feat: add benchmark pipeline, expose APIs, and enforce strict paths

Introduces a Make-based orchestration for simulating, indexing, merging, filtering, and verifying k-mer counts and presence. Exposes internal builder and iterator APIs publicly, enforces mandatory leading slashes for predicate patterns, registers the `obitaxonomy` crate, and updates tooling configurations alongside documentation.
2026-06-19 09:55:41 +02:00
parent 280ca1f5a3
commit c694e1f2b0
42 changed files with 2585 additions and 84 deletions
@@ -0,0 +1,144 @@
+# 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)
+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)
+
+.NOTPARALLEL:
+
+.PHONY: all simulate reference \
+        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
+
+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
+
+# ── dependency file ───────────────────────────────────────────────────────────
+
+deps.mk: $(GENOMES)
+	$(VENV_PY) make_deps.py $^ > $@
+
+# ── simulation ────────────────────────────────────────────────────────────────
+# Prerequisites (genome → reads) are in deps.mk; $< is the genome file.
+
+$(SIMULATED_READS):
+	bash simulate_one.sh $< $(dir $@)
+
+simulate: $(SIMULATED_READS)
+
+# ── reference kmer sets ───────────────────────────────────────────────────────
+# Prerequisites (reads → npz) are in deps.mk.
+
+reference_index/%.npz:
+	bash build_reference.sh $*
+
+reference: $(REF_NPZS)
+
+# ── 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