),
|
(true, Euclidean) => count.euclidean_dist_matrix(),
|
||||||
DistanceMetric::RelfreqEuclidean => agg.relfreq_euclidean_dist_matrix(),
|
(true, RelfreqEuclidean) => count.relfreq_euclidean_dist_matrix(),
|
||||||
DistanceMetric::Hellinger => agg.hellinger_dist_matrix(),
|
(true, Hellinger) => count.hellinger_dist_matrix(),
|
||||||
DistanceMetric::HellingerEuclidean => agg.hellinger_euclidean_dist_matrix(),
|
(true, HellingerEuclidean) => count.hellinger_euclidean_dist_matrix(),
|
||||||
DistanceMetric::Jaccard => agg.threshold_jaccard_dist_matrix(presence_threshold),
|
(true, Jaccard) => count.threshold_jaccard_dist_matrix(presence_threshold),
|
||||||
DistanceMetric::Mash => agg.threshold_mash_dist_matrix(kmer_size, presence_threshold),
|
(true, Mash) => count.threshold_mash_dist_matrix(kmer_size, presence_threshold),
|
||||||
DistanceMetric::Hamming => {
|
(true, Hamming) => {
|
||||||
return Err(OKIError::InvalidInput(
|
return Err(OKIError::InvalidInput(
|
||||||
"Hamming is only available for presence/absence indexes".into(),
|
"Hamming is only available for presence/absence indexes".into(),
|
||||||
));
|
));
|
||||||
}
|
}
|
||||||
};
|
(false, Jaccard) => bit.jaccard_dist_matrix(),
|
||||||
|
(false, Mash) => bit.mash_dist_matrix(kmer_size),
|
||||||
let shared = if shared_kmers {
|
(false, Hamming) => bit.hamming_dist_matrix().mapv(|v| v as f64),
|
||||||
let (inter, _) = agg.partial_threshold_jaccard(presence_threshold);
|
(
|
||||||
Some(inter)
|
false,
|
||||||
} else {
|
BrayCurtis | RelfreqBrayCurtis | Euclidean | RelfreqEuclidean | Hellinger | HellingerEuclidean,
|
||||||
None
|
) => {
|
||||||
};
|
|
||||||
|
|
||||||
Ok(DistanceOutput { matrix, shared_kmers: shared })
|
|
||||||
} else {
|
|
||||||
let agg = AggregatedBit { cache: self, n_genomes };
|
|
||||||
|
|
||||||
let matrix = match metric {
|
|
||||||
DistanceMetric::Jaccard => agg.jaccard_dist_matrix(),
|
|
||||||
DistanceMetric::Mash => agg.mash_dist_matrix(kmer_size),
|
|
||||||
DistanceMetric::Hamming => agg.hamming_dist_matrix().mapv(|v| v as f64),
|
|
||||||
other => {
|
|
||||||
return Err(OKIError::InvalidInput(format!(
|
return Err(OKIError::InvalidInput(format!(
|
||||||
"{other:?} requires a count index; use --metric jaccard or --metric hamming"
|
"{metric:?} requires a count index (with_counts = true); \
|
||||||
|
on an index without counts use --distance jaccard, mash or hamming"
|
||||||
)));
|
)));
|
||||||
}
|
}
|
||||||
};
|
};
|
||||||
|
|
||||||
let shared = if shared_kmers {
|
let shared = shared_kmers.then(|| self.shared_kmers(presence_threshold)).transpose()?;
|
||||||
let (inter, _) = agg.partial_jaccard();
|
|
||||||
Some(inter)
|
|
||||||
} else {
|
|
||||||
None
|
|
||||||
};
|
|
||||||
|
|
||||||
Ok(DistanceOutput { matrix, shared_kmers: shared })
|
Ok(DistanceOutput { matrix, shared_kmers: shared })
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
|
||||||
Reference in new issue
Block a user