Merge branch 'release/v5.2.0'

ACEnglish · Feb 16, 2025 · 7ff8091 · 7ff8091
2 parents 14fa7b6 + 694a781
commit 7ff8091
Show file tree

Hide file tree

Showing 277 changed files with 424 additions and 28,032 deletions.
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 [![pylint](imgs/pylint.svg)](https://github.com/acenglish/truvari/actions/workflows/pylint.yml)
 [![FuncTests](https://github.com/acenglish/truvari/actions/workflows/func_tests.yml/badge.svg?branch=develop&event=push)](https://github.com/acenglish/truvari/actions/workflows/func_tests.yml)
 [![coverage](imgs/coverage.svg)](https://github.com/acenglish/truvari/actions/workflows/func_tests.yml)
-[![develop](https://img.shields.io/github/commits-since/acenglish/truvari/v5.0.0)](https://github.com/ACEnglish/truvari/compare/v5.0.0...develop)
+[![develop](https://img.shields.io/github/commits-since/acenglish/truvari/v5.1.1)](https://github.com/ACEnglish/truvari/compare/v5.1.1...develop)
 [![Downloads](https://static.pepy.tech/badge/truvari)](https://pepy.tech/project/truvari)
 
 ![Logo](https://raw.githubusercontent.com/ACEnglish/truvari/develop/imgs/BoxScale1_DarkBG.png)  
@@ -26,12 +26,12 @@ Each sub-command contains help documentation. Start with `truvari -h` to see ava
 
 The current most common Truvari use case is for structural variation benchmarking:
 ```
-  truvari bench -b base.vcf.gz -c comp.vcf.gz -o output_dir/
+  truvari bench -b base.vcf.gz -c comp.vcf.gz -f reference.fa -o output_dir/
 ```
 
 Find more matches by harmonizing phased varians using refine:
 ```
-   truvari refine -R -U -r reference.fa --regions output_dir/candidate.refine.bed output_dir/
+   truvari refine output_dir/
 ```
 
 Use Truvari's comparison engine to consolidate redundant variants in a merged multi-sample VCF:

diff --git a/imgs/coverage.svg b/imgs/coverage.svg
diff --git a/repo_utils/answer_key/bench/bench12_gtcomp/fn.vcf.gz b/repo_utils/answer_key/bench/bench12_gtcomp/fn.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench12_gtcomp/fn.vcf.gz.tbi b/repo_utils/answer_key/bench/bench12_gtcomp/fn.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench12_gtcomp/fp.vcf.gz b/repo_utils/answer_key/bench/bench12_gtcomp/fp.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench12_gtcomp/fp.vcf.gz.tbi b/repo_utils/answer_key/bench/bench12_gtcomp/fp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_bnd/fn.vcf.gz b/repo_utils/answer_key/bench/bench_bnd/fn.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/tp-base.vcf.gz b/repo_utils/answer_key/bench/bench_bnd_decomp/tp-base.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/tp-base.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd_decomp/tp-base.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_gtcomp_edgecase1/fn.vcf.gz b/repo_utils/answer_key/bench/bench_gtcomp_edgecase1/fn.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_gtcomp_edgecase1/fn.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_gtcomp_edgecase1/fn.vcf.gz.tbi
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine.base.vcf.gz b/repo_utils/answer_key/ga4gh/ga4gh_withrefine.base.vcf.gz
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine.base.vcf.gz.tbi b/repo_utils/answer_key/ga4gh/ga4gh_withrefine.base.vcf.gz.tbi
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine.comp.vcf.gz b/repo_utils/answer_key/ga4gh/ga4gh_withrefine.comp.vcf.gz
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine.comp.vcf.gz.tbi b/repo_utils/answer_key/ga4gh/ga4gh_withrefine.comp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.base.vcf.gz b/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.base.vcf.gz
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.base.vcf.gz.tbi b/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.base.vcf.gz.tbi
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.comp.vcf.gz b/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.comp.vcf.gz
diff --git a/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.comp.vcf.gz.tbi b/repo_utils/answer_key/ga4gh/ga4gh_withrefine_orig.comp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/help.txt b/repo_utils/answer_key/help.txt
@@ -1,6 +1,6 @@
 usage: truvari [-h] CMD ...
 
