Push zunrplorkwkt #70

Merged
coissac merged 93 commits from push-zunrplorkwkt into main 2026-08-28 23:15:38 +00:00
1057 changed files with 449 additions and 449 deletions
Showing only changes of commit 52f26809af - Show all commits
+1 -19
View File
@@ -30,25 +30,7 @@ data-stress
*.bin.idx
*.prsb
Betula_exilis--IGA-24-33
benchmark/genomes
benchmark/genomes_orig
benchmark/simulated_data
benchmark/specimen_index_presence
benchmark/global_index_count_dense
benchmark/global_index_presence
benchmark/global_index_presence_orig
benchmark/global_index_presence_sav
benchmark/global_index_presence_dense
benchmark/all_specific
benchmark/global_index_count
benchmark/specimen_index_count
benchmark/stats
benchmark/reference_index
benchmark/reference_dist
benchmark/obikmer_dist
benchmark/specific_index_count
benchmark/specific_index_presence
benchmark/query_data
benchmark/run/
TNT
phyg
biblio
+88 -83
View File
@@ -2,23 +2,27 @@
BINARY := ../src/target/release/obikmer
VENV_PY := ../.venv/bin/python3
GENOMES := $(wildcard genomes/*.fna.gz)
# All generated/downloaded artifacts live under RUN/ so the whole tree can be
# gitignored with a single entry (benchmark/run/) — see benchmark/README.md.
RUN := run
GENOMES := $(wildcard $(RUN)/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/, \
REF_NPZS := $(SPECIMENS:%=$(RUN)/reference_index/%.npz)
REF_DIST_CSVS := $(addprefix $(RUN)/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/, \
OBIKMER_PRESENCE_DIST := $(addprefix $(RUN)/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/, \
OBIKMER_COUNT_DIST := $(addprefix $(RUN)/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 \
@@ -26,28 +30,28 @@ OBIKMER_COUNT_DIST := $(addprefix obikmer_dist/count/, \
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)
DIST_COMPARISON := $(RUN)/stats/dist_comparison/summary.csv
PRESENCE_DONE := $(SPECIMENS:%=$(RUN)/specimen_index_presence/%/index.done)
PRESENCE_STATS := $(SPECIMENS:%=$(RUN)/stats/indexing_presence/%.stats)
COUNT_DONE := $(SPECIMENS:%=$(RUN)/specimen_index_count/%/index.done)
COUNT_STATS := $(SPECIMENS:%=$(RUN)/stats/indexing_count/%.stats)
VERIFY_PRESENCE_STATS := $(SPECIMENS:%=$(RUN)/stats/verify_presence/%.stats)
VERIFY_COUNT_STATS := $(SPECIMENS:%=$(RUN)/stats/verify_count/%.stats)
SPECIFIC_PRESENCE_DONE := $(SPECIES:%=$(RUN)/specific_index_presence/%/index.done)
SPECIFIC_PRESENCE_STATS := $(SPECIES:%=$(RUN)/stats/specific_kmer_presence/%.stats)
SPECIFIC_COUNT_DONE := $(SPECIES:%=$(RUN)/specific_index_count/%/index.done)
SPECIFIC_COUNT_STATS := $(SPECIES:%=$(RUN)/stats/specific_kmer_count/%.stats)
SIMULATED_READS := $(foreach s,$(SPECIMENS),$(RUN)/simulated_data/$(subst --,/,$s)/reads_R1.fastq.gz)
QUERY_READS := $(foreach s,$(QUERY_SPECIMENS),$(RUN)/query_data/$(subst --,/,$s)/reads_R1.fastq.gz)
QUERY_PRESENCE_DENSE_DONE := $(QUERY_SPECIMENS:%=$(RUN)/query_presence_dense/%.fasta.gz)
QUERY_PRESENCE_DENSE_STATS := $(QUERY_SPECIMENS:%=$(RUN)/stats/query_presence_dense/%.stats)
QUERY_PRESENCE_SPARSE_DONE := $(QUERY_SPECIMENS:%=$(RUN)/query_presence_sparse/%.fasta.gz)
QUERY_PRESENCE_SPARSE_STATS := $(QUERY_SPECIMENS:%=$(RUN)/stats/query_presence_sparse/%.stats)
QUERY_COUNT_DENSE_DONE := $(QUERY_SPECIMENS:%=$(RUN)/query_count_dense/%.fasta.gz)
QUERY_COUNT_DENSE_STATS := $(QUERY_SPECIMENS:%=$(RUN)/stats/query_count_dense/%.stats)
QUERY_COUNT_SPARSE_DONE := $(QUERY_SPECIMENS:%=$(RUN)/query_count_sparse/%.fasta.gz)
QUERY_COUNT_SPARSE_STATS := $(QUERY_SPECIMENS:%=$(RUN)/stats/query_count_sparse/%.stats)
VERIFY_QUERY_STATS := $(QUERY_SPECIMENS:%=$(RUN)/stats/verify_query/%.stats)
.NOTPARALLEL:
@@ -69,8 +73,8 @@ VERIFY_QUERY_STATS := $(QUERY_SPECIMENS:%=stats/verify_query/%.stats)
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
verify_merge_presence: $(RUN)/stats/verify_merge_presence/current.csv
verify_merge_count: $(RUN)/stats/verify_merge_count/current.csv
all: aggregate_verify_presence aggregate_verify_count \
verify_merge_presence verify_merge_count \
@@ -104,7 +108,7 @@ simulate_query: $(QUERY_READS)
# ── reference kmer sets ───────────────────────────────────────────────────────
# Prerequisites (reads → npz) are in deps.mk.
reference_index/%.npz:
$(RUN)/reference_index/%.npz:
bash build_reference.sh $*
reference: $(REF_NPZS)
@@ -112,57 +116,58 @@ reference: $(REF_NPZS)
# ── reference distance matrices ───────────────────────────────────────────────
$(REF_DIST_CSVS) &: $(REF_NPZS) build_reference_dist.py
$(VENV_PY) build_reference_dist.py
$(VENV_PY) build_reference_dist.py \
--ref-dir $(RUN)/reference_index --out-dir $(RUN)/reference_dist
reference_dist: $(REF_DIST_CSVS)
# ── obikmer phylo (presence index) ──────────────────────────────────────────
$(OBIKMER_PRESENCE_DIST) &: global_index_presence/index.done $(BINARY)
mkdir -p obikmer_dist/presence
$(OBIKMER_PRESENCE_DIST) &: $(RUN)/global_index_presence/index.done $(BINARY)
mkdir -p $(RUN)/obikmer_dist/presence
$(BINARY) phylo \
--output obikmer_dist/presence/jaccard \
--output $(RUN)/obikmer_dist/presence/jaccard \
--distance jaccard --csv --shared-kmers --nj \
global_index_presence
$(RUN)/global_index_presence
$(BINARY) phylo \
--output obikmer_dist/presence/hamming \
--output $(RUN)/obikmer_dist/presence/hamming \
--distance hamming --csv --nj \
global_index_presence
$(RUN)/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
$(OBIKMER_COUNT_DIST) &: $(RUN)/global_index_count/index.done $(BINARY)
mkdir -p $(RUN)/obikmer_dist/count
$(BINARY) phylo \
--output obikmer_dist/count/jaccard \
--output $(RUN)/obikmer_dist/count/jaccard \
--distance jaccard --csv --shared-kmers --nj \
global_index_count
$(RUN)/global_index_count
$(BINARY) phylo \
--output obikmer_dist/count/bray_curtis \
--output $(RUN)/obikmer_dist/count/bray_curtis \
--distance bray-curtis --csv --nj \
global_index_count
$(RUN)/global_index_count
$(BINARY) phylo \
--output obikmer_dist/count/relfreq_bray_curtis \
--output $(RUN)/obikmer_dist/count/relfreq_bray_curtis \
--distance relfreq-bray-curtis --csv --nj \
global_index_count
$(RUN)/global_index_count
$(BINARY) phylo \
--output obikmer_dist/count/euclidean \
--output $(RUN)/obikmer_dist/count/euclidean \
--distance euclidean --csv --nj \
global_index_count
$(RUN)/global_index_count
$(BINARY) phylo \
--output obikmer_dist/count/relfreq_euclidean \
--output $(RUN)/obikmer_dist/count/relfreq_euclidean \
--distance relfreq-euclidean --csv --nj \
global_index_count
$(RUN)/global_index_count
$(BINARY) phylo \
--output obikmer_dist/count/hellinger \
--output $(RUN)/obikmer_dist/count/hellinger \
--distance hellinger --csv --nj \
global_index_count
$(RUN)/global_index_count
$(BINARY) phylo \
--output obikmer_dist/count/hellinger_euclidean \
--output $(RUN)/obikmer_dist/count/hellinger_euclidean \
--distance hellinger-euclidean --csv --nj \
global_index_count
$(RUN)/global_index_count
obikmer_dist_count: $(OBIKMER_COUNT_DIST)
@@ -171,19 +176,19 @@ 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)
$(VENV_PY) compare_all_dist.py --run-dir $(RUN) --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)
$(RUN)/specimen_index_presence/%/index.done \
$(RUN)/stats/indexing_presence/%.stats &: $(BINARY)
bash index_one_presence.sh $*
specimen_index_count/%/index.done \
stats/indexing_count/%.stats &: $(BINARY)
$(RUN)/specimen_index_count/%/index.done \
$(RUN)/stats/indexing_count/%.stats &: $(BINARY)
bash index_one_count.sh $*
index_presence: $(PRESENCE_DONE)
@@ -199,22 +204,22 @@ aggregate_index_count: $(COUNT_STATS)
# ── global merge ──────────────────────────────────────────────────────────────
global_index_presence/index.done: $(PRESENCE_DONE) $(BINARY)
$(RUN)/global_index_presence/index.done: $(PRESENCE_DONE) $(BINARY)
bash merge_presence.sh
global_index_count/index.done: $(COUNT_DONE) $(BINARY)
$(RUN)/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
merge_presence: $(RUN)/global_index_presence/index.done
merge_count: $(RUN)/global_index_count/index.done
# ── per-specimen verification ─────────────────────────────────────────────────
# Prerequisites (index.done + npz → .stats) are in deps.mk.
stats/verify_presence/%.stats:
$(RUN)/stats/verify_presence/%.stats:
bash verify_one_presence.sh $*
stats/verify_count/%.stats:
$(RUN)/stats/verify_count/%.stats:
bash verify_one_count.sh $*
verify_presence: $(VERIFY_PRESENCE_STATS)
@@ -231,12 +236,12 @@ aggregate_verify_count: $(VERIFY_COUNT_STATS)
# ── species-specific indexes ──────────────────────────────────────────────────
# Prerequisites (global index → specific index) are in deps.mk.
specific_index_presence/%/index.done \
stats/specific_kmer_presence/%.stats &: $(BINARY)
$(RUN)/specific_index_presence/%/index.done \
$(RUN)/stats/specific_kmer_presence/%.stats &: $(BINARY)
bash filter_one_presence.sh $*
specific_index_count/%/index.done \
stats/specific_kmer_count/%.stats &: $(BINARY)
$(RUN)/specific_index_count/%/index.done \
$(RUN)/stats/specific_kmer_count/%.stats &: $(BINARY)
bash filter_one_count.sh $*
filter_presence: $(SPECIFIC_PRESENCE_DONE)
@@ -250,10 +255,10 @@ aggregate_filter_count: $(SPECIFIC_COUNT_STATS)
# ── merged index verification ─────────────────────────────────────────────────
stats/verify_merge_presence/current.csv: $(REF_NPZS) global_index_presence/index.done
$(RUN)/stats/verify_merge_presence/current.csv: $(REF_NPZS) $(RUN)/global_index_presence/index.done
bash verify_merge_presence.sh
stats/verify_merge_count/current.csv: $(REF_NPZS) global_index_count/index.done
$(RUN)/stats/verify_merge_count/current.csv: $(REF_NPZS) $(RUN)/global_index_count/index.done
bash verify_merge_count.sh
# ── dense variants (query benchmark) ────────────────────────────────────────────
@@ -262,34 +267,34 @@ stats/verify_merge_count/current.csv: $(REF_NPZS) global_index_count/index.done
# 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)
$(RUN)/global_index_presence_dense/index.done: $(RUN)/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)
$(RUN)/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
pack_dense_presence: $(RUN)/global_index_presence_dense/index.done
pack_dense_count: $(RUN)/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
$(RUN)/query_presence_dense/%.fasta.gz \
$(RUN)/stats/query_presence_dense/%.stats &: $(BINARY) $(RUN)/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
$(RUN)/query_presence_sparse/%.fasta.gz \
$(RUN)/stats/query_presence_sparse/%.stats &: $(BINARY) $(RUN)/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
$(RUN)/query_count_dense/%.fasta.gz \
$(RUN)/stats/query_count_dense/%.stats &: $(BINARY) $(RUN)/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
$(RUN)/query_count_sparse/%.fasta.gz \
$(RUN)/stats/query_count_sparse/%.stats &: $(BINARY) $(RUN)/global_index_count/index.done
bash query_one.sh count sparse $*
query_presence_dense: $(QUERY_PRESENCE_DENSE_DONE)
@@ -311,7 +316,7 @@ aggregate_query_count_sparse: $(QUERY_COUNT_SPARSE_STATS)
# ── query: dense/sparse regression ──────────────────────────────────────────────
stats/verify_query/%.stats:
$(RUN)/stats/verify_query/%.stats:
bash verify_query_one.sh $*
verify_query: $(VERIFY_QUERY_STATS)
+108 -77
View File
@@ -8,108 +8,124 @@ gmake simulate # simulation only
gmake reference # reference kmer sets only
```
All generated and downloaded artifacts live under `run/` (see
[Directory layout](#directory-layout)), so the whole tree is gitignored with
a single `benchmark/run/` entry.
