is_bnd fix

pysam.VariantFile.allele_variant_types isn't reliable
ACEnglish · Jan 29, 2025 · 664fd5b · 664fd5b
1 parent 24859cf
commit 664fd5b
Show file tree

Hide file tree

Showing 22 changed files with 69 additions and 70 deletions.
diff --git a/repo_utils/answer_key/bench/bench_bnd/candidate.refine.bed b/repo_utils/answer_key/bench/bench_bnd/candidate.refine.bed
@@ -29,7 +29,6 @@ chr13	56380894	56381040
 chr13	114073358	114074122
 chr14	102919538	102919632
 chr15	31496974	31637324
-chr15	40450778	40450800
 chr15	44117191	44248483
 chr15	74894096	74894117
 chr15	90787610	90889113

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/fn.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd/fn.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_bnd/fp.vcf.gz b/repo_utils/answer_key/bench/bench_bnd/fp.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd/fp.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd/fp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_bnd/log.txt b/repo_utils/answer_key/bench/bench_bnd/log.txt
@@ -1,6 +1,6 @@
-2025-01-09 21:35:26,687 [INFO] Truvari v5.0.0
-2025-01-09 21:35:26,688 [INFO] Command /data/truvari/__main__.py bench -b repo_utils/test_files/variants/bnd.base.vcf.gz -c repo_utils/test_files/variants/bnd.comp.vcf.gz -p 0 -o test_results/bench_bnd/ --no-decompose
-2025-01-09 21:35:26,688 [INFO] Params:
+2025-01-29 01:41:34,415 [INFO] Truvari v5.0.1.dev0+24859cf.uc
+2025-01-29 01:41:34,416 [INFO] Command /data/truvari/__main__.py bench -b repo_utils/test_files/variants/bnd.base.vcf.gz -c repo_utils/test_files/variants/bnd.comp.vcf.gz -p 0 -o test_results/bench_bnd/ --no-decompose
+2025-01-29 01:41:34,418 [INFO] Params:
 {
     "base": "/data/repo_utils/test_files/variants/bnd.base.vcf.gz",
     "comp": "/data/repo_utils/test_files/variants/bnd.comp.vcf.gz",
@@ -36,27 +36,27 @@
     "skip_gt": false,
     "max_resolve": 25000
 }
-2025-01-09 21:35:26,723 [WARNING] 193 contigs present in comparison VCF header are not in baseline VCF.
-2025-01-09 21:35:26,898 [INFO] Zipped 439 variants Counter({'comp': 243, 'base': 196})
-2025-01-09 21:35:26,899 [INFO] 223 chunks of 439 variants Counter({'comp': 243, 'base': 186, '__filtered': 10})
-2025-01-09 21:35:26,974 [INFO] Stats: {
-    "TP-base": 119,
-    "TP-comp": 119,
+2025-01-29 01:41:34,484 [WARNING] 193 contigs present in comparison VCF header are not in baseline VCF.
+2025-01-29 01:41:34,766 [INFO] Zipped 439 variants Counter({'comp': 243, 'base': 196})
+2025-01-29 01:41:34,767 [INFO] 226 chunks of 439 variants Counter({'comp': 243, 'base': 195, '__filtered': 1})
+2025-01-29 01:41:34,907 [INFO] Stats: {
+    "TP-base": 120,
+    "TP-comp": 120,
     "FP": 102,
-    "FN": 67,
-    "precision": 0.5384615384615384,
-    "recall": 0.6397849462365591,
-    "f1": 0.5847665847665847,
-    "base cnt": 186,
-    "comp cnt": 221,
-    "TP-comp_TP-gt": 99,
+    "FN": 75,
+    "precision": 0.5405405405405406,
+    "recall": 0.6153846153846154,
+    "f1": 0.5755395683453237,
+    "base cnt": 195,
+    "comp cnt": 222,
+    "TP-comp_TP-gt": 100,
     "TP-comp_FP-gt": 20,
-    "TP-base_TP-gt": 99,
+    "TP-base_TP-gt": 100,
     "TP-base_FP-gt": 20,
-    "gt_concordance": 0.8319327731092437,
+    "gt_concordance": 0.8333333333333334,
     "gt_matrix": {
         "(0, 1)": {
-            "(0, 1)": 94,
+            "(0, 1)": 95,
             "(0, 0)": 19,
             "(1, 1)": 1
         },
@@ -68,4 +68,4 @@
         }
     }
 }
-2025-01-09 21:35:26,974 [INFO] Finished bench
+2025-01-29 01:41:34,908 [INFO] Finished bench
diff --git a/repo_utils/answer_key/bench/bench_bnd/summary.json b/repo_utils/answer_key/bench/bench_bnd/summary.json
@@ -1,21 +1,21 @@
 {
-    "TP-base": 119,
-    "TP-comp": 119,
+    "TP-base": 120,
+    "TP-comp": 120,
     "FP": 102,
-    "FN": 67,
-    "precision": 0.5384615384615384,
-    "recall": 0.6397849462365591,
-    "f1": 0.5847665847665847,
-    "base cnt": 186,
-    "comp cnt": 221,
-    "TP-comp_TP-gt": 99,
+    "FN": 75,
+    "precision": 0.5405405405405406,
+    "recall": 0.6153846153846154,
+    "f1": 0.5755395683453237,
+    "base cnt": 195,
+    "comp cnt": 222,
+    "TP-comp_TP-gt": 100,
     "TP-comp_FP-gt": 20,
-    "TP-base_TP-gt": 99,
+    "TP-base_TP-gt": 100,
     "TP-base_FP-gt": 20,
-    "gt_concordance": 0.8319327731092437,
+    "gt_concordance": 0.8333333333333334,
     "gt_matrix": {
         "(0, 1)": {
-            "(0, 1)": 94,
+            "(0, 1)": 95,
             "(0, 0)": 19,
             "(1, 1)": 1
         },