-Truvari v5.1.1 Structural Variant Benchmarking and Annotation
+Truvari v5.2.0 Structural Variant Benchmarking and Annotation
 
 Available commands:
     bench         Performance metrics from comparison of two VCFs

diff --git a/repo_utils/answer_key/refine/refine_output_one/log.txt b/repo_utils/answer_key/refine/refine_output_one/log.txt
@@ -1,6 +1,6 @@
-2025-02-02 06:13:45,675 [INFO] Truvari v5.0.1.dev0+aef4e1a.uc
-2025-02-02 06:13:45,675 [INFO] Command /data/truvari/__main__.py bench -b repo_utils/test_files/refine_data/hg002_base.vcf.gz -c repo_utils/test_files/refine_data/hg002_comp.vcf.gz --includebed repo_utils/test_files/refine_data/h1_hc_tr_hg002.bed -s 5 -o test_results/refine_output_one
-2025-02-02 06:13:45,676 [INFO] Params:
+2025-02-16 01:48:20,256 [INFO] Truvari v5.1.1
+2025-02-16 01:48:20,257 [INFO] Command /data/truvari/__main__.py bench -b repo_utils/test_files/refine_data/hg002_base.vcf.gz -c repo_utils/test_files/refine_data/hg002_comp.vcf.gz --includebed repo_utils/test_files/refine_data/h1_hc_tr_hg002.bed -s 5 -o test_results/refine_output_one
+2025-02-16 01:48:20,258 [INFO] Params:
 {
     "base": "/data/repo_utils/test_files/refine_data/hg002_base.vcf.gz",
     "comp": "/data/repo_utils/test_files/refine_data/hg002_comp.vcf.gz",
@@ -36,10 +36,10 @@
     "skip_gt": false,
     "max_resolve": 25000
 }
-2025-02-02 06:13:45,720 [INFO] Including 225 bed regions
-2025-02-02 06:13:49,217 [INFO] Zipped 7157 variants Counter({'comp': 5302, 'base': 1855})
-2025-02-02 06:13:49,218 [INFO] 211 chunks of 7157 variants Counter({'__filtered': 6137, 'base': 569, 'comp': 451})
-2025-02-02 06:13:49,324 [INFO] Stats: {
+2025-02-16 01:48:20,308 [INFO] Including 225 bed regions
+2025-02-16 01:48:24,069 [INFO] Zipped 7157 variants Counter({'comp': 5302, 'base': 1855})
+2025-02-16 01:48:24,070 [INFO] 211 chunks of 7157 variants Counter({'__filtered': 6137, 'base': 569, 'comp': 451})
+2025-02-16 01:48:24,192 [INFO] Stats: {
     "TP-base": 387,
     "TP-comp": 387,
     "FP": 64,
@@ -71,4 +71,4 @@
         }
     }
 }
-2025-02-02 06:13:49,324 [INFO] Finished bench
+2025-02-16 01:48:24,193 [INFO] Finished bench
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab.output.vcf.gz b/repo_utils/answer_key/refine/refine_output_one/phab.output.vcf.gz
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab.output.vcf.gz.tbi b/repo_utils/answer_key/refine/refine_output_one/phab.output.vcf.gz.tbi
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/candidate.refine.bed b/repo_utils/answer_key/refine/refine_output_one/phab_bench/candidate.refine.bed
@@ -1,5 +1,5 @@
 chr20	5040466	5040487
-chr20	5041931	5042443
+chr20	5041952	5042292
 chr20	16257844	16259455
 chr20	32723034	32723055
 chr20	51953809	51953830
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/fp.vcf.gz b/repo_utils/answer_key/refine/refine_output_one/phab_bench/fp.vcf.gz
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/fp.vcf.gz.tbi b/repo_utils/answer_key/refine/refine_output_one/phab_bench/fp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/params.json b/repo_utils/answer_key/refine/refine_output_one/phab_bench/params.json
@@ -1 +1 @@
-{"base": "test_results/refine_output_one/phab.output.vcf.gz", "comp": "test_results/refine_output_one/phab.output.vcf.gz", "output": "test_results/refine_output_one/phab_bench", "includebed": "/tmp/xn9atc8u.bed", "extend": 0, "debug": false, "reference": null, "refdist": 500, "pctseq": 0.7, "pctsize": 0.7, "pctovl": 0.0, "typeignore": false, "no_roll": true, "chunksize": 1000, "bSample": "syndip", "cSample": "p:HG002", "dup_to_ins": false, "bnddist": 100, "sizemin": 5, "sizefilt": 5, "sizemax": -1, "passonly": false, "no_ref": "a", "pick": "single", "ignore_monref": true, "check_multi": true, "check_monref": true, "no_single_bnd": true, "write_resolved": false, "decompose": true, "short_circuit": true, "skip_gt": false, "max_resolve": 25000}
