Merge branch 'feature/refine2' into develop

repo_utils/answer_key/refine/refine_output_one/log.txt

@@ -1,6 +1,6 @@
-2025-01-06 03:04:53,537 [INFO] Truvari v5.0.0
-2025-01-06 03:04:53,537 [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
-2025-01-06 03:04:53,538 [INFO] Params:
+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:
 {
     "base": "/data/repo_utils/test_files/refine_data/hg002_base.vcf.gz",
     "comp": "/data/repo_utils/test_files/refine_data/hg002_comp.vcf.gz",
@@ -22,17 +22,24 @@
     "bnddist": 100,
     "sizemin": 5,
     "sizefilt": 5,
-    "sizemax": 50000,
+    "sizemax": -1,
     "passonly": false,
     "no_ref": false,
     "pick": "single",
+    "ignore_monref": true,
+    "check_multi": true,
     "check_monref": true,
-    "check_multi": true
+    "no_single_bnd": true,
+    "write_resolved": false,
+    "decompose": true,
+    "short_circuit": false,
+    "skip_gt": false,
+    "max_resolve": 25000
 }
-2025-01-06 03:04:53,572 [INFO] Including 225 bed regions
-2025-01-06 03:04:55,638 [INFO] Zipped 7157 variants Counter({'comp': 5302, 'base': 1855})
-2025-01-06 03:04:55,638 [INFO] 211 chunks of 7157 variants Counter({'__filtered': 6137, 'base': 569, 'comp': 451})
-2025-01-06 03:04:55,718 [INFO] Stats: {
+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: {
     "TP-base": 387,
     "TP-comp": 387,
     "FP": 64,
@@ -64,4 +71,4 @@
         }
     }
 }
-2025-01-06 03:04:55,718 [INFO] Finished bench
+2025-02-02 06:13:49,324 [INFO] Finished bench

repo_utils/answer_key/refine/refine_output_one/params.json

@@ -1 +1 @@
-{"base": "/data/repo_utils/test_files/refine_data/hg002_base.vcf.gz", "comp": "/data/repo_utils/test_files/refine_data/hg002_comp.vcf.gz", "output": "test_results/refine_output_one", "includebed": "/data/repo_utils/test_files/refine_data/h1_hc_tr_hg002.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": "HG002", "dup_to_ins": false, "bnddist": 100, "sizemin": 5, "sizefilt": 5, "sizemax": 50000, "passonly": false, "no_ref": false, "pick": "single", "check_monref": true, "check_multi": true}
+{"base": "/data/repo_utils/test_files/refine_data/hg002_base.vcf.gz", "comp": "/data/repo_utils/test_files/refine_data/hg002_comp.vcf.gz", "output": "test_results/refine_output_one", "includebed": "/data/repo_utils/test_files/refine_data/h1_hc_tr_hg002.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": "HG002", "dup_to_ins": false, "bnddist": 100, "sizemin": 5, "sizefilt": 5, "sizemax": -1, "passonly": false, "no_ref": false, "pick": "single", "ignore_monref": true, "check_multi": true, "check_monref": true, "no_single_bnd": true, "write_resolved": false, "decompose": true, "short_circuit": false, "skip_gt": false, "max_resolve": 25000}

repo_utils/answer_key/refine/refine_output_one/phab_bench/candidate.refine.bed

@@ -1,5 +1,5 @@
 chr20	5040466	5040487
 chr20	5041931	5042443
-chr20	16257844	16259215
+chr20	16257844	16259455
 chr20	32723034	32723055
 chr20	51953809	51953830