## Pipeline overview
```mermaid
flowchart TD
GENOMES["genomes/*.fna.gz"]
GENOMES["run/genomes/*.fna.gz"]
BIN["obikmer binary"]
GENOMES --> simulate
simulate --> simdata[("simulated_data/")]
simulate --> simdata[("run/simulated_data/")]
simdata --> reference
reference --> refnpz[("reference_index/*.npz")]
reference --> refnpz[("run/reference_index/*.npz")]
subgraph presence ["Presence track"]
simdata --> index_presence
BIN --> index_presence
index_presence --> pres_done[("specimen_index_presence/")]
index_presence --> pres_istats[("stats/indexing_presence/")]
index_presence --> pres_done[("run/specimen_index_presence/")]
index_presence --> pres_istats[("run/stats/indexing_presence/")]
pres_istats --> aggregate_index_presence
pres_done --> merge_presence
BIN --> merge_presence
merge_presence --> gpres[("global_index_presence/")]
merge_presence --> gpres[("run/global_index_presence/")]
refnpz --> verify_presence
pres_done --> verify_presence
verify_presence --> vpres_stats[("stats/verify_presence/")]
verify_presence --> vpres_stats[("run/stats/verify_presence/")]
vpres_stats --> aggregate_verify_presence
gpres --> filter_presence
BIN --> filter_presence
filter_presence --> spec_pres[("specific_index_presence/")]
filter_presence --> spec_pres_stats[("stats/specific_kmer_presence/")]
filter_presence --> spec_pres[("run/specific_index_presence/")]
filter_presence --> spec_pres_stats[("run/stats/specific_kmer_presence/")]
spec_pres_stats --> aggregate_filter_presence
refnpz --> verify_merge_presence
gpres --> verify_merge_presence
verify_merge_presence --> vmp[("stats/verify_merge_presence/")]
verify_merge_presence --> vmp[("run/stats/verify_merge_presence/")]
end
subgraph count ["Count track"]
simdata --> index_count
BIN --> index_count
index_count --> count_done[("specimen_index_count/")]
index_count --> count_istats[("stats/indexing_count/")]
index_count --> count_done[("run/specimen_index_count/")]
index_count --> count_istats[("run/stats/indexing_count/")]
count_istats --> aggregate_index_count
count_done --> merge_count
BIN --> merge_count
merge_count --> gcount[("global_index_count/")]
merge_count --> gcount[("run/global_index_count/")]
refnpz --> verify_count
count_done --> verify_count
verify_count --> vcount_stats[("stats/verify_count/")]
verify_count --> vcount_stats[("run/stats/verify_count/")]
vcount_stats --> aggregate_verify_count
gcount --> filter_count
BIN --> filter_count
filter_count --> spec_count[("specific_index_count/")]
filter_count --> spec_count_stats[("stats/specific_kmer_count/")]
filter_count --> spec_count[("run/specific_index_count/")]
filter_count --> spec_count_stats[("run/stats/specific_kmer_count/")]
spec_count_stats --> aggregate_filter_count
refnpz --> verify_merge_count
gcount --> verify_merge_count
verify_merge_count --> vmc[("stats/verify_merge_count/")]
verify_merge_count --> vmc[("run/stats/verify_merge_count/")]
end
subgraph query ["Query track (2 specimens: E. coli + archaeon)"]
GENOMES --> simulate_query
simulate_query --> qdata[("query_data/")]
simulate_query --> qdata[("run/query_data/")]
gpres --> pack_sparse
BIN --> pack_sparse
pack_sparse --> gsparse[("global_index_presence_sparse/")]
gpres --> pack_dense_presence
BIN --> pack_dense_presence
pack_dense_presence --> gpresd[("run/global_index_presence_dense/")]
qdata --> query_dense
gpres --> query_dense
BIN --> query_dense
query_dense --> qd[("query_dense/")]
query_dense --> qd_stats[("stats/query_dense/")]
qd_stats --> aggregate_query_dense
count_done --> pack_dense_count
BIN --> pack_dense_count
pack_dense_count --> gcountd[("run/global_index_count_dense/")]
qdata --> query_sparse
gsparse --> query_sparse
BIN --> query_sparse
query_sparse --> qs[("query_sparse/")]
query_sparse --> qs_stats[("stats/query_sparse/")]
qs_stats --> aggregate_query_sparse
qdata --> query_presence_dense
gpresd --> query_presence_dense
query_presence_dense --> qpd[("run/query_presence_dense/")]
qpd --> aggregate_query_presence_dense
qd --> verify_query
qs --> verify_query
verify_query --> vq_stats[("stats/verify_query/")]
qdata --> query_presence_sparse
gpres --> query_presence_sparse
query_presence_sparse --> qps[("run/query_presence_sparse/")]
qps --> aggregate_query_presence_sparse
qdata --> query_count_dense
gcountd --> query_count_dense
query_count_dense --> qcd[("run/query_count_dense/")]
qcd --> aggregate_query_count_dense
qdata --> query_count_sparse
gcount --> query_count_sparse
query_count_sparse --> qcs[("run/query_count_sparse/")]
qcs --> aggregate_query_count_sparse
qpd --> verify_query
qps --> verify_query
verify_query --> vq_stats[("run/stats/verify_query/")]
vq_stats --> aggregate_verify_query
end
aggregate_verify_presence --> all
aggregate_verify_count --> all
vmp --> all
vmc --> all
aggregate_query_dense --> all
aggregate_query_sparse --> all
aggregate_verify_query --> all
aggregate_verify_presence --> all
aggregate_verify_count --> all
vmp --> all
vmc --> all
aggregate_query_presence_dense --> all
aggregate_query_presence_sparse --> all
aggregate_query_count_dense --> all
aggregate_query_count_sparse --> all
aggregate_verify_query --> all
all -. "$(MAKE) re-eval" .-> aggregate_filter_presence
all -. "$(MAKE) re-eval" .-> aggregate_filter_count
```
@@ -137,44 +153,59 @@ flowchart TD
| `verify_merge_presence` | `verify_merge_presence.sh` | Verify global presence index against all reference sets |
| `verify_merge_count` | `verify_merge_count.sh` | Verify global count index against all reference sets |
| `simulate_query` | `simulate_query_one.sh` | Simulate a fixed-size (100k pairs) read set per query specimen |
| `pack_sparse` | `pack_sparse.sh` | Build `global_index_presence_sparse/` from `global_index_presence/` |
| `query_dense` | `query_one.sh dense` | Query each query specimen's reads against the dense global index |
| `query_sparse` | `query_one.sh sparse` | Query each query specimen's reads against the sparse global index |
| `aggregate_query_dense` | `aggregate_stats.sh` | Aggregate dense query wall/RSS stats |
| `aggregate_query_sparse` | `aggregate_stats.sh` | Aggregate sparse query wall/RSS stats |
| `verify_query` | `verify_query_one.sh` | Diff dense vs sparse query output per specimen (regression check) |
| `pack_dense_presence` | `pack_dense.sh presence` | Build `global_index_presence_dense/` from `global_index_presence/` |
| `pack_dense_count` | `pack_dense.sh count` | Build `global_index_count_dense/` from the per-specimen count sources |
| `query_presence_dense` | `query_one.sh presence dense` | Query against the dense presence global index |
| `query_presence_sparse` | `query_one.sh presence sparse` | Query against the sparse (as-merged) presence global index |
| `query_count_dense` | `query_one.sh count dense` | Query against the dense count global index |
| `query_count_sparse` | `query_one.sh count sparse` | Query against the sparse (as-merged) count global index |
| `aggregate_query_presence_dense` | `aggregate_stats.sh` | Aggregate dense presence-query wall/RSS stats |
| `aggregate_query_presence_sparse` | `aggregate_stats.sh` | Aggregate sparse presence-query wall/RSS stats |
| `aggregate_query_count_dense` | `aggregate_stats.sh` | Aggregate dense count-query wall/RSS stats |
| `aggregate_query_count_sparse` | `aggregate_stats.sh` | Aggregate sparse count-query wall/RSS stats |
| `verify_query` | `verify_query_one.sh` | Diff dense vs sparse presence-query output per specimen (regression check) |
| `aggregate_verify_query` | `aggregate_stats.sh` | Aggregate dense/sparse query regression stats |
## Directory layout
```
benchmark/
── genomes/ # input reference genomes (.fna.gz)
├── simulated_data/ # generated by simulate
── <species>/<specimen>/
├── query_data/ # generated by simulate_query (2 specimens, fixed 100k pairs)
── <species>/<specimen>/
├── reference_index/ # reference kmer sets (.npz)
├── specimen_index_presence/ # per-specimen presence indexes
├── specimen_index_count/ # per-specimen count indexes
├── global_index_presence/ # merged global presence index (dense-packed)
├── global_index_presence_sparse/ # global presence index, sparse-packed (query benchmark)
├── global_index_count/ # merged global count index
├── specific_index_presence/ # species-specific presence indexes
├── specific_index_count/ # species-specific count indexes
├── query_dense/ # query output against global_index_presence
├── query_sparse/ # query output against global_index_presence_sparse
└── stats/ # all benchmark statistics
├── indexing_presence/
├── indexing_count/
├── verify_presence/
├── verify_count/
├── specific_kmer_presence/
── specific_kmer_count/
├── verify_merge_presence/
├── verify_merge_count/
├── pack_sparse/
├── query_dense/
├── query_sparse/
└── verify_query/
── run/ # everything generated/downloaded — gitignored as a whole
├── genomes/ # input reference genomes (.fna.gz), downloaded by downloads.sh
── simulated_data/ # generated by simulate
│ └── <species>/<specimen>/
── query_data/ # generated by simulate_query (2 specimens, fixed 100k pairs)
│ └── <species>/<specimen>/
├── reference_index/ # reference kmer sets (.npz)
├── reference_dist/ # reference pairwise distance matrices
├── obikmer_dist/ # obikmer phylo distance matrices (presence/, count/)
├── specimen_index_presence/ # per-specimen presence indexes
├── specimen_index_count/ # per-specimen count indexes
├── global_index_presence/ # merged global presence index (sparse, as merged)
├── global_index_presence_dense/ # global presence index, dense-repacked (query benchmark)
├── global_index_count/ # merged global count index (sparse, as merged)
├── global_index_count_dense/ # global count index, dense-repacked (query benchmark)
├── specific_index_presence/ # species-specific presence indexes
├── specific_index_count/ # species-specific count indexes
├── query_presence_dense/ # query output against global_index_presence_dense
├── query_presence_sparse/ # query output against global_index_presence
├── query_count_dense/ # query output against global_index_count_dense
├── query_count_sparse/ # query output against global_index_count
── stats/ # all benchmark statistics
├── indexing_presence/
├── indexing_count/
├── verify_presence/
├── verify_count/
├── specific_kmer_presence/
├── specific_kmer_count/
├── verify_merge_presence/
├── verify_merge_count/
├── pack_dense_presence/
├── pack_dense_count/
├── query_presence_dense/
├── query_presence_sparse/
├── query_count_dense/
├── query_count_sparse/
├── dist_comparison/
└── verify_query/
```
+1 -1
View File
@@ -11,7 +11,7 @@ set -euo pipefail
TYPE="$1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
STATS_DIR="${SCRIPT_DIR}/stats/${TYPE}"
STATS_DIR="${SCRIPT_DIR}/run/stats/${TYPE}"
case "${TYPE}" in
indexing_presence|indexing_count)
+3 -2
View File
@@ -2,8 +2,9 @@
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SIMDATA_DIR="${SCRIPT_DIR}/simulated_data"
REF_DIR="${SCRIPT_DIR}/reference_index"
RUN_DIR="${SCRIPT_DIR}/run"
SIMDATA_DIR="${RUN_DIR}/simulated_data"
REF_DIR="${RUN_DIR}/reference_index"
PYTHON="${SCRIPT_DIR}/../.venv/bin/python3"
BUILD_PY="${SCRIPT_DIR}/build_reference.py"
+4 -4
View File
@@ -176,10 +176,10 @@ def write_csv(path: Path, labels: list[str], mat: np.ndarray, fmt: str) -> None:
def main() -> None:
ap = argparse.ArgumentParser(description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
ap.add_argument('--ref-dir', default='reference_index',
help='Directory with per-specimen .npz files (default: reference_index)')
ap.add_argument('--out-dir', default='reference_dist',
help='Output directory for CSV files (default: reference_dist)')
ap.add_argument('--ref-dir', default='run/reference_index',
help='Directory with per-specimen .npz files (default: run/reference_index)')
ap.add_argument('--out-dir', default='run/reference_dist',
help='Output directory for CSV files (default: run/reference_dist)')
args = ap.parse_args()
ref_dir = Path(args.ref_dir)
+5 -2
View File
@@ -150,17 +150,20 @@ def main() -> None:
formatter_class=argparse.RawDescriptionHelpFormatter)
ap.add_argument('--tol', type=float, default=1e-4,
help='Max abs diff threshold for PASS/FAIL (default 1e-4)')
ap.add_argument('--out', default='stats/dist_comparison/summary.csv',
ap.add_argument('--run-dir', default='run',
help='Root directory holding reference_dist/ and obikmer_dist/ (default: run)')
ap.add_argument('--out', default='run/stats/dist_comparison/summary.csv',
help='Output summary CSV path')
args = ap.parse_args()
out_path = Path(args.out)
out_path.parent.mkdir(parents=True, exist_ok=True)
run_dir = Path(args.run_dir)
print(f'Comparing {len(COMPARISONS)} matrix pairs…', file=sys.stderr)
rows = []
for label, ref, obi in COMPARISONS:
rows.append(compare(label, Path(ref), Path(obi), tol=args.tol))
rows.append(compare(label, run_dir / ref, run_dir / obi, tol=args.tol))
fields = ['comparison', 'max_abs', 'mean_abs', 'rmse', 'n_pairs', 'status']
with out_path.open('w', newline='') as fh:
+152 -152
View File
@@ -2,212 +2,212 @@ SPECIMENS := Escherichia_coli--K-12_MG1655 Escherichia_coli--EDL933 Salmonella_e
