Eric Coissac
54e4600120
Introduces a `batch_int_group_stats` API for computing presence counts, sums, minimums, and maximums across sparse and dense matrix representations. The selection layer now utilizes this batched approach to optimize aggregation semantics for boolean and numeric operations. Additionally, reorganizes the benchmarking infrastructure to support querying across presence and count index variants in both dense and sparse formats, including new packing scripts and updated statistics aggregation.
321 lines
14 KiB
Makefile
321 lines
14 KiB
Makefile
# Requires GNU Make >= 4.3 (grouped targets &:) — use gmake on macOS
|
|
BINARY := ../src/target/release/obikmer
|
|
VENV_PY := ../.venv/bin/python3
|
|
|
|
GENOMES := $(wildcard genomes/*.fna.gz)
|
|
|
|
# SPECIMENS, SPECIES, and the full dependency graph are generated by
|
|
# make_deps.py from the genome FASTA headers — like .d files in C.
|
|
# Make rebuilds deps.mk whenever genomes/ changes and restarts.
|
|
-include deps.mk
|
|
|
|
REF_NPZS := $(SPECIMENS:%=reference_index/%.npz)
|
|
REF_DIST_CSVS := $(addprefix reference_dist/, \
|
|
shared_kmers.csv hamming_dist.csv jaccard_dist.csv \
|
|
bray_curtis_dist.csv relfreq_bray_curtis_dist.csv \
|
|
euclidean_dist.csv relfreq_euclidean_dist.csv \
|
|
hellinger_dist.csv hellinger_euclidean_dist.csv)
|
|
OBIKMER_PRESENCE_DIST := $(addprefix obikmer_dist/presence/, \
|
|
jaccard_dist.csv jaccard_shared.csv jaccard_nj.nwk \
|
|
hamming_dist.csv hamming_nj.nwk)
|
|
OBIKMER_COUNT_DIST := $(addprefix obikmer_dist/count/, \
|
|
jaccard_dist.csv jaccard_shared.csv jaccard_nj.nwk \
|
|
bray_curtis_dist.csv bray_curtis_nj.nwk \
|
|
relfreq_bray_curtis_dist.csv relfreq_bray_curtis_nj.nwk \
|
|
euclidean_dist.csv euclidean_nj.nwk \
|
|
relfreq_euclidean_dist.csv relfreq_euclidean_nj.nwk \
|
|
hellinger_dist.csv hellinger_nj.nwk \
|
|
hellinger_euclidean_dist.csv hellinger_euclidean_nj.nwk)
|
|
DIST_COMPARISON := stats/dist_comparison/summary.csv
|
|
PRESENCE_DONE := $(SPECIMENS:%=specimen_index_presence/%/index.done)
|
|
PRESENCE_STATS := $(SPECIMENS:%=stats/indexing_presence/%.stats)
|
|
COUNT_DONE := $(SPECIMENS:%=specimen_index_count/%/index.done)
|
|
COUNT_STATS := $(SPECIMENS:%=stats/indexing_count/%.stats)
|
|
VERIFY_PRESENCE_STATS := $(SPECIMENS:%=stats/verify_presence/%.stats)
|
|
VERIFY_COUNT_STATS := $(SPECIMENS:%=stats/verify_count/%.stats)
|
|
SPECIFIC_PRESENCE_DONE := $(SPECIES:%=specific_index_presence/%/index.done)
|
|
SPECIFIC_PRESENCE_STATS := $(SPECIES:%=stats/specific_kmer_presence/%.stats)
|
|
SPECIFIC_COUNT_DONE := $(SPECIES:%=specific_index_count/%/index.done)
|
|
SPECIFIC_COUNT_STATS := $(SPECIES:%=stats/specific_kmer_count/%.stats)
|
|
SIMULATED_READS := $(foreach s,$(SPECIMENS),simulated_data/$(subst --,/,$s)/reads_R1.fastq.gz)
|
|