+{"base": "test_results/refine_output_one/phab.output.vcf.gz", "comp": "test_results/refine_output_one/phab.output.vcf.gz", "output": "test_results/refine_output_one/phab_bench", "includebed": "/tmp/_0inhoz1.bed", "extend": 0, "debug": false, "reference": null, "refdist": 500, "pctseq": 0.7, "pctsize": 0.7, "pctovl": 0.0, "typeignore": false, "no_roll": true, "chunksize": 1000, "bSample": "syndip", "cSample": "p:HG002", "dup_to_ins": false, "bnddist": 100, "sizemin": 5, "sizefilt": 5, "sizemax": -1, "passonly": false, "no_ref": "a", "pick": "single", "ignore_monref": true, "check_multi": true, "check_monref": true, "no_single_bnd": true, "write_resolved": false, "decompose": true, "short_circuit": true, "skip_gt": false, "max_resolve": 25000}
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/summary.json b/repo_utils/answer_key/refine/refine_output_one/phab_bench/summary.json
@@ -1,27 +1,27 @@
 {
-    "TP-base": 361,
-    "TP-comp": 361,
-    "FP": 5,
+    "TP-base": 320,
+    "TP-comp": 320,
+    "FP": 9,
     "FN": 2,
-    "precision": 0.9863387978142076,
-    "recall": 0.9944903581267218,
-    "f1": 0.9903978052126201,
-    "base cnt": 363,
-    "comp cnt": 366,
-    "TP-comp_TP-gt": 361,
+    "precision": 0.9726443768996961,
+    "recall": 0.9937888198757764,
+    "f1": 0.9831029185867896,
+    "base cnt": 322,
+    "comp cnt": 329,
+    "TP-comp_TP-gt": 320,
     "TP-comp_FP-gt": 0,
-    "TP-base_TP-gt": 361,
+    "TP-base_TP-gt": 320,
     "TP-base_FP-gt": 0,
     "gt_concordance": 1.0,
     "gt_matrix": {
         "(0, 1)": {
-            "(1, 0)": 136
+            "(1, 0)": 125
         },
         "(1, 0)": {
-            "(0, 1)": 178
+            "(0, 1)": 162
         },
         "(1, 1)": {
-            "(1, 1)": 47
+            "(1, 1)": 33
         }
     }
 }
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-base.vcf.gz b/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-base.vcf.gz
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-base.vcf.gz.tbi b/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-base.vcf.gz.tbi
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-comp.vcf.gz b/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-comp.vcf.gz
diff --git a/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-comp.vcf.gz.tbi b/repo_utils/answer_key/refine/refine_output_one/phab_bench/tp-comp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/refine/refine_output_one/refine.base.vcf.gz b/repo_utils/answer_key/refine/refine_output_one/refine.base.vcf.gz
diff --git a/repo_utils/answer_key/refine/refine_output_one/refine.base.vcf.gz.tbi b/repo_utils/answer_key/refine/refine_output_one/refine.base.vcf.gz.tbi
diff --git a/repo_utils/answer_key/refine/refine_output_one/refine.comp.vcf.gz b/repo_utils/answer_key/refine/refine_output_one/refine.comp.vcf.gz
diff --git a/repo_utils/answer_key/refine/refine_output_one/refine.comp.vcf.gz.tbi b/repo_utils/answer_key/refine/refine_output_one/refine.comp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/refine/refine_output_one/refine.log.txt b/repo_utils/answer_key/refine/refine_output_one/refine.log.txt
@@ -1,9 +1,9 @@
-2025-02-02 06:13:50,924 [INFO] Truvari v5.0.1.dev0+aef4e1a.uc
-2025-02-02 06:13:50,924 [INFO] Command /data/truvari/__main__.py refine --write-phab --coords O --buffer 100 --use-original-vcfs -f repo_utils/test_files/refine_data/chr20.fa.gz test_results/refine_output_one
-2025-02-02 06:13:50,925 [INFO] Params:
+2025-02-16 01:48:25,954 [INFO] Truvari v5.1.1
+2025-02-16 01:48:25,954 [INFO] Command /data/truvari/__main__.py refine --write-phab --coords O --use-original-vcfs -f repo_utils/test_files/refine_data/chr20.fa.gz test_results/refine_output_one
+2025-02-16 01:48:25,956 [INFO] Params:
 {
     "benchdir": "test_results/refine_output_one",
-    "align": "mafft",
+    "align": "poa",
     "use_original_vcfs": true,
     "write_phab": true,
     "threads": 4,
@@ -15,19 +15,30 @@
     "mafft_params": "--auto --thread 1",
     "debug": false
 }
-2025-02-02 06:13:50,925 [INFO] Setting up regions
-2025-02-02 06:13:50,941 [INFO] Evaluating 225 regions
-2025-02-02 06:13:50,942 [INFO] Extending the regions by 100 bases