SPECIES := Escherichia_coli Salmonella_enterica Bacillus_subtilis Shouchella_clausii Klebsiella_pneumoniae Opitutus_terrae Saccharolobus_islandicus Acidobacterium_capsulatum Proteus_mirabilis Wolbachia_endosymbiont Yersinia_ruckeri Candidozyma_auris
# Escherichia_coli--K-12_MG1655
simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz: genomes/GCF_000005845.2_ASM584v2_genomic.fna.gz
reference_index/Escherichia_coli--K-12_MG1655.npz: simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz
specimen_index_presence/Escherichia_coli--K-12_MG1655/index.done stats/indexing_presence/Escherichia_coli--K-12_MG1655.stats: simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz
specimen_index_count/Escherichia_coli--K-12_MG1655/index.done stats/indexing_count/Escherichia_coli--K-12_MG1655.stats: simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz
stats/verify_presence/Escherichia_coli--K-12_MG1655.stats: reference_index/Escherichia_coli--K-12_MG1655.npz specimen_index_presence/Escherichia_coli--K-12_MG1655/index.done
stats/verify_count/Escherichia_coli--K-12_MG1655.stats: reference_index/Escherichia_coli--K-12_MG1655.npz specimen_index_count/Escherichia_coli--K-12_MG1655/index.done
run/simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz: run/genomes/GCF_000005845.2_ASM584v2_genomic.fna.gz
run/reference_index/Escherichia_coli--K-12_MG1655.npz: run/simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz
run/specimen_index_presence/Escherichia_coli--K-12_MG1655/index.done run/stats/indexing_presence/Escherichia_coli--K-12_MG1655.stats: run/simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz
run/specimen_index_count/Escherichia_coli--K-12_MG1655/index.done run/stats/indexing_count/Escherichia_coli--K-12_MG1655.stats: run/simulated_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz
run/stats/verify_presence/Escherichia_coli--K-12_MG1655.stats: run/reference_index/Escherichia_coli--K-12_MG1655.npz run/specimen_index_presence/Escherichia_coli--K-12_MG1655/index.done
run/stats/verify_count/Escherichia_coli--K-12_MG1655.stats: run/reference_index/Escherichia_coli--K-12_MG1655.npz run/specimen_index_count/Escherichia_coli--K-12_MG1655/index.done
# Escherichia_coli--EDL933
simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz: genomes/GCF_000006665.1_ASM666v1_genomic.fna.gz
reference_index/Escherichia_coli--EDL933.npz: simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz
specimen_index_presence/Escherichia_coli--EDL933/index.done stats/indexing_presence/Escherichia_coli--EDL933.stats: simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz
specimen_index_count/Escherichia_coli--EDL933/index.done stats/indexing_count/Escherichia_coli--EDL933.stats: simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz
stats/verify_presence/Escherichia_coli--EDL933.stats: reference_index/Escherichia_coli--EDL933.npz specimen_index_presence/Escherichia_coli--EDL933/index.done
stats/verify_count/Escherichia_coli--EDL933.stats: reference_index/Escherichia_coli--EDL933.npz specimen_index_count/Escherichia_coli--EDL933/index.done
run/simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz: run/genomes/GCF_000006665.1_ASM666v1_genomic.fna.gz
run/reference_index/Escherichia_coli--EDL933.npz: run/simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz
run/specimen_index_presence/Escherichia_coli--EDL933/index.done run/stats/indexing_presence/Escherichia_coli--EDL933.stats: run/simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz
run/specimen_index_count/Escherichia_coli--EDL933/index.done run/stats/indexing_count/Escherichia_coli--EDL933.stats: run/simulated_data/Escherichia_coli/EDL933/reads_R1.fastq.gz
run/stats/verify_presence/Escherichia_coli--EDL933.stats: run/reference_index/Escherichia_coli--EDL933.npz run/specimen_index_presence/Escherichia_coli--EDL933/index.done
run/stats/verify_count/Escherichia_coli--EDL933.stats: run/reference_index/Escherichia_coli--EDL933.npz run/specimen_index_count/Escherichia_coli--EDL933/index.done
# Salmonella_enterica--LT2
simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz: genomes/GCF_000006945.2_ASM694v2_genomic.fna.gz
reference_index/Salmonella_enterica--LT2.npz: simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz
specimen_index_presence/Salmonella_enterica--LT2/index.done stats/indexing_presence/Salmonella_enterica--LT2.stats: simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz
specimen_index_count/Salmonella_enterica--LT2/index.done stats/indexing_count/Salmonella_enterica--LT2.stats: simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz
stats/verify_presence/Salmonella_enterica--LT2.stats: reference_index/Salmonella_enterica--LT2.npz specimen_index_presence/Salmonella_enterica--LT2/index.done
stats/verify_count/Salmonella_enterica--LT2.stats: reference_index/Salmonella_enterica--LT2.npz specimen_index_count/Salmonella_enterica--LT2/index.done
run/simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz: run/genomes/GCF_000006945.2_ASM694v2_genomic.fna.gz
run/reference_index/Salmonella_enterica--LT2.npz: run/simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz
run/specimen_index_presence/Salmonella_enterica--LT2/index.done run/stats/indexing_presence/Salmonella_enterica--LT2.stats: run/simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz
run/specimen_index_count/Salmonella_enterica--LT2/index.done run/stats/indexing_count/Salmonella_enterica--LT2.stats: run/simulated_data/Salmonella_enterica/LT2/reads_R1.fastq.gz
run/stats/verify_presence/Salmonella_enterica--LT2.stats: run/reference_index/Salmonella_enterica--LT2.npz run/specimen_index_presence/Salmonella_enterica--LT2/index.done
run/stats/verify_count/Salmonella_enterica--LT2.stats: run/reference_index/Salmonella_enterica--LT2.npz run/specimen_index_count/Salmonella_enterica--LT2/index.done
# Escherichia_coli--CFT073
simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz: genomes/GCF_000007445.1_ASM744v1_genomic.fna.gz
reference_index/Escherichia_coli--CFT073.npz: simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz
specimen_index_presence/Escherichia_coli--CFT073/index.done stats/indexing_presence/Escherichia_coli--CFT073.stats: simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz
specimen_index_count/Escherichia_coli--CFT073/index.done stats/indexing_count/Escherichia_coli--CFT073.stats: simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz
stats/verify_presence/Escherichia_coli--CFT073.stats: reference_index/Escherichia_coli--CFT073.npz specimen_index_presence/Escherichia_coli--CFT073/index.done
stats/verify_count/Escherichia_coli--CFT073.stats: reference_index/Escherichia_coli--CFT073.npz specimen_index_count/Escherichia_coli--CFT073/index.done
run/simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz: run/genomes/GCF_000007445.1_ASM744v1_genomic.fna.gz
run/reference_index/Escherichia_coli--CFT073.npz: run/simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz
run/specimen_index_presence/Escherichia_coli--CFT073/index.done run/stats/indexing_presence/Escherichia_coli--CFT073.stats: run/simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz
run/specimen_index_count/Escherichia_coli--CFT073/index.done run/stats/indexing_count/Escherichia_coli--CFT073.stats: run/simulated_data/Escherichia_coli/CFT073/reads_R1.fastq.gz
run/stats/verify_presence/Escherichia_coli--CFT073.stats: run/reference_index/Escherichia_coli--CFT073.npz run/specimen_index_presence/Escherichia_coli--CFT073/index.done
run/stats/verify_count/Escherichia_coli--CFT073.stats: run/reference_index/Escherichia_coli--CFT073.npz run/specimen_index_count/Escherichia_coli--CFT073/index.done
# Bacillus_subtilis--168
simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz: genomes/GCF_000009045.1_ASM904v1_genomic.fna.gz
reference_index/Bacillus_subtilis--168.npz: simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz
specimen_index_presence/Bacillus_subtilis--168/index.done stats/indexing_presence/Bacillus_subtilis--168.stats: simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz
specimen_index_count/Bacillus_subtilis--168/index.done stats/indexing_count/Bacillus_subtilis--168.stats: simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz
stats/verify_presence/Bacillus_subtilis--168.stats: reference_index/Bacillus_subtilis--168.npz specimen_index_presence/Bacillus_subtilis--168/index.done
stats/verify_count/Bacillus_subtilis--168.stats: reference_index/Bacillus_subtilis--168.npz specimen_index_count/Bacillus_subtilis--168/index.done
run/simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz: run/genomes/GCF_000009045.1_ASM904v1_genomic.fna.gz
run/reference_index/Bacillus_subtilis--168.npz: run/simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz
run/specimen_index_presence/Bacillus_subtilis--168/index.done run/stats/indexing_presence/Bacillus_subtilis--168.stats: run/simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz
run/specimen_index_count/Bacillus_subtilis--168/index.done run/stats/indexing_count/Bacillus_subtilis--168.stats: run/simulated_data/Bacillus_subtilis/168/reads_R1.fastq.gz
run/stats/verify_presence/Bacillus_subtilis--168.stats: run/reference_index/Bacillus_subtilis--168.npz run/specimen_index_presence/Bacillus_subtilis--168/index.done
run/stats/verify_count/Bacillus_subtilis--168.stats: run/reference_index/Bacillus_subtilis--168.npz run/specimen_index_count/Bacillus_subtilis--168/index.done
# Salmonella_enterica--P125109
simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz: genomes/GCF_000009505.1_ASM950v1_genomic.fna.gz
reference_index/Salmonella_enterica--P125109.npz: simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz
specimen_index_presence/Salmonella_enterica--P125109/index.done stats/indexing_presence/Salmonella_enterica--P125109.stats: simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz
specimen_index_count/Salmonella_enterica--P125109/index.done stats/indexing_count/Salmonella_enterica--P125109.stats: simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz
stats/verify_presence/Salmonella_enterica--P125109.stats: reference_index/Salmonella_enterica--P125109.npz specimen_index_presence/Salmonella_enterica--P125109/index.done
stats/verify_count/Salmonella_enterica--P125109.stats: reference_index/Salmonella_enterica--P125109.npz specimen_index_count/Salmonella_enterica--P125109/index.done
run/simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz: run/genomes/GCF_000009505.1_ASM950v1_genomic.fna.gz
run/reference_index/Salmonella_enterica--P125109.npz: run/simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz
run/specimen_index_presence/Salmonella_enterica--P125109/index.done run/stats/indexing_presence/Salmonella_enterica--P125109.stats: run/simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz
run/specimen_index_count/Salmonella_enterica--P125109/index.done run/stats/indexing_count/Salmonella_enterica--P125109.stats: run/simulated_data/Salmonella_enterica/P125109/reads_R1.fastq.gz
run/stats/verify_presence/Salmonella_enterica--P125109.stats: run/reference_index/Salmonella_enterica--P125109.npz run/specimen_index_presence/Salmonella_enterica--P125109/index.done
run/stats/verify_count/Salmonella_enterica--P125109.stats: run/reference_index/Salmonella_enterica--P125109.npz run/specimen_index_count/Salmonella_enterica--P125109/index.done
# Shouchella_clausii--KSM-K16
simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz: genomes/GCF_000009825.1_ASM982v1_genomic.fna.gz
reference_index/Shouchella_clausii--KSM-K16.npz: simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz
specimen_index_presence/Shouchella_clausii--KSM-K16/index.done stats/indexing_presence/Shouchella_clausii--KSM-K16.stats: simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz
specimen_index_count/Shouchella_clausii--KSM-K16/index.done stats/indexing_count/Shouchella_clausii--KSM-K16.stats: simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz
stats/verify_presence/Shouchella_clausii--KSM-K16.stats: reference_index/Shouchella_clausii--KSM-K16.npz specimen_index_presence/Shouchella_clausii--KSM-K16/index.done
stats/verify_count/Shouchella_clausii--KSM-K16.stats: reference_index/Shouchella_clausii--KSM-K16.npz specimen_index_count/Shouchella_clausii--KSM-K16/index.done
run/simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz: run/genomes/GCF_000009825.1_ASM982v1_genomic.fna.gz
run/reference_index/Shouchella_clausii--KSM-K16.npz: run/simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz
run/specimen_index_presence/Shouchella_clausii--KSM-K16/index.done run/stats/indexing_presence/Shouchella_clausii--KSM-K16.stats: run/simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz
run/specimen_index_count/Shouchella_clausii--KSM-K16/index.done run/stats/indexing_count/Shouchella_clausii--KSM-K16.stats: run/simulated_data/Shouchella_clausii/KSM-K16/reads_R1.fastq.gz
run/stats/verify_presence/Shouchella_clausii--KSM-K16.stats: run/reference_index/Shouchella_clausii--KSM-K16.npz run/specimen_index_presence/Shouchella_clausii--KSM-K16/index.done