diff --git a/repo_utils/answer_key/bench/bench_bnd/tp-base.vcf.gz b/repo_utils/answer_key/bench/bench_bnd/tp-base.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd/tp-base.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd/tp-base.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_bnd/tp-comp.vcf.gz b/repo_utils/answer_key/bench/bench_bnd/tp-comp.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd/tp-comp.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd/tp-comp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/fn.vcf.gz b/repo_utils/answer_key/bench/bench_bnd_decomp/fn.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/fn.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd_decomp/fn.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/fp.vcf.gz b/repo_utils/answer_key/bench/bench_bnd_decomp/fp.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/fp.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd_decomp/fp.vcf.gz.tbi
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/log.txt b/repo_utils/answer_key/bench/bench_bnd_decomp/log.txt
@@ -1,6 +1,6 @@
-2025-01-28 22:35:15,820 [INFO] Truvari v5.0.1.dev0+31b79f9
-2025-01-28 22:35:15,822 [INFO] Command /data/truvari/__main__.py bench -b repo_utils/test_files/variants/bnd.base.vcf.gz -c repo_utils/test_files/variants/bnd.comp2.vcf.gz --sizemax 1000000000 -p 0 --pick multi -o test_results/bench_bnd_decomp/
-2025-01-28 22:35:15,823 [INFO] Params:
+2025-01-29 01:41:36,655 [INFO] Truvari v5.0.1.dev0+24859cf.uc
+2025-01-29 01:41:36,657 [INFO] Command /data/truvari/__main__.py bench -b repo_utils/test_files/variants/bnd.base.vcf.gz -c repo_utils/test_files/variants/bnd.comp2.vcf.gz --sizemax 1000000000 -p 0 --pick multi -o test_results/bench_bnd_decomp/
+2025-01-29 01:41:36,658 [INFO] Params:
 {
     "base": "/data/repo_utils/test_files/variants/bnd.base.vcf.gz",
     "comp": "/data/repo_utils/test_files/variants/bnd.comp2.vcf.gz",
@@ -36,27 +36,27 @@
     "skip_gt": false,
     "max_resolve": 25000
 }
-2025-01-28 22:35:15,911 [WARNING] 193 contigs present in comparison VCF header are not in baseline VCF.
-2025-01-28 22:35:39,849 [INFO] Zipped 30098 variants Counter({'comp': 29902, 'base': 196})
-2025-01-28 22:35:39,850 [INFO] 20659 chunks of 30098 variants Counter({'comp': 29902, 'base': 186, '__filtered': 10})
-2025-01-28 22:35:45,581 [INFO] Stats: {
-    "TP-base": 147,
-    "TP-comp": 128,
-    "FP": 28402,
-    "FN": 39,
-    "precision": 0.004486505432877673,
-    "recall": 0.7903225806451613,
-    "f1": 0.008922360385402724,
-    "base cnt": 186,
-    "comp cnt": 28530,
+2025-01-29 01:41:36,746 [WARNING] 193 contigs present in comparison VCF header are not in baseline VCF.
+2025-01-29 01:41:58,627 [INFO] Zipped 30098 variants Counter({'comp': 29902, 'base': 196})
+2025-01-29 01:41:58,627 [INFO] 20660 chunks of 30098 variants Counter({'comp': 29902, 'base': 195, '__filtered': 1})