QUERY_READS := $(foreach s,$(QUERY_SPECIMENS),query_data/$(subst --,/,$s)/reads_R1.fastq.gz)
|
|
QUERY_PRESENCE_DENSE_DONE := $(QUERY_SPECIMENS:%=query_presence_dense/%.fasta.gz)
|
|
QUERY_PRESENCE_DENSE_STATS := $(QUERY_SPECIMENS:%=stats/query_presence_dense/%.stats)
|
|
QUERY_PRESENCE_SPARSE_DONE := $(QUERY_SPECIMENS:%=query_presence_sparse/%.fasta.gz)
|
|
QUERY_PRESENCE_SPARSE_STATS := $(QUERY_SPECIMENS:%=stats/query_presence_sparse/%.stats)
|
|
QUERY_COUNT_DENSE_DONE := $(QUERY_SPECIMENS:%=query_count_dense/%.fasta.gz)
|
|
QUERY_COUNT_DENSE_STATS := $(QUERY_SPECIMENS:%=stats/query_count_dense/%.stats)
|
|
QUERY_COUNT_SPARSE_DONE := $(QUERY_SPECIMENS:%=query_count_sparse/%.fasta.gz)
|
|
QUERY_COUNT_SPARSE_STATS := $(QUERY_SPECIMENS:%=stats/query_count_sparse/%.stats)
|
|
VERIFY_QUERY_STATS := $(QUERY_SPECIMENS:%=stats/verify_query/%.stats)
|
|
|
|
.NOTPARALLEL:
|
|
|
|
.PHONY: all simulate reference reference_dist \
|
|
obikmer_dist obikmer_dist_presence obikmer_dist_count \
|
|
dist_comparison \
|
|
index_presence index_count \
|
|
aggregate_index_presence aggregate_index_count \
|
|
merge_presence merge_count \
|
|
verify_presence verify_count \
|
|
aggregate_verify_presence aggregate_verify_count \
|
|
verify_merge_presence verify_merge_count \
|
|
filter_presence filter_count \
|
|
aggregate_filter_presence aggregate_filter_count \
|
|
pack_dense_presence pack_dense_count simulate_query \
|
|
query_presence_dense query_presence_sparse \
|
|
query_count_dense query_count_sparse \
|
|
aggregate_query_presence_dense aggregate_query_presence_sparse \
|
|
aggregate_query_count_dense aggregate_query_count_sparse \
|
|
verify_query aggregate_verify_query
|
|
|
|
verify_merge_presence: stats/verify_merge_presence/current.csv
|
|
verify_merge_count: stats/verify_merge_count/current.csv
|
|
|
|
all: aggregate_verify_presence aggregate_verify_count \
|
|
verify_merge_presence verify_merge_count \
|
|
aggregate_filter_presence aggregate_filter_count \
|
|
dist_comparison \
|
|
aggregate_query_presence_dense aggregate_query_presence_sparse \
|
|
aggregate_query_count_dense aggregate_query_count_sparse \
|
|
aggregate_verify_query
|
|
|
|
# ── dependency file ───────────────────────────────────────────────────────────
|
|
|
|
deps.mk: $(GENOMES) make_deps.py
|
|
$(VENV_PY) make_deps.py $(GENOMES) > $@
|
|
|
|
# ── simulation ────────────────────────────────────────────────────────────────
|
|
# Prerequisites (genome → reads) are in deps.mk; $< is the genome file.
|
|
|
|
$(SIMULATED_READS):
|
|
bash simulate_one.sh $< $(dir $@)
|
|
|
|
simulate: $(SIMULATED_READS)
|
|
|
|
# ── query read simulation (fixed size, independent draw) ───────────────────────
|
|
# Prerequisites (genome → reads) are in deps.mk; $< is the genome file.
|
|
|
|
$(QUERY_READS):
|
|
bash simulate_query_one.sh $< $(dir $@)
|
|
|
|
simulate_query: $(QUERY_READS)