run/stats/verify_count/Shouchella_clausii--KSM-K16.stats: run/reference_index/Shouchella_clausii--KSM-K16.npz run/specimen_index_count/Shouchella_clausii--KSM-K16/index.done
# Escherichia_coli--K-12_W3110
simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz: genomes/GCF_000010245.2_ASM1024v1_genomic.fna.gz
reference_index/Escherichia_coli--K-12_W3110.npz: simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz
specimen_index_presence/Escherichia_coli--K-12_W3110/index.done stats/indexing_presence/Escherichia_coli--K-12_W3110.stats: simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz
specimen_index_count/Escherichia_coli--K-12_W3110/index.done stats/indexing_count/Escherichia_coli--K-12_W3110.stats: simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz
stats/verify_presence/Escherichia_coli--K-12_W3110.stats: reference_index/Escherichia_coli--K-12_W3110.npz specimen_index_presence/Escherichia_coli--K-12_W3110/index.done
stats/verify_count/Escherichia_coli--K-12_W3110.stats: reference_index/Escherichia_coli--K-12_W3110.npz specimen_index_count/Escherichia_coli--K-12_W3110/index.done
run/simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz: run/genomes/GCF_000010245.2_ASM1024v1_genomic.fna.gz
run/reference_index/Escherichia_coli--K-12_W3110.npz: run/simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz
run/specimen_index_presence/Escherichia_coli--K-12_W3110/index.done run/stats/indexing_presence/Escherichia_coli--K-12_W3110.stats: run/simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz
run/specimen_index_count/Escherichia_coli--K-12_W3110/index.done run/stats/indexing_count/Escherichia_coli--K-12_W3110.stats: run/simulated_data/Escherichia_coli/K-12_W3110/reads_R1.fastq.gz
run/stats/verify_presence/Escherichia_coli--K-12_W3110.stats: run/reference_index/Escherichia_coli--K-12_W3110.npz run/specimen_index_presence/Escherichia_coli--K-12_W3110/index.done
run/stats/verify_count/Escherichia_coli--K-12_W3110.stats: run/reference_index/Escherichia_coli--K-12_W3110.npz run/specimen_index_count/Escherichia_coli--K-12_W3110/index.done
# Klebsiella_pneumoniae--MGH_78578
simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz: genomes/GCF_000016305.1_ASM1630v1_genomic.fna.gz
reference_index/Klebsiella_pneumoniae--MGH_78578.npz: simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz
specimen_index_presence/Klebsiella_pneumoniae--MGH_78578/index.done stats/indexing_presence/Klebsiella_pneumoniae--MGH_78578.stats: simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz
specimen_index_count/Klebsiella_pneumoniae--MGH_78578/index.done stats/indexing_count/Klebsiella_pneumoniae--MGH_78578.stats: simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz
stats/verify_presence/Klebsiella_pneumoniae--MGH_78578.stats: reference_index/Klebsiella_pneumoniae--MGH_78578.npz specimen_index_presence/Klebsiella_pneumoniae--MGH_78578/index.done
stats/verify_count/Klebsiella_pneumoniae--MGH_78578.stats: reference_index/Klebsiella_pneumoniae--MGH_78578.npz specimen_index_count/Klebsiella_pneumoniae--MGH_78578/index.done
run/simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz: run/genomes/GCF_000016305.1_ASM1630v1_genomic.fna.gz
run/reference_index/Klebsiella_pneumoniae--MGH_78578.npz: run/simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz
run/specimen_index_presence/Klebsiella_pneumoniae--MGH_78578/index.done run/stats/indexing_presence/Klebsiella_pneumoniae--MGH_78578.stats: run/simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz
run/specimen_index_count/Klebsiella_pneumoniae--MGH_78578/index.done run/stats/indexing_count/Klebsiella_pneumoniae--MGH_78578.stats: run/simulated_data/Klebsiella_pneumoniae/MGH_78578/reads_R1.fastq.gz
run/stats/verify_presence/Klebsiella_pneumoniae--MGH_78578.stats: run/reference_index/Klebsiella_pneumoniae--MGH_78578.npz run/specimen_index_presence/Klebsiella_pneumoniae--MGH_78578/index.done
run/stats/verify_count/Klebsiella_pneumoniae--MGH_78578.stats: run/reference_index/Klebsiella_pneumoniae--MGH_78578.npz run/specimen_index_count/Klebsiella_pneumoniae--MGH_78578/index.done
# Opitutus_terrae--PB90-1
simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz: genomes/GCF_000019965.1_ASM1996v1_genomic.fna.gz
reference_index/Opitutus_terrae--PB90-1.npz: simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz
specimen_index_presence/Opitutus_terrae--PB90-1/index.done stats/indexing_presence/Opitutus_terrae--PB90-1.stats: simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz
specimen_index_count/Opitutus_terrae--PB90-1/index.done stats/indexing_count/Opitutus_terrae--PB90-1.stats: simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz
stats/verify_presence/Opitutus_terrae--PB90-1.stats: reference_index/Opitutus_terrae--PB90-1.npz specimen_index_presence/Opitutus_terrae--PB90-1/index.done
stats/verify_count/Opitutus_terrae--PB90-1.stats: reference_index/Opitutus_terrae--PB90-1.npz specimen_index_count/Opitutus_terrae--PB90-1/index.done
run/simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz: run/genomes/GCF_000019965.1_ASM1996v1_genomic.fna.gz
run/reference_index/Opitutus_terrae--PB90-1.npz: run/simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz
run/specimen_index_presence/Opitutus_terrae--PB90-1/index.done run/stats/indexing_presence/Opitutus_terrae--PB90-1.stats: run/simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz
run/specimen_index_count/Opitutus_terrae--PB90-1/index.done run/stats/indexing_count/Opitutus_terrae--PB90-1.stats: run/simulated_data/Opitutus_terrae/PB90-1/reads_R1.fastq.gz
run/stats/verify_presence/Opitutus_terrae--PB90-1.stats: run/reference_index/Opitutus_terrae--PB90-1.npz run/specimen_index_presence/Opitutus_terrae--PB90-1/index.done
run/stats/verify_count/Opitutus_terrae--PB90-1.stats: run/reference_index/Opitutus_terrae--PB90-1.npz run/specimen_index_count/Opitutus_terrae--PB90-1/index.done
# Saccharolobus_islandicus--M.16.4
simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz: genomes/GCF_000022445.1_ASM2244v1_genomic.fna.gz
reference_index/Saccharolobus_islandicus--M.16.4.npz: simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz
specimen_index_presence/Saccharolobus_islandicus--M.16.4/index.done stats/indexing_presence/Saccharolobus_islandicus--M.16.4.stats: simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz
specimen_index_count/Saccharolobus_islandicus--M.16.4/index.done stats/indexing_count/Saccharolobus_islandicus--M.16.4.stats: simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz
stats/verify_presence/Saccharolobus_islandicus--M.16.4.stats: reference_index/Saccharolobus_islandicus--M.16.4.npz specimen_index_presence/Saccharolobus_islandicus--M.16.4/index.done
stats/verify_count/Saccharolobus_islandicus--M.16.4.stats: reference_index/Saccharolobus_islandicus--M.16.4.npz specimen_index_count/Saccharolobus_islandicus--M.16.4/index.done
run/simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz: run/genomes/GCF_000022445.1_ASM2244v1_genomic.fna.gz
run/reference_index/Saccharolobus_islandicus--M.16.4.npz: run/simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz
run/specimen_index_presence/Saccharolobus_islandicus--M.16.4/index.done run/stats/indexing_presence/Saccharolobus_islandicus--M.16.4.stats: run/simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz
run/specimen_index_count/Saccharolobus_islandicus--M.16.4/index.done run/stats/indexing_count/Saccharolobus_islandicus--M.16.4.stats: run/simulated_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz
run/stats/verify_presence/Saccharolobus_islandicus--M.16.4.stats: run/reference_index/Saccharolobus_islandicus--M.16.4.npz run/specimen_index_presence/Saccharolobus_islandicus--M.16.4/index.done
run/stats/verify_count/Saccharolobus_islandicus--M.16.4.stats: run/reference_index/Saccharolobus_islandicus--M.16.4.npz run/specimen_index_count/Saccharolobus_islandicus--M.16.4/index.done
# Acidobacterium_capsulatum--ATCC_51196
simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz: genomes/GCF_000022565.1_ASM2256v1_genomic.fna.gz
reference_index/Acidobacterium_capsulatum--ATCC_51196.npz: simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz
specimen_index_presence/Acidobacterium_capsulatum--ATCC_51196/index.done stats/indexing_presence/Acidobacterium_capsulatum--ATCC_51196.stats: simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz
specimen_index_count/Acidobacterium_capsulatum--ATCC_51196/index.done stats/indexing_count/Acidobacterium_capsulatum--ATCC_51196.stats: simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz
stats/verify_presence/Acidobacterium_capsulatum--ATCC_51196.stats: reference_index/Acidobacterium_capsulatum--ATCC_51196.npz specimen_index_presence/Acidobacterium_capsulatum--ATCC_51196/index.done
stats/verify_count/Acidobacterium_capsulatum--ATCC_51196.stats: reference_index/Acidobacterium_capsulatum--ATCC_51196.npz specimen_index_count/Acidobacterium_capsulatum--ATCC_51196/index.done
run/simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz: run/genomes/GCF_000022565.1_ASM2256v1_genomic.fna.gz
run/reference_index/Acidobacterium_capsulatum--ATCC_51196.npz: run/simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz
run/specimen_index_presence/Acidobacterium_capsulatum--ATCC_51196/index.done run/stats/indexing_presence/Acidobacterium_capsulatum--ATCC_51196.stats: run/simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz
run/specimen_index_count/Acidobacterium_capsulatum--ATCC_51196/index.done run/stats/indexing_count/Acidobacterium_capsulatum--ATCC_51196.stats: run/simulated_data/Acidobacterium_capsulatum/ATCC_51196/reads_R1.fastq.gz
run/stats/verify_presence/Acidobacterium_capsulatum--ATCC_51196.stats: run/reference_index/Acidobacterium_capsulatum--ATCC_51196.npz run/specimen_index_presence/Acidobacterium_capsulatum--ATCC_51196/index.done
run/stats/verify_count/Acidobacterium_capsulatum--ATCC_51196.stats: run/reference_index/Acidobacterium_capsulatum--ATCC_51196.npz run/specimen_index_count/Acidobacterium_capsulatum--ATCC_51196/index.done
# Salmonella_enterica--AKU_12601
simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz: genomes/GCF_000026565.1_ASM2656v1_genomic.fna.gz
reference_index/Salmonella_enterica--AKU_12601.npz: simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz
specimen_index_presence/Salmonella_enterica--AKU_12601/index.done stats/indexing_presence/Salmonella_enterica--AKU_12601.stats: simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz
specimen_index_count/Salmonella_enterica--AKU_12601/index.done stats/indexing_count/Salmonella_enterica--AKU_12601.stats: simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz
stats/verify_presence/Salmonella_enterica--AKU_12601.stats: reference_index/Salmonella_enterica--AKU_12601.npz specimen_index_presence/Salmonella_enterica--AKU_12601/index.done
stats/verify_count/Salmonella_enterica--AKU_12601.stats: reference_index/Salmonella_enterica--AKU_12601.npz specimen_index_count/Salmonella_enterica--AKU_12601/index.done
run/simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz: run/genomes/GCF_000026565.1_ASM2656v1_genomic.fna.gz
run/reference_index/Salmonella_enterica--AKU_12601.npz: run/simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz
run/specimen_index_presence/Salmonella_enterica--AKU_12601/index.done run/stats/indexing_presence/Salmonella_enterica--AKU_12601.stats: run/simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz
run/specimen_index_count/Salmonella_enterica--AKU_12601/index.done run/stats/indexing_count/Salmonella_enterica--AKU_12601.stats: run/simulated_data/Salmonella_enterica/AKU_12601/reads_R1.fastq.gz
run/stats/verify_presence/Salmonella_enterica--AKU_12601.stats: run/reference_index/Salmonella_enterica--AKU_12601.npz run/specimen_index_presence/Salmonella_enterica--AKU_12601/index.done
run/stats/verify_count/Salmonella_enterica--AKU_12601.stats: run/reference_index/Salmonella_enterica--AKU_12601.npz run/specimen_index_count/Salmonella_enterica--AKU_12601/index.done
# Proteus_mirabilis--HI4320
simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz: genomes/GCF_000069965.1_ASM6996v1_genomic.fna.gz
reference_index/Proteus_mirabilis--HI4320.npz: simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz
specimen_index_presence/Proteus_mirabilis--HI4320/index.done stats/indexing_presence/Proteus_mirabilis--HI4320.stats: simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz
specimen_index_count/Proteus_mirabilis--HI4320/index.done stats/indexing_count/Proteus_mirabilis--HI4320.stats: simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz
stats/verify_presence/Proteus_mirabilis--HI4320.stats: reference_index/Proteus_mirabilis--HI4320.npz specimen_index_presence/Proteus_mirabilis--HI4320/index.done
stats/verify_count/Proteus_mirabilis--HI4320.stats: reference_index/Proteus_mirabilis--HI4320.npz specimen_index_count/Proteus_mirabilis--HI4320/index.done
run/simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz: run/genomes/GCF_000069965.1_ASM6996v1_genomic.fna.gz