-2025-02-02 06:13:50,979 [INFO] Found 1 chromosomes with overlapping regions
-2025-02-02 06:13:51,987 [INFO] 75 regions to be refined
-2025-02-02 06:13:51,997 [WARNING] Harmonizing variants ≥50kbp is not recommended
-2025-02-02 06:13:51,998 [INFO] Preparing regions
-2025-02-02 06:13:52,006 [INFO] Extracting haplotypes
-2025-02-02 06:13:53,095 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:888: CoverageWarning:No data was collected. (no-data-collected)
-2025-02-02 06:13:53,099 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:888: CoverageWarning:No data was collected. (no-data-collected)
-2025-02-02 06:13:53,110 [INFO] Harmonizing variants
-2025-02-02 06:13:55,109 [INFO] Running bench
-2025-02-02 06:13:55,134 [INFO] Including 75 bed regions
-2025-02-02 06:13:57,321 [INFO] Zipped 4134 variants Counter({'base': 2067, 'comp': 2067})
-2025-02-02 06:13:57,322 [INFO] 76 chunks of 4134 variants Counter({'__filtered': 3405, 'comp': 366, 'base': 363})
-2025-02-02 06:13:58,488 [INFO] Finished refine
+2025-02-16 01:48:25,956 [INFO] Setting up regions
+2025-02-16 01:48:25,970 [INFO] Evaluating 225 regions
+2025-02-16 01:48:25,971 [INFO] Extending the regions by 100 bases
+2025-02-16 01:48:26,011 [INFO] Found 1 chromosomes with overlapping regions
+2025-02-16 01:48:27,023 [INFO] 75 regions to be refined
+2025-02-16 01:48:27,034 [WARNING] Harmonizing variants ≥50kbp is not recommended
+2025-02-16 01:48:27,035 [INFO] Preparing regions
+2025-02-16 01:48:27,043 [INFO] Extracting haplotypes
+2025-02-16 01:48:28,113 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:892: CoverageWarning:No data was collected. (no-data-collected)
+2025-02-16 01:48:28,116 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:892: CoverageWarning:No data was collected. (no-data-collected)
+2025-02-16 01:48:28,130 [INFO] Harmonizing variants
+2025-02-16 01:48:30,259 [INFO] Running bench
+2025-02-16 01:48:30,288 [INFO] Including 75 bed regions
+2025-02-16 01:48:32,225 [INFO] Zipped 4226 variants Counter({'base': 2113, 'comp': 2113})
+2025-02-16 01:48:32,226 [INFO] 77 chunks of 4226 variants Counter({'__filtered': 3575, 'comp': 329, 'base': 322})
+2025-02-16 01:48:33,331 [INFO] Stats: {
+    "TP-base": 555,
+    "TP-comp": 555,
+    "FP": 20,
+    "FN": 2,
+    "precision": 0.9652173913043478,
+    "recall": 0.9964093357271095,
+    "f1": 0.980565371024735,
+    "base cnt": 557,
+    "comp cnt": 575
+}
+2025-02-16 01:48:33,332 [INFO] Finished refine
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		{"base": "test_results/refine_output_one/phab.output.vcf.gz", "comp": "test_results/refine_output_one/phab.output.vcf.gz", "output": "test_results/refine_output_one/phab_bench", "includebed": "/tmp/xn9atc8u.bed", "extend": 0, "debug": false, "reference": null, "refdist": 500, "pctseq": 0.7, "pctsize": 0.7, "pctovl": 0.0, "typeignore": false, "no_roll": true, "chunksize": 1000, "bSample": "syndip", "cSample": "p:HG002", "dup_to_ins": false, "bnddist": 100, "sizemin": 5, "sizefilt": 5, "sizemax": -1, "passonly": false, "no_ref": "a", "pick": "single", "ignore_monref": true, "check_multi": true, "check_monref": true, "no_single_bnd": true, "write_resolved": false, "decompose": true, "short_circuit": true, "skip_gt": false, "max_resolve": 25000}
		{"base": "test_results/refine_output_one/phab.output.vcf.gz", "comp": "test_results/refine_output_one/phab.output.vcf.gz", "output": "test_results/refine_output_one/phab_bench", "includebed": "/tmp/_0inhoz1.bed", "extend": 0, "debug": false, "reference": null, "refdist": 500, "pctseq": 0.7, "pctsize": 0.7, "pctovl": 0.0, "typeignore": false, "no_roll": true, "chunksize": 1000, "bSample": "syndip", "cSample": "p:HG002", "dup_to_ins": false, "bnddist": 100, "sizemin": 5, "sizefilt": 5, "sizemax": -1, "passonly": false, "no_ref": "a", "pick": "single", "ignore_monref": true, "check_multi": true, "check_monref": true, "no_single_bnd": true, "write_resolved": false, "decompose": true, "short_circuit": true, "skip_gt": false, "max_resolve": 25000}