|
|
|
|
# ── reference kmer sets ───────────────────────────────────────────────────────
|
|
# Prerequisites (reads → npz) are in deps.mk.
|
|
|
|
reference_index/%.npz:
|
|
bash build_reference.sh $*
|
|
|
|
reference: $(REF_NPZS)
|
|
|
|
# ── reference distance matrices ───────────────────────────────────────────────
|
|
|
|
$(REF_DIST_CSVS) &: $(REF_NPZS) build_reference_dist.py
|
|
$(VENV_PY) build_reference_dist.py
|
|
|
|
reference_dist: $(REF_DIST_CSVS)
|
|
|
|
# ── obikmer phylo (presence index) ──────────────────────────────────────────
|
|
|
|
$(OBIKMER_PRESENCE_DIST) &: global_index_presence/index.done $(BINARY)
|
|
mkdir -p obikmer_dist/presence
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/presence/jaccard \
|
|
--distance jaccard --csv --shared-kmers --nj \
|
|
global_index_presence
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/presence/hamming \
|
|
--distance hamming --csv --nj \
|
|
global_index_presence
|
|
|
|
obikmer_dist_presence: $(OBIKMER_PRESENCE_DIST)
|
|
|
|
# ── obikmer phylo (count index) ─────────────────────────────────────────────
|
|
|
|
$(OBIKMER_COUNT_DIST) &: global_index_count/index.done $(BINARY)
|
|
mkdir -p obikmer_dist/count
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/count/jaccard \
|
|
--distance jaccard --csv --shared-kmers --nj \
|
|
global_index_count
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/count/bray_curtis \
|
|
--distance bray-curtis --csv --nj \
|
|
global_index_count
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/count/relfreq_bray_curtis \
|
|
--distance relfreq-bray-curtis --csv --nj \
|
|
global_index_count
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/count/euclidean \
|
|
--distance euclidean --csv --nj \
|
|
global_index_count
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/count/relfreq_euclidean \
|
|
--distance relfreq-euclidean --csv --nj \
|
|
global_index_count
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/count/hellinger \
|
|
--distance hellinger --csv --nj \
|
|
global_index_count
|
|
$(BINARY) phylo \
|
|
--output obikmer_dist/count/hellinger_euclidean \
|
|
--distance hellinger-euclidean --csv --nj \
|
|
global_index_count
|
|
|
|
obikmer_dist_count: $(OBIKMER_COUNT_DIST)
|
|
|
|
obikmer_dist: obikmer_dist_presence obikmer_dist_count
|
|
|
|
# ── distance comparison ───────────────────────────────────────────────────────
|
|
|
|
$(DIST_COMPARISON): $(REF_DIST_CSVS) $(OBIKMER_PRESENCE_DIST) $(OBIKMER_COUNT_DIST) compare_all_dist.py
|
|
$(VENV_PY) compare_all_dist.py --out $(DIST_COMPARISON)
|
|
|
|
dist_comparison: $(DIST_COMPARISON)
|
|
|
|
# ── per-specimen indexing ─────────────────────────────────────────────────────
|
|
# Prerequisites (reads → index.done + .stats) are in deps.mk.
|
|
|
|
specimen_index_presence/%/index.done \
|
|
stats/indexing_presence/%.stats &: $(BINARY)
|
|
bash index_one_presence.sh $*
|
|
|
|
specimen_index_count/%/index.done \
|
|
stats/indexing_count/%.stats &: $(BINARY)
|
|
bash index_one_count.sh $*
|
|
|
|
index_presence: $(PRESENCE_DONE)
|
|
index_count: $(COUNT_DONE)
|
|
|
|
# ── indexing stats aggregation ────────────────────────────────────────────────
|
|
|
|
aggregate_index_presence: $(PRESENCE_STATS)
|
|
bash aggregate_stats.sh indexing_presence
|
|
|
|
aggregate_index_count: $(COUNT_STATS)
|
|
bash aggregate_stats.sh indexing_count
|
|
|
|
# ── global merge ──────────────────────────────────────────────────────────────
|
|
|
|
global_index_presence/index.done: $(PRESENCE_DONE) $(BINARY)
|
|
bash merge_presence.sh
|
|
|
|
global_index_count/index.done: $(COUNT_DONE) $(BINARY)
|
|
bash merge_count.sh
|
|
|
|
merge_presence: global_index_presence/index.done
|
|
merge_count: global_index_count/index.done
|
|
|
|
# ── per-specimen verification ─────────────────────────────────────────────────
|
|
# Prerequisites (index.done + npz → .stats) are in deps.mk.
|
|
|
|
stats/verify_presence/%.stats:
|
|
bash verify_one_presence.sh $*
|
|
|
|
stats/verify_count/%.stats:
|
|
bash verify_one_count.sh $*
|
|
|
|
verify_presence: $(VERIFY_PRESENCE_STATS)
|
|
verify_count: $(VERIFY_COUNT_STATS)
|
|
|
|
# ── verification stats aggregation ───────────────────────────────────────────
|
|
|
|
aggregate_verify_presence: $(VERIFY_PRESENCE_STATS)
|
|
bash aggregate_stats.sh verify_presence
|
|
|
|
aggregate_verify_count: $(VERIFY_COUNT_STATS)