run/reference_index/Proteus_mirabilis--HI4320.npz: run/simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz
run/specimen_index_presence/Proteus_mirabilis--HI4320/index.done run/stats/indexing_presence/Proteus_mirabilis--HI4320.stats: run/simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz
run/specimen_index_count/Proteus_mirabilis--HI4320/index.done run/stats/indexing_count/Proteus_mirabilis--HI4320.stats: run/simulated_data/Proteus_mirabilis/HI4320/reads_R1.fastq.gz
run/stats/verify_presence/Proteus_mirabilis--HI4320.stats: run/reference_index/Proteus_mirabilis--HI4320.npz run/specimen_index_presence/Proteus_mirabilis--HI4320/index.done
run/stats/verify_count/Proteus_mirabilis--HI4320.stats: run/reference_index/Proteus_mirabilis--HI4320.npz run/specimen_index_count/Proteus_mirabilis--HI4320/index.done
# Salmonella_enterica--CT18
simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz: genomes/GCF_000195995.1_ASM19599v1_genomic.fna.gz
reference_index/Salmonella_enterica--CT18.npz: simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz
specimen_index_presence/Salmonella_enterica--CT18/index.done stats/indexing_presence/Salmonella_enterica--CT18.stats: simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz
specimen_index_count/Salmonella_enterica--CT18/index.done stats/indexing_count/Salmonella_enterica--CT18.stats: simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz
stats/verify_presence/Salmonella_enterica--CT18.stats: reference_index/Salmonella_enterica--CT18.npz specimen_index_presence/Salmonella_enterica--CT18/index.done
stats/verify_count/Salmonella_enterica--CT18.stats: reference_index/Salmonella_enterica--CT18.npz specimen_index_count/Salmonella_enterica--CT18/index.done
run/simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz: run/genomes/GCF_000195995.1_ASM19599v1_genomic.fna.gz
run/reference_index/Salmonella_enterica--CT18.npz: run/simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz
run/specimen_index_presence/Salmonella_enterica--CT18/index.done run/stats/indexing_presence/Salmonella_enterica--CT18.stats: run/simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz
run/specimen_index_count/Salmonella_enterica--CT18/index.done run/stats/indexing_count/Salmonella_enterica--CT18.stats: run/simulated_data/Salmonella_enterica/CT18/reads_R1.fastq.gz
run/stats/verify_presence/Salmonella_enterica--CT18.stats: run/reference_index/Salmonella_enterica--CT18.npz run/specimen_index_presence/Salmonella_enterica--CT18/index.done
run/stats/verify_count/Salmonella_enterica--CT18.stats: run/reference_index/Salmonella_enterica--CT18.npz run/specimen_index_count/Salmonella_enterica--CT18/index.done
# Klebsiella_pneumoniae--HS11286
simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz: genomes/GCF_000240185.1_ASM24018v2_genomic.fna.gz
reference_index/Klebsiella_pneumoniae--HS11286.npz: simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz
specimen_index_presence/Klebsiella_pneumoniae--HS11286/index.done stats/indexing_presence/Klebsiella_pneumoniae--HS11286.stats: simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz
specimen_index_count/Klebsiella_pneumoniae--HS11286/index.done stats/indexing_count/Klebsiella_pneumoniae--HS11286.stats: simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz
stats/verify_presence/Klebsiella_pneumoniae--HS11286.stats: reference_index/Klebsiella_pneumoniae--HS11286.npz specimen_index_presence/Klebsiella_pneumoniae--HS11286/index.done
stats/verify_count/Klebsiella_pneumoniae--HS11286.stats: reference_index/Klebsiella_pneumoniae--HS11286.npz specimen_index_count/Klebsiella_pneumoniae--HS11286/index.done
run/simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz: run/genomes/GCF_000240185.1_ASM24018v2_genomic.fna.gz
run/reference_index/Klebsiella_pneumoniae--HS11286.npz: run/simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz
run/specimen_index_presence/Klebsiella_pneumoniae--HS11286/index.done run/stats/indexing_presence/Klebsiella_pneumoniae--HS11286.stats: run/simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz
run/specimen_index_count/Klebsiella_pneumoniae--HS11286/index.done run/stats/indexing_count/Klebsiella_pneumoniae--HS11286.stats: run/simulated_data/Klebsiella_pneumoniae/HS11286/reads_R1.fastq.gz
run/stats/verify_presence/Klebsiella_pneumoniae--HS11286.stats: run/reference_index/Klebsiella_pneumoniae--HS11286.npz run/specimen_index_presence/Klebsiella_pneumoniae--HS11286/index.done
run/stats/verify_count/Klebsiella_pneumoniae--HS11286.stats: run/reference_index/Klebsiella_pneumoniae--HS11286.npz run/specimen_index_count/Klebsiella_pneumoniae--HS11286/index.done
# Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1
simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz: genomes/GCF_000306885.1_ASM30688v1_genomic.fna.gz
reference_index/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.npz: simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz
specimen_index_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done stats/indexing_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz
specimen_index_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done stats/indexing_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz
stats/verify_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: reference_index/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.npz specimen_index_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done
stats/verify_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: reference_index/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.npz specimen_index_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done
run/simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz: run/genomes/GCF_000306885.1_ASM30688v1_genomic.fna.gz
run/reference_index/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.npz: run/simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz
run/specimen_index_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done run/stats/indexing_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: run/simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz
run/specimen_index_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done run/stats/indexing_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: run/simulated_data/Wolbachia_endosymbiont/GCF_000306885.1_ASM30688v1/reads_R1.fastq.gz
run/stats/verify_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: run/reference_index/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.npz run/specimen_index_presence/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done
run/stats/verify_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.stats: run/reference_index/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1.npz run/specimen_index_count/Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1/index.done
# Klebsiella_pneumoniae--ATCC_13883
simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz: genomes/GCF_000742135.1_ASM74213v1_genomic.fna.gz
reference_index/Klebsiella_pneumoniae--ATCC_13883.npz: simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz
specimen_index_presence/Klebsiella_pneumoniae--ATCC_13883/index.done stats/indexing_presence/Klebsiella_pneumoniae--ATCC_13883.stats: simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz
specimen_index_count/Klebsiella_pneumoniae--ATCC_13883/index.done stats/indexing_count/Klebsiella_pneumoniae--ATCC_13883.stats: simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz
stats/verify_presence/Klebsiella_pneumoniae--ATCC_13883.stats: reference_index/Klebsiella_pneumoniae--ATCC_13883.npz specimen_index_presence/Klebsiella_pneumoniae--ATCC_13883/index.done
stats/verify_count/Klebsiella_pneumoniae--ATCC_13883.stats: reference_index/Klebsiella_pneumoniae--ATCC_13883.npz specimen_index_count/Klebsiella_pneumoniae--ATCC_13883/index.done
run/simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz: run/genomes/GCF_000742135.1_ASM74213v1_genomic.fna.gz
run/reference_index/Klebsiella_pneumoniae--ATCC_13883.npz: run/simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz
run/specimen_index_presence/Klebsiella_pneumoniae--ATCC_13883/index.done run/stats/indexing_presence/Klebsiella_pneumoniae--ATCC_13883.stats: run/simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz
run/specimen_index_count/Klebsiella_pneumoniae--ATCC_13883/index.done run/stats/indexing_count/Klebsiella_pneumoniae--ATCC_13883.stats: run/simulated_data/Klebsiella_pneumoniae/ATCC_13883/reads_R1.fastq.gz
run/stats/verify_presence/Klebsiella_pneumoniae--ATCC_13883.stats: run/reference_index/Klebsiella_pneumoniae--ATCC_13883.npz run/specimen_index_presence/Klebsiella_pneumoniae--ATCC_13883/index.done
run/stats/verify_count/Klebsiella_pneumoniae--ATCC_13883.stats: run/reference_index/Klebsiella_pneumoniae--ATCC_13883.npz run/specimen_index_count/Klebsiella_pneumoniae--ATCC_13883/index.done
# Yersinia_ruckeri--YRB
simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz: genomes/GCF_000834255.1_ASM83425v1_genomic.fna.gz
reference_index/Yersinia_ruckeri--YRB.npz: simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz
specimen_index_presence/Yersinia_ruckeri--YRB/index.done stats/indexing_presence/Yersinia_ruckeri--YRB.stats: simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz
specimen_index_count/Yersinia_ruckeri--YRB/index.done stats/indexing_count/Yersinia_ruckeri--YRB.stats: simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz
stats/verify_presence/Yersinia_ruckeri--YRB.stats: reference_index/Yersinia_ruckeri--YRB.npz specimen_index_presence/Yersinia_ruckeri--YRB/index.done
stats/verify_count/Yersinia_ruckeri--YRB.stats: reference_index/Yersinia_ruckeri--YRB.npz specimen_index_count/Yersinia_ruckeri--YRB/index.done
run/simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz: run/genomes/GCF_000834255.1_ASM83425v1_genomic.fna.gz
run/reference_index/Yersinia_ruckeri--YRB.npz: run/simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz
run/specimen_index_presence/Yersinia_ruckeri--YRB/index.done run/stats/indexing_presence/Yersinia_ruckeri--YRB.stats: run/simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz
run/specimen_index_count/Yersinia_ruckeri--YRB/index.done run/stats/indexing_count/Yersinia_ruckeri--YRB.stats: run/simulated_data/Yersinia_ruckeri/YRB/reads_R1.fastq.gz
run/stats/verify_presence/Yersinia_ruckeri--YRB.stats: run/reference_index/Yersinia_ruckeri--YRB.npz run/specimen_index_presence/Yersinia_ruckeri--YRB/index.done
run/stats/verify_count/Yersinia_ruckeri--YRB.stats: run/reference_index/Yersinia_ruckeri--YRB.npz run/specimen_index_count/Yersinia_ruckeri--YRB/index.done
# Candidozyma_auris--GCF_003013715.1_ASM301371v2
simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz: genomes/GCF_003013715.1_ASM301371v2_genomic.fna.gz
reference_index/Candidozyma_auris--GCF_003013715.1_ASM301371v2.npz: simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz
specimen_index_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done stats/indexing_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz
specimen_index_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done stats/indexing_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz
stats/verify_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: reference_index/Candidozyma_auris--GCF_003013715.1_ASM301371v2.npz specimen_index_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done
stats/verify_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: reference_index/Candidozyma_auris--GCF_003013715.1_ASM301371v2.npz specimen_index_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done
run/simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz: run/genomes/GCF_003013715.1_ASM301371v2_genomic.fna.gz
run/reference_index/Candidozyma_auris--GCF_003013715.1_ASM301371v2.npz: run/simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz
run/specimen_index_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done run/stats/indexing_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: run/simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz
run/specimen_index_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done run/stats/indexing_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: run/simulated_data/Candidozyma_auris/GCF_003013715.1_ASM301371v2/reads_R1.fastq.gz
run/stats/verify_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: run/reference_index/Candidozyma_auris--GCF_003013715.1_ASM301371v2.npz run/specimen_index_presence/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done
run/stats/verify_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2.stats: run/reference_index/Candidozyma_auris--GCF_003013715.1_ASM301371v2.npz run/specimen_index_count/Candidozyma_auris--GCF_003013715.1_ASM301371v2/index.done
# Escherichia_coli
specific_index_presence/Escherichia_coli/index.done stats/specific_kmer_presence/Escherichia_coli.stats: global_index_presence/index.done
specific_index_count/Escherichia_coli/index.done stats/specific_kmer_count/Escherichia_coli.stats: global_index_count/index.done