+2025-01-29 01:42:03,703 [INFO] Stats: {
+    "TP-base": 152,
+    "TP-comp": 131,
+    "FP": 28401,
+    "FN": 43,
+    "precision": 0.004591336043740362,
+    "recall": 0.7794871794871795,
+    "f1": 0.009128901026932595,
+    "base cnt": 195,
+    "comp cnt": 28532,
     "TP-comp_TP-gt": 1,
-    "TP-comp_FP-gt": 127,
+    "TP-comp_FP-gt": 130,
     "TP-base_TP-gt": 1,
-    "TP-base_FP-gt": 146,
-    "gt_concordance": 0.0078125,
+    "TP-base_FP-gt": 151,
+    "gt_concordance": 0.007633587786259542,
     "gt_matrix": {
         "(0, 1)": {
-            "(0, 0)": 133,
+            "(0, 0)": 137,
             "(0, 1)": 1
         },
         "(0, 0, 1)": {
@@ -66,7 +66,7 @@
             "(0, 0)": 2
         },
         "(0, 0, 0, 1)": {
-            "(0, 0)": 1
+            "(0, 0)": 2
         },
         "(0, 0, 1, 0)": {
             "(0, 0)": 1
@@ -79,4 +79,4 @@
         }
     }
 }
-2025-01-28 22:35:45,582 [INFO] Finished bench
+2025-01-29 01:42:03,704 [INFO] Finished bench
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/summary.json b/repo_utils/answer_key/bench/bench_bnd_decomp/summary.json
@@ -1,21 +1,21 @@
 {
-    "TP-base": 147,
-    "TP-comp": 128,
-    "FP": 28402,
-    "FN": 39,
-    "precision": 0.004486505432877673,
-    "recall": 0.7903225806451613,
-    "f1": 0.008922360385402724,
-    "base cnt": 186,
-    "comp cnt": 28530,
+    "TP-base": 152,
+    "TP-comp": 131,
+    "FP": 28401,
+    "FN": 43,
+    "precision": 0.004591336043740362,
+    "recall": 0.7794871794871795,
+    "f1": 0.009128901026932595,
+    "base cnt": 195,
+    "comp cnt": 28532,
     "TP-comp_TP-gt": 1,
-    "TP-comp_FP-gt": 127,
+    "TP-comp_FP-gt": 130,
     "TP-base_TP-gt": 1,
-    "TP-base_FP-gt": 146,
-    "gt_concordance": 0.0078125,
+    "TP-base_FP-gt": 151,
+    "gt_concordance": 0.007633587786259542,
     "gt_matrix": {
         "(0, 1)": {
-            "(0, 0)": 133,
+            "(0, 0)": 137,
             "(0, 1)": 1
         },
         "(0, 0, 1)": {
@@ -25,7 +25,7 @@
             "(0, 0)": 2
         },
         "(0, 0, 0, 1)": {
-            "(0, 0)": 1
+            "(0, 0)": 2
         },
         "(0, 0, 1, 0)": {
             "(0, 0)": 1

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_bnd_decomp/tp-comp.vcf.gz b/repo_utils/answer_key/bench/bench_bnd_decomp/tp-comp.vcf.gz
diff --git a/repo_utils/answer_key/bench/bench_bnd_decomp/tp-comp.vcf.gz.tbi b/repo_utils/answer_key/bench/bench_bnd_decomp/tp-comp.vcf.gz.tbi
diff --git a/truvari/variant_record.py b/truvari/variant_record.py
@@ -404,7 +404,7 @@ def is_bnd(self):
         """
         Returns if a record is a resolved BND
         """
-        return self.alleles_variant_types[1] == 'BND'
+        return '[' in self._record.alts[0] or ']' in self._record.alts[0]
 
     def is_filtered(self, values=None):
         """