|
|
bash aggregate_stats.sh verify_count
|
|
|
|
# ── species-specific indexes ──────────────────────────────────────────────────
|
|
# Prerequisites (global index → specific index) are in deps.mk.
|
|
|
|
specific_index_presence/%/index.done \
|
|
stats/specific_kmer_presence/%.stats &: $(BINARY)
|
|
bash filter_one_presence.sh $*
|
|
|
|
specific_index_count/%/index.done \
|
|
stats/specific_kmer_count/%.stats &: $(BINARY)
|
|
bash filter_one_count.sh $*
|
|
|
|
filter_presence: $(SPECIFIC_PRESENCE_DONE)
|
|
filter_count: $(SPECIFIC_COUNT_DONE)
|
|
|
|
aggregate_filter_presence: $(SPECIFIC_PRESENCE_STATS)
|
|
bash aggregate_stats.sh specific_kmer_presence
|
|
|
|
aggregate_filter_count: $(SPECIFIC_COUNT_STATS)
|
|
bash aggregate_stats.sh specific_kmer_count
|
|
|
|
# ── merged index verification ─────────────────────────────────────────────────
|
|
|
|
stats/verify_merge_presence/current.csv: $(REF_NPZS) global_index_presence/index.done
|
|
bash verify_merge_presence.sh
|
|
|
|
stats/verify_merge_count/current.csv: $(REF_NPZS) global_index_count/index.done
|
|
bash verify_merge_count.sh
|
|
|
|
# ── dense variants (query benchmark) ────────────────────────────────────────────
|
|
# `merge` packs sparse by default (2026-08-28) — global_index_presence/
|
|
# global_index_count *are* the sparse variants already; the dense ones are
|
|
# built explicitly here, from a hard-link-based copy (see
|
|
# copy_index_hardlink.sh) rather than a full `cp -r`.
|
|
|
|
global_index_presence_dense/index.done: global_index_presence/index.done $(BINARY)
|
|
bash pack_dense.sh presence
|
|
|
|
# Rebuilt from the per-specimen count sources directly (via `merge --dense`),
|
|
# not repacked from global_index_count — see pack_dense.sh's own comment.
|
|
global_index_count_dense/index.done: $(COUNT_DONE) $(BINARY)
|
|
bash pack_dense.sh count
|
|
|
|
pack_dense_presence: global_index_presence_dense/index.done
|
|
pack_dense_count: global_index_count_dense/index.done
|
|
|
|
# ── query: dense vs sparse, presence and count ──────────────────────────────────
|
|
# Prerequisites (reads + index → output + .stats) are in deps.mk.
|
|
|
|
query_presence_dense/%.fasta.gz \
|
|
stats/query_presence_dense/%.stats &: $(BINARY) global_index_presence_dense/index.done
|
|
bash query_one.sh presence dense $*
|
|
|
|
query_presence_sparse/%.fasta.gz \
|
|
stats/query_presence_sparse/%.stats &: $(BINARY) global_index_presence/index.done
|
|
bash query_one.sh presence sparse $*
|
|
|
|
query_count_dense/%.fasta.gz \
|
|
stats/query_count_dense/%.stats &: $(BINARY) global_index_count_dense/index.done
|
|
bash query_one.sh count dense $*
|
|
|
|
query_count_sparse/%.fasta.gz \
|
|
stats/query_count_sparse/%.stats &: $(BINARY) global_index_count/index.done
|
|
bash query_one.sh count sparse $*
|
|
|
|
query_presence_dense: $(QUERY_PRESENCE_DENSE_DONE)
|
|
query_presence_sparse: $(QUERY_PRESENCE_SPARSE_DONE)
|
|
query_count_dense: $(QUERY_COUNT_DENSE_DONE)
|
|
query_count_sparse: $(QUERY_COUNT_SPARSE_DONE)
|
|
|
|
aggregate_query_presence_dense: $(QUERY_PRESENCE_DENSE_STATS)
|
|
bash aggregate_stats.sh query_presence_dense
|
|
|
|
aggregate_query_presence_sparse: $(QUERY_PRESENCE_SPARSE_STATS)
|
|
bash aggregate_stats.sh query_presence_sparse
|
|
|
|
aggregate_query_count_dense: $(QUERY_COUNT_DENSE_STATS)
|
|
bash aggregate_stats.sh query_count_dense
|
|
|
|
aggregate_query_count_sparse: $(QUERY_COUNT_SPARSE_STATS)
|
|
bash aggregate_stats.sh query_count_sparse
|
|
|
|
# ── query: dense/sparse regression ──────────────────────────────────────────────
|
|
|
|
stats/verify_query/%.stats:
|
|
bash verify_query_one.sh $*
|
|
|
|
verify_query: $(VERIFY_QUERY_STATS)
|
|
|
|
aggregate_verify_query: $(VERIFY_QUERY_STATS)
|
|
bash aggregate_stats.sh verify_query
|