run/specific_index_presence/Escherichia_coli/index.done run/stats/specific_kmer_presence/Escherichia_coli.stats: run/global_index_presence/index.done
run/specific_index_count/Escherichia_coli/index.done run/stats/specific_kmer_count/Escherichia_coli.stats: run/global_index_count/index.done
# Salmonella_enterica
specific_index_presence/Salmonella_enterica/index.done stats/specific_kmer_presence/Salmonella_enterica.stats: global_index_presence/index.done
specific_index_count/Salmonella_enterica/index.done stats/specific_kmer_count/Salmonella_enterica.stats: global_index_count/index.done
run/specific_index_presence/Salmonella_enterica/index.done run/stats/specific_kmer_presence/Salmonella_enterica.stats: run/global_index_presence/index.done
run/specific_index_count/Salmonella_enterica/index.done run/stats/specific_kmer_count/Salmonella_enterica.stats: run/global_index_count/index.done
# Bacillus_subtilis
specific_index_presence/Bacillus_subtilis/index.done stats/specific_kmer_presence/Bacillus_subtilis.stats: global_index_presence/index.done
specific_index_count/Bacillus_subtilis/index.done stats/specific_kmer_count/Bacillus_subtilis.stats: global_index_count/index.done
run/specific_index_presence/Bacillus_subtilis/index.done run/stats/specific_kmer_presence/Bacillus_subtilis.stats: run/global_index_presence/index.done
run/specific_index_count/Bacillus_subtilis/index.done run/stats/specific_kmer_count/Bacillus_subtilis.stats: run/global_index_count/index.done
# Shouchella_clausii
specific_index_presence/Shouchella_clausii/index.done stats/specific_kmer_presence/Shouchella_clausii.stats: global_index_presence/index.done
specific_index_count/Shouchella_clausii/index.done stats/specific_kmer_count/Shouchella_clausii.stats: global_index_count/index.done
run/specific_index_presence/Shouchella_clausii/index.done run/stats/specific_kmer_presence/Shouchella_clausii.stats: run/global_index_presence/index.done
run/specific_index_count/Shouchella_clausii/index.done run/stats/specific_kmer_count/Shouchella_clausii.stats: run/global_index_count/index.done
# Klebsiella_pneumoniae
specific_index_presence/Klebsiella_pneumoniae/index.done stats/specific_kmer_presence/Klebsiella_pneumoniae.stats: global_index_presence/index.done
specific_index_count/Klebsiella_pneumoniae/index.done stats/specific_kmer_count/Klebsiella_pneumoniae.stats: global_index_count/index.done
run/specific_index_presence/Klebsiella_pneumoniae/index.done run/stats/specific_kmer_presence/Klebsiella_pneumoniae.stats: run/global_index_presence/index.done
run/specific_index_count/Klebsiella_pneumoniae/index.done run/stats/specific_kmer_count/Klebsiella_pneumoniae.stats: run/global_index_count/index.done
# Opitutus_terrae
specific_index_presence/Opitutus_terrae/index.done stats/specific_kmer_presence/Opitutus_terrae.stats: global_index_presence/index.done
specific_index_count/Opitutus_terrae/index.done stats/specific_kmer_count/Opitutus_terrae.stats: global_index_count/index.done
run/specific_index_presence/Opitutus_terrae/index.done run/stats/specific_kmer_presence/Opitutus_terrae.stats: run/global_index_presence/index.done
run/specific_index_count/Opitutus_terrae/index.done run/stats/specific_kmer_count/Opitutus_terrae.stats: run/global_index_count/index.done
# Saccharolobus_islandicus
specific_index_presence/Saccharolobus_islandicus/index.done stats/specific_kmer_presence/Saccharolobus_islandicus.stats: global_index_presence/index.done
specific_index_count/Saccharolobus_islandicus/index.done stats/specific_kmer_count/Saccharolobus_islandicus.stats: global_index_count/index.done
run/specific_index_presence/Saccharolobus_islandicus/index.done run/stats/specific_kmer_presence/Saccharolobus_islandicus.stats: run/global_index_presence/index.done
run/specific_index_count/Saccharolobus_islandicus/index.done run/stats/specific_kmer_count/Saccharolobus_islandicus.stats: run/global_index_count/index.done
# Acidobacterium_capsulatum
specific_index_presence/Acidobacterium_capsulatum/index.done stats/specific_kmer_presence/Acidobacterium_capsulatum.stats: global_index_presence/index.done
specific_index_count/Acidobacterium_capsulatum/index.done stats/specific_kmer_count/Acidobacterium_capsulatum.stats: global_index_count/index.done
run/specific_index_presence/Acidobacterium_capsulatum/index.done run/stats/specific_kmer_presence/Acidobacterium_capsulatum.stats: run/global_index_presence/index.done
run/specific_index_count/Acidobacterium_capsulatum/index.done run/stats/specific_kmer_count/Acidobacterium_capsulatum.stats: run/global_index_count/index.done
# Proteus_mirabilis
specific_index_presence/Proteus_mirabilis/index.done stats/specific_kmer_presence/Proteus_mirabilis.stats: global_index_presence/index.done
specific_index_count/Proteus_mirabilis/index.done stats/specific_kmer_count/Proteus_mirabilis.stats: global_index_count/index.done
run/specific_index_presence/Proteus_mirabilis/index.done run/stats/specific_kmer_presence/Proteus_mirabilis.stats: run/global_index_presence/index.done
run/specific_index_count/Proteus_mirabilis/index.done run/stats/specific_kmer_count/Proteus_mirabilis.stats: run/global_index_count/index.done
# Wolbachia_endosymbiont
specific_index_presence/Wolbachia_endosymbiont/index.done stats/specific_kmer_presence/Wolbachia_endosymbiont.stats: global_index_presence/index.done
specific_index_count/Wolbachia_endosymbiont/index.done stats/specific_kmer_count/Wolbachia_endosymbiont.stats: global_index_count/index.done
run/specific_index_presence/Wolbachia_endosymbiont/index.done run/stats/specific_kmer_presence/Wolbachia_endosymbiont.stats: run/global_index_presence/index.done
run/specific_index_count/Wolbachia_endosymbiont/index.done run/stats/specific_kmer_count/Wolbachia_endosymbiont.stats: run/global_index_count/index.done
# Yersinia_ruckeri
specific_index_presence/Yersinia_ruckeri/index.done stats/specific_kmer_presence/Yersinia_ruckeri.stats: global_index_presence/index.done
specific_index_count/Yersinia_ruckeri/index.done stats/specific_kmer_count/Yersinia_ruckeri.stats: global_index_count/index.done
run/specific_index_presence/Yersinia_ruckeri/index.done run/stats/specific_kmer_presence/Yersinia_ruckeri.stats: run/global_index_presence/index.done
run/specific_index_count/Yersinia_ruckeri/index.done run/stats/specific_kmer_count/Yersinia_ruckeri.stats: run/global_index_count/index.done
# Candidozyma_auris
specific_index_presence/Candidozyma_auris/index.done stats/specific_kmer_presence/Candidozyma_auris.stats: global_index_presence/index.done
specific_index_count/Candidozyma_auris/index.done stats/specific_kmer_count/Candidozyma_auris.stats: global_index_count/index.done
run/specific_index_presence/Candidozyma_auris/index.done run/stats/specific_kmer_presence/Candidozyma_auris.stats: run/global_index_presence/index.done
run/specific_index_count/Candidozyma_auris/index.done run/stats/specific_kmer_count/Candidozyma_auris.stats: run/global_index_count/index.done
QUERY_SPECIMENS := Escherichia_coli--K-12_MG1655 Saccharolobus_islandicus--M.16.4
# query: Escherichia_coli--K-12_MG1655
query_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz: genomes/GCF_000005845.2_ASM584v2_genomic.fna.gz
query_dense/Escherichia_coli--K-12_MG1655.fasta.gz stats/query_dense/Escherichia_coli--K-12_MG1655.stats: query_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz global_index_presence/index.done
query_sparse/Escherichia_coli--K-12_MG1655.fasta.gz stats/query_sparse/Escherichia_coli--K-12_MG1655.stats: query_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz global_index_presence_sparse/index.done
stats/verify_query/Escherichia_coli--K-12_MG1655.stats: query_dense/Escherichia_coli--K-12_MG1655.fasta.gz query_sparse/Escherichia_coli--K-12_MG1655.fasta.gz
run/query_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz: run/genomes/GCF_000005845.2_ASM584v2_genomic.fna.gz
run/query_presence_dense/Escherichia_coli--K-12_MG1655.fasta.gz run/stats/query_presence_dense/Escherichia_coli--K-12_MG1655.stats: run/query_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz run/global_index_presence_dense/index.done
run/query_presence_sparse/Escherichia_coli--K-12_MG1655.fasta.gz run/stats/query_presence_sparse/Escherichia_coli--K-12_MG1655.stats: run/query_data/Escherichia_coli/K-12_MG1655/reads_R1.fastq.gz run/global_index_presence/index.done
run/stats/verify_query/Escherichia_coli--K-12_MG1655.stats: run/query_presence_dense/Escherichia_coli--K-12_MG1655.fasta.gz run/query_presence_sparse/Escherichia_coli--K-12_MG1655.fasta.gz
# query: Saccharolobus_islandicus--M.16.4
query_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz: genomes/GCF_000022445.1_ASM2244v1_genomic.fna.gz
query_dense/Saccharolobus_islandicus--M.16.4.fasta.gz stats/query_dense/Saccharolobus_islandicus--M.16.4.stats: query_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz global_index_presence/index.done
query_sparse/Saccharolobus_islandicus--M.16.4.fasta.gz stats/query_sparse/Saccharolobus_islandicus--M.16.4.stats: query_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz global_index_presence_sparse/index.done
stats/verify_query/Saccharolobus_islandicus--M.16.4.stats: query_dense/Saccharolobus_islandicus--M.16.4.fasta.gz query_sparse/Saccharolobus_islandicus--M.16.4.fasta.gz
run/query_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz: run/genomes/GCF_000022445.1_ASM2244v1_genomic.fna.gz
run/query_presence_dense/Saccharolobus_islandicus--M.16.4.fasta.gz run/stats/query_presence_dense/Saccharolobus_islandicus--M.16.4.stats: run/query_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz run/global_index_presence_dense/index.done
run/query_presence_sparse/Saccharolobus_islandicus--M.16.4.fasta.gz run/stats/query_presence_sparse/Saccharolobus_islandicus--M.16.4.stats: run/query_data/Saccharolobus_islandicus/M.16.4/reads_R1.fastq.gz run/global_index_presence/index.done
run/stats/verify_query/Saccharolobus_islandicus--M.16.4.stats: run/query_presence_dense/Saccharolobus_islandicus--M.16.4.fasta.gz run/query_presence_sparse/Saccharolobus_islandicus--M.16.4.fasta.gz
+5 -2
View File
@@ -29,7 +29,10 @@ assemblies=(
GCF_000834255.1
)
mkdir -p genomes
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
GENOMES_DIR="${SCRIPT_DIR}/run/genomes"
mkdir -p "${GENOMES_DIR}"
for acc in "${assemblies[@]}"; do
echo "Downloading ${acc}"
@@ -41,7 +44,7 @@ for acc in "${assemblies[@]}"; do
unzip -q "${acc}.zip" -d "${acc}"
find "${acc}" -name "*.fna" |
while read file; do
obiconvert -Z ${file} >genomes/$(basename ${file}).gz
obiconvert -Z ${file} >"${GENOMES_DIR}/$(basename ${file}).gz"
done
rm -rf "${acc}" "${acc}.zip"
+4 -3
View File
@@ -12,11 +12,12 @@ set -euo pipefail
SPECIES="$1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
SOURCE="${SCRIPT_DIR}/global_index_count"
OUTPUT="${SCRIPT_DIR}/specific_index_count/${SPECIES}"
STATS_DIR="${SCRIPT_DIR}/stats/specific_kmer_count"
SOURCE="${RUN_DIR}/global_index_count"
OUTPUT="${RUN_DIR}/specific_index_count/${SPECIES}"
STATS_DIR="${RUN_DIR}/stats/specific_kmer_count"
STATS_FILE="${STATS_DIR}/${SPECIES}.stats"
mkdir -p "${STATS_DIR}"
+4 -3
View File
@@ -12,11 +12,12 @@ set -euo pipefail
SPECIES="$1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
SOURCE="${SCRIPT_DIR}/global_index_presence"
OUTPUT="${SCRIPT_DIR}/specific_index_presence/${SPECIES}"
STATS_DIR="${SCRIPT_DIR}/stats/specific_kmer_presence"
SOURCE="${RUN_DIR}/global_index_presence"
OUTPUT="${RUN_DIR}/specific_index_presence/${SPECIES}"
STATS_DIR="${RUN_DIR}/stats/specific_kmer_presence"
STATS_FILE="${STATS_DIR}/${SPECIES}.stats"
mkdir -p "${STATS_DIR}"
+4 -3
View File
@@ -8,14 +8,15 @@ set -euo pipefail
SPECIMEN="$1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
species="${SPECIMEN%%--*}"
strain="${SPECIMEN#*--}"
READS_DIR="${SCRIPT_DIR}/simulated_data/${species}/${strain}"
INDEX_PATH="${SCRIPT_DIR}/specimen_index_count/${SPECIMEN}"
STATS_DIR="${SCRIPT_DIR}/stats/indexing_count"
READS_DIR="${RUN_DIR}/simulated_data/${species}/${strain}"
INDEX_PATH="${RUN_DIR}/specimen_index_count/${SPECIMEN}"
STATS_DIR="${RUN_DIR}/stats/indexing_count"
STATS_FILE="${STATS_DIR}/${SPECIMEN}.stats"
mkdir -p "${STATS_DIR}"
+4 -3
View File
@@ -8,14 +8,15 @@ set -euo pipefail
SPECIMEN="$1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
species="${SPECIMEN%%--*}"
strain="${SPECIMEN#*--}"
READS_DIR="${SCRIPT_DIR}/simulated_data/${species}/${strain}"
INDEX_PATH="${SCRIPT_DIR}/specimen_index_presence/${SPECIMEN}"
STATS_DIR="${SCRIPT_DIR}/stats/indexing_presence"
READS_DIR="${RUN_DIR}/simulated_data/${species}/${strain}"
INDEX_PATH="${RUN_DIR}/specimen_index_presence/${SPECIMEN}"
STATS_DIR="${RUN_DIR}/stats/indexing_presence"
STATS_FILE="${STATS_DIR}/${SPECIMEN}.stats"
mkdir -p "${STATS_DIR}"
+25 -21
View File
@@ -13,6 +13,10 @@ STOP_WORDS = {'complete', 'chromosome', 'whole', 'sequence', 'genome',
'endosymbiont', 'of'}
STOP_PREFIXES = ('scaffold', 'contig', 'plasmid')
# All generated paths live under RUN/ (see Makefile) so the whole tree can be
# gitignored with a single entry.
RUN = 'run'