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/in6rjnqm.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": 50000, "passonly": false, "no_ref": "a", "pick": "single", "check_monref": true, "check_multi": true}
+{"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}

repo_utils/answer_key/refine/refine_output_one/phab_bench/summary.json

@@ -1,24 +1,24 @@
 {
-    "TP-base": 359,
-    "TP-comp": 359,
-    "FP": 4,
+    "TP-base": 361,
+    "TP-comp": 361,
+    "FP": 5,
     "FN": 2,
-    "precision": 0.9889807162534435,
-    "recall": 0.9944598337950139,
-    "f1": 0.9917127071823205,
-    "base cnt": 361,
-    "comp cnt": 363,
-    "TP-comp_TP-gt": 359,
+    "precision": 0.9863387978142076,
+    "recall": 0.9944903581267218,
+    "f1": 0.9903978052126201,
+    "base cnt": 363,
+    "comp cnt": 366,
+    "TP-comp_TP-gt": 361,
     "TP-comp_FP-gt": 0,
-    "TP-base_TP-gt": 359,
+    "TP-base_TP-gt": 361,
     "TP-base_FP-gt": 0,
     "gt_concordance": 1.0,
     "gt_matrix": {
         "(0, 1)": {
-            "(1, 0)": 135
+            "(1, 0)": 136
         },
         "(1, 0)": {
-            "(0, 1)": 177
+            "(0, 1)": 178
         },
         "(1, 1)": {
             "(1, 1)": 47

repo_utils/answer_key/refine/refine_output_one/refine.log.txt

@@ -1,28 +1,33 @@
-2025-01-06 03:04:56,953 [INFO] Truvari v5.0.0
-2025-01-06 03:04:56,953 [INFO] Command /data/truvari/__main__.py refine -u -f repo_utils/test_files/refine_data/chr20.fa.gz test_results/refine_output_one
-2025-01-06 03:04:56,954 [INFO] Params:
+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:
 {
     "benchdir": "test_results/refine_output_one",
-    "reference": "repo_utils/test_files/refine_data/chr20.fa.gz",
-    "regions": null,
+    "align": "mafft",
     "use_original_vcfs": true,
-    "use_region_coords": false,
-    "recount": false,
+    "write_phab": true,
     "threads": 4,
-    "align": "mafft",
+    "buffer": 100,
+    "reference": "repo_utils/test_files/refine_data/chr20.fa.gz",
+    "regions": null,
+    "coords": "O",
+    "subset": false,
     "mafft_params": "--auto --thread 1",
     "debug": false
 }
-2025-01-06 03:04:56,954 [INFO] Setting up regions
-2025-01-06 03:04:56,964 [INFO] Evaluating 225 regions
-2025-01-06 03:04:57,464 [INFO] 75 regions to be refined
-2025-01-06 03:04:57,473 [INFO] Preparing regions
-2025-01-06 03:04:57,480 [INFO] Extracting haplotypes
-2025-01-06 03:04:57,954 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:888: CoverageWarning:No data was collected. (no-data-collected)
-2025-01-06 03:04:57,956 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:888: CoverageWarning:No data was collected. (no-data-collected)
-2025-01-06 03:04:57,966 [INFO] Harmonizing variants
-2025-01-06 03:04:59,358 [INFO] Running bench
-2025-01-06 03:04:59,376 [INFO] Including 75 bed regions
-2025-01-06 03:05:00,104 [INFO] Zipped 3930 variants Counter({'base': 1965, 'comp': 1965})
-2025-01-06 03:05:00,104 [INFO] 76 chunks of 3930 variants Counter({'__filtered': 3206, 'comp': 363, 'base': 361})
-2025-01-06 03:05:00,365 [INFO] Finished refine
+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

repo_utils/answer_key/refine/refine_output_one/refine.region_summary.json

@@ -1,18 +1,18 @@
 {
     "TP": 199,
-    "TN": 14,
-    "FP": 10,
+    "TN": 13,
+    "FP": 11,
     "FN": 2,
     "base P": 202,
-    "base N": 23,
+    "base N": 22,
     "comp P": 210,
-    "comp N": 15,
+    "comp N": 14,
     "PPV": 0.9476190476190476,
     "TPR": 0.9851485148514851,
-    "TNR": 0.6086956521739131,
-    "NPV": 0.9333333333333333,
-    "ACC": 0.9466666666666667,
-    "BA": 0.7969220835126991,
+    "TNR": 0.5909090909090909,
+    "NPV": 0.9285714285714286,
+    "ACC": 0.9464285714285714,
+    "BA": 0.788028802880288,
     "F1": 0.9660194174757282,
     "UND": 0
 }