# Specimens used as read sources for the query benchmark (see
# DevDocMD/implementation/benchmark_query_testing.md): one common bacterium,
# one distant lineage (the only archaeon in SPECIES).
@@ -80,7 +84,7 @@ def main():
defn = first_definition(path)
sp, st = parse_organism(defn, gcf_id)
specimen = f'{sp}--{st}'
sim_dir = f'simulated_data/{sp}/{st}'
sim_dir = f'{RUN}/simulated_data/{sp}/{st}'
entries.append((specimen, sp, sim_dir, path))
if sp not in species_seen:
species_seen.append(sp)
@@ -91,13 +95,13 @@ def main():
for specimen, species, sim_dir, genome in entries:
reads = f'{sim_dir}/reads_R1.fastq.gz'
p_done = f'specimen_index_presence/{specimen}/index.done'
p_stats = f'stats/indexing_presence/{specimen}.stats'
c_done = f'specimen_index_count/{specimen}/index.done'
c_stats = f'stats/indexing_count/{specimen}.stats'
ref = f'reference_index/{specimen}.npz'
vp = f'stats/verify_presence/{specimen}.stats'
vc = f'stats/verify_count/{specimen}.stats'
p_done = f'{RUN}/specimen_index_presence/{specimen}/index.done'
p_stats = f'{RUN}/stats/indexing_presence/{specimen}.stats'
c_done = f'{RUN}/specimen_index_count/{specimen}/index.done'
c_stats = f'{RUN}/stats/indexing_count/{specimen}.stats'
ref = f'{RUN}/reference_index/{specimen}.npz'
vp = f'{RUN}/stats/verify_presence/{specimen}.stats'
vc = f'{RUN}/stats/verify_count/{specimen}.stats'
print()
print(f'# {specimen}')
@@ -110,13 +114,13 @@ def main():
print()
for sp in species_seen:
sp_done = f'specific_index_presence/{sp}/index.done'
sp_stats = f'stats/specific_kmer_presence/{sp}.stats'
sc_done = f'specific_index_count/{sp}/index.done'
sc_stats = f'stats/specific_kmer_count/{sp}.stats'
sp_done = f'{RUN}/specific_index_presence/{sp}/index.done'
sp_stats = f'{RUN}/stats/specific_kmer_presence/{sp}.stats'
sc_done = f'{RUN}/specific_index_count/{sp}/index.done'
sc_stats = f'{RUN}/stats/specific_kmer_count/{sp}.stats'
print(f'# {sp}')
print(f'{sp_done} {sp_stats}: global_index_presence/index.done')
print(f'{sc_done} {sc_stats}: global_index_count/index.done')
print(f'{sp_done} {sp_stats}: {RUN}/global_index_presence/index.done')
print(f'{sc_done} {sc_stats}: {RUN}/global_index_count/index.done')
print()
print('QUERY_SPECIMENS :=', ' '.join(QUERY_SPECIMENS))
@@ -126,17 +130,17 @@ def main():
_, species, sim_dir, genome = by_specimen[specimen]
query_dir = sim_dir.replace('simulated_data/', 'query_data/', 1)
reads = f'{query_dir}/reads_R1.fastq.gz'
dense_out = f'query_dense/{specimen}.fasta.gz'
dense_stat = f'stats/query_dense/{specimen}.stats'
sparse_out = f'query_sparse/{specimen}.fasta.gz'
sparse_stat = f'stats/query_sparse/{specimen}.stats'
vq_stat = f'stats/verify_query/{specimen}.stats'
dense_out = f'{RUN}/query_presence_dense/{specimen}.fasta.gz'
dense_stat = f'{RUN}/stats/query_presence_dense/{specimen}.stats'
sparse_out = f'{RUN}/query_presence_sparse/{specimen}.fasta.gz'
sparse_stat = f'{RUN}/stats/query_presence_sparse/{specimen}.stats'
vq_stat = f'{RUN}/stats/verify_query/{specimen}.stats'
print()
print(f'# query: {specimen}')
print(f'{reads}: {genome}')
print(f'{dense_out} {dense_stat}: {reads} global_index_presence/index.done')
print(f'{sparse_out} {sparse_stat}: {reads} global_index_presence_sparse/index.done')
print(f'{dense_out} {dense_stat}: {reads} {RUN}/global_index_presence_dense/index.done')
print(f'{sparse_out} {sparse_stat}: {reads} {RUN}/global_index_presence/index.done')
print(f'{vq_stat}: {dense_out} {sparse_out}')
+4 -3
View File
@@ -2,10 +2,11 @@
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
IDX_DIR="${SCRIPT_DIR}/specimen_index_count"
OUTPUT="${SCRIPT_DIR}/global_index_count"
STATS_DIR="${SCRIPT_DIR}/stats/merge_count"
IDX_DIR="${RUN_DIR}/specimen_index_count"
OUTPUT="${RUN_DIR}/global_index_count"
STATS_DIR="${RUN_DIR}/stats/merge_count"
mkdir -p "${STATS_DIR}"
+4 -3
View File
@@ -2,10 +2,11 @@
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
IDX_DIR="${SCRIPT_DIR}/specimen_index_presence"
OUTPUT="${SCRIPT_DIR}/global_index_presence"
STATS_DIR="${SCRIPT_DIR}/stats/merge_presence"
IDX_DIR="${RUN_DIR}/specimen_index_presence"
OUTPUT="${RUN_DIR}/global_index_presence"
STATS_DIR="${RUN_DIR}/stats/merge_presence"
mkdir -p "${STATS_DIR}"
+4 -3
View File
@@ -30,10 +30,11 @@ set -euo pipefail
KIND="$1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
SOURCE="${SCRIPT_DIR}/global_index_${KIND}"
OUTPUT="${SCRIPT_DIR}/global_index_${KIND}_dense"
STATS_DIR="${SCRIPT_DIR}/stats/pack_dense_${KIND}"
SOURCE="${RUN_DIR}/global_index_${KIND}"
OUTPUT="${RUN_DIR}/global_index_${KIND}_dense"
STATS_DIR="${RUN_DIR}/stats/pack_dense_${KIND}"
STATS_FILE="${STATS_DIR}/current.stats"
mkdir -p "${STATS_DIR}"
+6 -5
View File
@@ -14,6 +14,7 @@ KIND="$1"
MODE="$2"
SPECIMEN="$3"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
case "${KIND}" in
@@ -22,17 +23,17 @@ case "${KIND}" in
esac
case "${MODE}" in
sparse) INDEX="${SCRIPT_DIR}/global_index_${KIND}" ;;
dense) INDEX="${SCRIPT_DIR}/global_index_${KIND}_dense" ;;
sparse) INDEX="${RUN_DIR}/global_index_${KIND}" ;;
dense) INDEX="${RUN_DIR}/global_index_${KIND}_dense" ;;
*) echo "ERROR: unknown mode '${MODE}' (expected dense|sparse)" >&2; exit 1 ;;
esac
species="${SPECIMEN%%--*}"
strain="${SPECIMEN#*--}"
READS_DIR="${SCRIPT_DIR}/query_data/${species}/${strain}"
OUT_DIR="${SCRIPT_DIR}/query_${KIND}_${MODE}"
STATS_DIR="${SCRIPT_DIR}/stats/query_${KIND}_${MODE}"
READS_DIR="${RUN_DIR}/query_data/${species}/${strain}"
OUT_DIR="${RUN_DIR}/query_${KIND}_${MODE}"
STATS_DIR="${RUN_DIR}/stats/query_${KIND}_${MODE}"
OUT_FILE="${OUT_DIR}/${SPECIMEN}.fasta.gz"
STATS_FILE="${STATS_DIR}/${SPECIMEN}.stats"
+2 -1
View File
@@ -4,8 +4,9 @@
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
RUN_DIR="${SCRIPT_DIR}/run"
for genome_file in "${SCRIPT_DIR}"/genomes/*.fna.gz; do
for genome_file in "${RUN_DIR}"/genomes/*.fna.gz; do
out_dir=$("${SCRIPT_DIR}/../.venv/bin/python3" "${SCRIPT_DIR}/make_deps.py" \
--dir-for "${genome_file}")
bash "${SCRIPT_DIR}/simulate_one.sh" "${genome_file}" "${out_dir}"
-21
View File
@@ -1,21 +0,0 @@
genome,Candidozyma_auris--GCF_003013715.1_ASM301371v2,Acidobacterium_capsulatum--ATCC_51196,Bacillus_subtilis--168,Escherichia_coli--CFT073,Escherichia_coli--EDL933,Escherichia_coli--K-12_MG1655,Escherichia_coli--K-12_W3110,Klebsiella_pneumoniae--ATCC_13883,Klebsiella_pneumoniae--HS11286,Klebsiella_pneumoniae--MGH_78578,Opitutus_terrae--PB90-1,Proteus_mirabilis--HI4320,Saccharolobus_islandicus--M.16.4,Salmonella_enterica--AKU_12601,Salmonella_enterica--CT18,Salmonella_enterica--LT2,Salmonella_enterica--P125109,Shouchella_clausii--KSM-K16,Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1,Yersinia_ruckeri--YRB
Candidozyma_auris--GCF_003013715.1_ASM301371v2,0.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000
Acidobacterium_capsulatum--ATCC_51196,1.000000,0.000000,0.999981,0.999990,0.999989,0.999987,0.999987,0.999990,0.999988,0.999988,0.999994,0.999989,1.000000,0.999988,0.999987,0.999987,0.999988,0.999989,0.999991,0.999987
Bacillus_subtilis--168,1.000000,0.999981,0.000000,0.999990,0.999989,0.999989,0.999989,0.999989,0.999988,0.999986,0.999995,0.999985,0.999999,0.999988,0.999987,0.999989,0.999988,0.999778,0.999993,0.999987
Escherichia_coli--CFT073,1.000000,0.999990,0.999990,0.000000,0.825741,0.807495,0.807218,0.991156,0.996855,0.997849,0.999996,0.999633,1.000000,0.993885,0.996736,0.994148,0.993821,0.999991,0.999984,0.999291
Escherichia_coli--EDL933,1.000000,0.999989,0.999989,0.825741,0.000000,0.735107,0.734775,0.996126,0.998058,0.997908,0.999997,0.999640,1.000000,0.993993,0.997126,0.994390,0.994059,0.999991,0.999986,0.999292
Escherichia_coli--K-12_MG1655,1.000000,0.999987,0.999989,0.807495,0.735107,0.000000,0.382567,0.996190,0.997747,0.997455,0.999996,0.999604,1.000000,0.993444,0.996645,0.993773,0.993431,0.999989,0.999984,0.999174
Escherichia_coli--K-12_W3110,1.000000,0.999987,0.999989,0.807218,0.734775,0.382567,0.000000,0.996220,0.997761,0.997467,0.999995,0.999604,1.000000,0.993445,0.996669,0.993769,0.993443,0.999990,0.999985,0.999165
Klebsiella_pneumoniae--ATCC_13883,1.000000,0.999990,0.999989,0.991156,0.996126,0.996190,0.996220,0.000000,0.845220,0.840545,0.999997,0.999648,1.000000,0.996177,0.998128,0.996268,0.996052,0.999990,0.999987,0.999325
Klebsiella_pneumoniae--HS11286,1.000000,0.999988,0.999988,0.996855,0.998058,0.997747,0.997761,0.845220,0.000000,0.906475,0.999996,0.999683,1.000000,0.997724,0.995697,0.997776,0.997769,0.999989,0.999979,0.999463
Klebsiella_pneumoniae--MGH_78578,1.000000,0.999988,0.999986,0.997849,0.997908,0.997455,0.997467,0.840545,0.906475,0.000000,0.999996,0.999704,1.000000,0.997928,0.995054,0.997844,0.997868,0.999990,0.999980,0.999479
Opitutus_terrae--PB90-1,1.000000,0.999994,0.999995,0.999996,0.999997,0.999996,0.999995,0.999997,0.999996,0.999996,0.000000,0.999997,0.999998,0.999996,0.999996,0.999996,0.999995,0.999997,0.999993,0.999996
Proteus_mirabilis--HI4320,1.000000,0.999989,0.999985,0.999633,0.999640,0.999604,0.999604,0.999648,0.999683,0.999704,0.999997,0.000000,1.000000,0.999604,0.999699,0.999622,0.999613,0.999987,0.999983,0.999505
Saccharolobus_islandicus--M.16.4,1.000000,1.000000,0.999999,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,0.999998,1.000000,0.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000,1.000000
Salmonella_enterica--AKU_12601,1.000000,0.999988,0.999988,0.993885,0.993993,0.993444,0.993445,0.996177,0.997724,0.997928,0.999996,0.999604,1.000000,0.000000,0.869238,0.682277,0.663383,0.999990,0.999985,0.999260
Salmonella_enterica--CT18,1.000000,0.999987,0.999987,0.996736,0.997126,0.996645,0.996669,0.998128,0.995697,0.995054,0.999996,0.999699,1.000000,0.869238,0.000000,0.890872,0.886148,0.999988,0.999976,0.999524
Salmonella_enterica--LT2,1.000000,0.999987,0.999989,0.994148,0.994390,0.993773,0.993769,0.996268,0.997776,0.997844,0.999996,0.999622,1.000000,0.682277,0.890872,0.000000,0.622606,0.999989,0.999985,0.999296
Salmonella_enterica--P125109,1.000000,0.999988,0.999988,0.993821,0.994059,0.993431,0.993443,0.996052,0.997769,0.997868,0.999995,0.999613,1.000000,0.663383,0.886148,0.622606,0.000000,0.999988,0.999983,0.999270
Shouchella_clausii--KSM-K16,1.000000,0.999989,0.999778,0.999991,0.999991,0.999989,0.999990,0.999990,0.999989,0.999990,0.999997,0.999987,1.000000,0.999990,0.999988,0.999989,0.999988,0.000000,0.999991,0.999988
Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1,1.000000,0.999991,0.999993,0.999984,0.999986,0.999984,0.999985,0.999987,0.999979,0.999980,0.999993,0.999983,1.000000,0.999985,0.999976,0.999985,0.999983,0.999991,0.000000,0.999983
Yersinia_ruckeri--YRB,1.000000,0.999987,0.999987,0.999291,0.999292,0.999174,0.999165,0.999325,0.999463,0.999479,0.999996,0.999505,1.000000,0.999260,0.999524,0.999296,0.999270,0.999988,0.999983,0.000000
1 genome Candidozyma_auris--GCF_003013715.1_ASM301371v2 Acidobacterium_capsulatum--ATCC_51196 Bacillus_subtilis--168 Escherichia_coli--CFT073 Escherichia_coli--EDL933 Escherichia_coli--K-12_MG1655 Escherichia_coli--K-12_W3110 Klebsiella_pneumoniae--ATCC_13883 Klebsiella_pneumoniae--HS11286 Klebsiella_pneumoniae--MGH_78578 Opitutus_terrae--PB90-1 Proteus_mirabilis--HI4320 Saccharolobus_islandicus--M.16.4 Salmonella_enterica--AKU_12601 Salmonella_enterica--CT18 Salmonella_enterica--LT2 Salmonella_enterica--P125109 Shouchella_clausii--KSM-K16 Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1 Yersinia_ruckeri--YRB
2 Candidozyma_auris--GCF_003013715.1_ASM301371v2 0.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000
3 Acidobacterium_capsulatum--ATCC_51196 1.000000 0.000000 0.999981 0.999990 0.999989 0.999987 0.999987 0.999990 0.999988 0.999988 0.999994 0.999989 1.000000 0.999988 0.999987 0.999987 0.999988 0.999989 0.999991 0.999987
4 Bacillus_subtilis--168 1.000000 0.999981 0.000000 0.999990 0.999989 0.999989 0.999989 0.999989 0.999988 0.999986 0.999995 0.999985 0.999999 0.999988 0.999987 0.999989 0.999988 0.999778 0.999993 0.999987
5 Escherichia_coli--CFT073 1.000000 0.999990 0.999990 0.000000 0.825741 0.807495 0.807218 0.991156 0.996855 0.997849 0.999996 0.999633 1.000000 0.993885 0.996736 0.994148 0.993821 0.999991 0.999984 0.999291
6 Escherichia_coli--EDL933 1.000000 0.999989 0.999989 0.825741 0.000000 0.735107 0.734775 0.996126 0.998058 0.997908 0.999997 0.999640 1.000000 0.993993 0.997126 0.994390 0.994059 0.999991 0.999986 0.999292
7 Escherichia_coli--K-12_MG1655 1.000000 0.999987 0.999989 0.807495 0.735107 0.000000 0.382567 0.996190 0.997747 0.997455 0.999996 0.999604 1.000000 0.993444 0.996645 0.993773 0.993431 0.999989 0.999984 0.999174
8 Escherichia_coli--K-12_W3110 1.000000 0.999987 0.999989 0.807218 0.734775 0.382567 0.000000 0.996220 0.997761 0.997467 0.999995 0.999604 1.000000 0.993445 0.996669 0.993769 0.993443 0.999990 0.999985 0.999165
9 Klebsiella_pneumoniae--ATCC_13883 1.000000 0.999990 0.999989 0.991156 0.996126 0.996190 0.996220 0.000000 0.845220 0.840545 0.999997 0.999648 1.000000 0.996177 0.998128 0.996268 0.996052 0.999990 0.999987 0.999325
10 Klebsiella_pneumoniae--HS11286 1.000000 0.999988 0.999988 0.996855 0.998058 0.997747 0.997761 0.845220 0.000000 0.906475 0.999996 0.999683 1.000000 0.997724 0.995697 0.997776 0.997769 0.999989 0.999979 0.999463
11 Klebsiella_pneumoniae--MGH_78578 1.000000 0.999988 0.999986 0.997849 0.997908 0.997455 0.997467 0.840545 0.906475 0.000000 0.999996 0.999704 1.000000 0.997928 0.995054 0.997844 0.997868 0.999990 0.999980 0.999479
12 Opitutus_terrae--PB90-1 1.000000 0.999994 0.999995 0.999996 0.999997 0.999996 0.999995 0.999997 0.999996 0.999996 0.000000 0.999997 0.999998 0.999996 0.999996 0.999996 0.999995 0.999997 0.999993 0.999996
13 Proteus_mirabilis--HI4320 1.000000 0.999989 0.999985 0.999633 0.999640 0.999604 0.999604 0.999648 0.999683 0.999704 0.999997 0.000000 1.000000 0.999604 0.999699 0.999622 0.999613 0.999987 0.999983 0.999505
14 Saccharolobus_islandicus--M.16.4 1.000000 1.000000 0.999999 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 0.999998 1.000000 0.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000
15 Salmonella_enterica--AKU_12601 1.000000 0.999988 0.999988 0.993885 0.993993 0.993444 0.993445 0.996177 0.997724 0.997928 0.999996 0.999604 1.000000 0.000000 0.869238 0.682277 0.663383 0.999990 0.999985 0.999260
16 Salmonella_enterica--CT18 1.000000 0.999987 0.999987 0.996736 0.997126 0.996645 0.996669 0.998128 0.995697 0.995054 0.999996 0.999699 1.000000 0.869238 0.000000 0.890872 0.886148 0.999988 0.999976 0.999524
17 Salmonella_enterica--LT2 1.000000 0.999987 0.999989 0.994148 0.994390 0.993773 0.993769 0.996268 0.997776 0.997844 0.999996 0.999622 1.000000 0.682277 0.890872 0.000000 0.622606 0.999989 0.999985 0.999296
18 Salmonella_enterica--P125109 1.000000 0.999988 0.999988 0.993821 0.994059 0.993431 0.993443 0.996052 0.997769 0.997868 0.999995 0.999613 1.000000 0.663383 0.886148 0.622606 0.000000 0.999988 0.999983 0.999270
19 Shouchella_clausii--KSM-K16 1.000000 0.999989 0.999778 0.999991 0.999991 0.999989 0.999990 0.999990 0.999989 0.999990 0.999997 0.999987 1.000000 0.999990 0.999988 0.999989 0.999988 0.000000 0.999991 0.999988
20 Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1 1.000000 0.999991 0.999993 0.999984 0.999986 0.999984 0.999985 0.999987 0.999979 0.999980 0.999993 0.999983 1.000000 0.999985 0.999976 0.999985 0.999983 0.999991 0.000000 0.999983
21 Yersinia_ruckeri--YRB 1.000000 0.999987 0.999987 0.999291 0.999292 0.999174 0.999165 0.999325 0.999463 0.999479 0.999996 0.999505 1.000000 0.999260 0.999524 0.999296 0.999270 0.999988 0.999983 0.000000
-1
View File
@@ -1 +0,0 @@
(((((((((((Candidozyma_auris--GCF_003013715.1_ASM301371v2:0.5000001881725941,Saccharolobus_islandicus--M.16.4:0.4999993211600824):0.0000023411501775538747,Opitutus_terrae--PB90-1:0.499997075187947):0.0000029791191795691675,(Acidobacterium_capsulatum--ATCC_51196:0.49999227771334689,(Bacillus_subtilis--168:0.49988797935621456,Shouchella_clausii--KSM-K16:0.49988984146059159):0.0001037210285571577):0.0000023959836053522034):0.0000034093646568700288,Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1:0.4999920159222422):0.000199555100890203,Proteus_mirabilis--HI4320:0.49979129185300427):0.00010103619067070024,Yersinia_ruckeri--YRB:0.4996806650749249):0.0013719139155004,(Klebsiella_pneumoniae--HS11286:0.43798845051648258,(Klebsiella_pneumoniae--ATCC_13883:0.41780293826821265,Klebsiella_pneumoniae--MGH_78578:0.42274184870836559):0.017586732339732737):0.0604124197073832):0.0006482538063555254,(Salmonella_enterica--CT18:0.43952894448143017,(Salmonella_enterica--AKU_12601:0.3357977326267918,(Salmonella_enterica--LT2:0.31203395843666389,Salmonella_enterica--P125109:0.31057217324861216):0.025729515856701136):0.10292985918524672):0.05825411485542886):0.08937928015651564,Escherichia_coli--CFT073:0.40806501650701029):0.0410131211869626,Escherichia_coli--EDL933:0.3681464750911808):0.1755112579711463,Escherichia_coli--K-12_MG1655:0.19129818036662728,Escherichia_coli--K-12_W3110:0.19126872019906239);
-21
View File
@@ -1,21 +0,0 @@
genome,Candidozyma_auris--GCF_003013715.1_ASM301371v2,Acidobacterium_capsulatum--ATCC_51196,Bacillus_subtilis--168,Escherichia_coli--CFT073,Escherichia_coli--EDL933,Escherichia_coli--K-12_MG1655,Escherichia_coli--K-12_W3110,Klebsiella_pneumoniae--ATCC_13883,Klebsiella_pneumoniae--HS11286,Klebsiella_pneumoniae--MGH_78578,Opitutus_terrae--PB90-1,Proteus_mirabilis--HI4320,Saccharolobus_islandicus--M.16.4,Salmonella_enterica--AKU_12601,Salmonella_enterica--CT18,Salmonella_enterica--LT2,Salmonella_enterica--P125109,Shouchella_clausii--KSM-K16,Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1,Yersinia_ruckeri--YRB
Candidozyma_auris--GCF_003013715.1_ASM301371v2,0,0,0,0,0,0,0,0,0,0,0,0,8,0,1,0,0,0,0,3
Acidobacterium_capsulatum--ATCC_51196,0,0,203,119,128,141,140,116,109,111,78,112,0,136,109,147,134,117,55,129
Bacillus_subtilis--168,0,203,0,124,132,128,123,133,109,130,66,158,6,131,112,124,135,2393,46,124
Escherichia_coli--CFT073,0,119,124,0,1966777,1998059,1999094,117743,32029,22312,63,4225,0,74946,31918,73311,76585,113,128,7854
Escherichia_coli--EDL933,0,128,132,1966777,0,2627885,2628700,52488,20134,22064,48,4202,0,74655,28602,71244,74665,112,108,7963
Escherichia_coli--K-12_MG1655,0,141,128,1998059,2627885,0,4452541,48302,21382,24602,47,4277,0,75729,30449,73622,76778,119,111,8566
Escherichia_coli--K-12_W3110,0,140,123,1999094,2628700,4452541,0,47894,21226,24470,68,4278,0,75658,30207,73614,76583,112,108,8660
Klebsiella_pneumoniae--ATCC_13883,0,116,133,117743,52488,48302,47894,0,1416091,1477759,42,4172,0,48296,18988,48144,50416,120,106,7712
Klebsiella_pneumoniae--HS11286,0,109,109,32029,20134,21382,21226,1416091,0,644063,42,2738,0,21498,29758,21606,21376,99,102,4417
Klebsiella_pneumoniae--MGH_78578,0,111,130,22312,22064,24602,24470,1477759,644063,0,42,2614,0,19948,35067,21330,20813,97,102,4374
Opitutus_terrae--PB90-1,0,78,66,63,48,47,68,42,42,42,0,43,18,57,42,53,66,39,58,43
Proteus_mirabilis--HI4320,0,112,158,4225,4202,4277,4278,4172,2738,2614,43,0,0,4254,2481,4166,4215,131,103,4704
Saccharolobus_islandicus--M.16.4,8,0,6,0,0,0,0,0,0,0,18,0,0,0,0,0,0,0,0,0
Salmonella_enterica--AKU_12601,0,136,131,74946,74655,75729,75658,48296,21498,19948,57,4254,0,0,1047731,2857146,2951421,117,108,7643
Salmonella_enterica--CT18,1,109,112,31918,28602,30449,30207,18988,29758,35067,42,2481,0,1047731,0,917948,940297,106,106,3716
Salmonella_enterica--LT2,0,147,124,73311,71244,73622,73614,48144,21606,21330,53,4166,0,2857146,917948,0,3284800,122,108,7460
Salmonella_enterica--P125109,0,134,135,76585,74665,76778,76583,50416,21376,20813,66,4215,0,2951421,940297,3284800,0,134,124,7645
Shouchella_clausii--KSM-K16,0,117,2393,113,112,119,112,120,99,97,39,131,0,117,106,122,134,0,58,124
Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1,0,55,46,128,108,111,108,106,102,102,58,103,0,108,106,108,124,58,0,96
Yersinia_ruckeri--YRB,3,129,124,7854,7963,8566,8660,7712,4417,4374,43,4704,0,7643,3716,7460,7645,124,96,0
1 genome Candidozyma_auris--GCF_003013715.1_ASM301371v2 Acidobacterium_capsulatum--ATCC_51196 Bacillus_subtilis--168 Escherichia_coli--CFT073 Escherichia_coli--EDL933 Escherichia_coli--K-12_MG1655 Escherichia_coli--K-12_W3110 Klebsiella_pneumoniae--ATCC_13883 Klebsiella_pneumoniae--HS11286 Klebsiella_pneumoniae--MGH_78578 Opitutus_terrae--PB90-1 Proteus_mirabilis--HI4320 Saccharolobus_islandicus--M.16.4 Salmonella_enterica--AKU_12601 Salmonella_enterica--CT18 Salmonella_enterica--LT2 Salmonella_enterica--P125109 Shouchella_clausii--KSM-K16 Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1 Yersinia_ruckeri--YRB
2 Candidozyma_auris--GCF_003013715.1_ASM301371v2 0 0 0 0 0 0 0 0 0 0 0 0 8 0 1 0 0 0 0 3
3 Acidobacterium_capsulatum--ATCC_51196 0 0 203 119 128 141 140 116 109 111 78 112 0 136 109 147 134 117 55 129
4 Bacillus_subtilis--168 0 203 0 124 132 128 123 133 109 130 66 158 6 131 112 124 135 2393 46 124
5 Escherichia_coli--CFT073 0 119 124 0 1966777 1998059 1999094 117743 32029 22312 63 4225 0 74946 31918 73311 76585 113 128 7854
6 Escherichia_coli--EDL933 0 128 132 1966777 0 2627885 2628700 52488 20134 22064 48 4202 0 74655 28602 71244 74665 112 108 7963
7 Escherichia_coli--K-12_MG1655 0 141 128 1998059 2627885 0 4452541 48302 21382 24602 47 4277 0 75729 30449 73622 76778 119 111 8566
8 Escherichia_coli--K-12_W3110 0 140 123 1999094 2628700 4452541 0 47894 21226 24470 68 4278 0 75658 30207 73614 76583 112 108 8660
9 Klebsiella_pneumoniae--ATCC_13883 0 116 133 117743 52488 48302 47894 0 1416091 1477759 42 4172 0 48296 18988 48144 50416 120 106 7712
10 Klebsiella_pneumoniae--HS11286 0 109 109 32029 20134 21382 21226 1416091 0 644063 42 2738 0 21498 29758 21606 21376 99 102 4417
11 Klebsiella_pneumoniae--MGH_78578 0 111 130 22312 22064 24602 24470 1477759 644063 0 42 2614 0 19948 35067 21330 20813 97 102 4374
12 Opitutus_terrae--PB90-1 0 78 66 63 48 47 68 42 42 42 0 43 18 57 42 53 66 39 58 43
13 Proteus_mirabilis--HI4320 0 112 158 4225 4202 4277 4278 4172 2738 2614 43 0 0 4254 2481 4166 4215 131 103 4704
14 Saccharolobus_islandicus--M.16.4 8 0 6 0 0 0 0 0 0 0 18 0 0 0 0 0 0 0 0 0
15 Salmonella_enterica--AKU_12601 0 136 131 74946 74655 75729 75658 48296 21498 19948 57 4254 0 0 1047731 2857146 2951421 117 108 7643
16 Salmonella_enterica--CT18 1 109 112 31918 28602 30449 30207 18988 29758 35067 42 2481 0 1047731 0 917948 940297 106 106 3716
17 Salmonella_enterica--LT2 0 147 124 73311 71244 73622 73614 48144 21606 21330 53 4166 0 2857146 917948 0 3284800 122 108 7460
18 Salmonella_enterica--P125109 0 134 135 76585 74665 76778 76583 50416 21376 20813 66 4215 0 2951421 940297 3284800 0 134 124 7645
19 Shouchella_clausii--KSM-K16 0 117 2393 113 112 119 112 120 99 97 39 131 0 117 106 122 134 0 58 124
20 Wolbachia_endosymbiont--GCF_000306885.1_ASM30688v1 0 55 46 128 108 111 108 106 102 102 58 103 0 108 106 108 124 58 0 96
21 Yersinia_ruckeri--YRB 3 129 124 7854 7963 8566 8660 7712 4417 4374 43 4704 0 7643 3716 7460 7645 124 96 0

Some files were not shown because too many files have changed in this diff Show More