Merge branch 'develop' into feature/rust

repo_utils/answer_key/refine/refine_output_three/candidate.refine.bed

@@ -1,92 +1,92 @@
-chr20	278929	279069
-chr20	641912	642420
-chr20	2240960	2241290
-chr20	4032357	4033228
-chr20	5040476	5040477
-chr20	5041941	5042268
-chr20	7720952	7720968
-chr20	8661944	8662119
-chr20	10802727	10802844
-chr20	13848272	13848544
-chr20	14862054	14862644
-chr20	16257854	16259205
-chr20	16395201	16395373
-chr20	17081293	17081365
-chr20	18209139	18210134
-chr20	20296014	20296330
-chr20	20320339	20320519
-chr20	20337285	20337624
-chr20	20354912	20355435
-chr20	20356530	20357810
-chr20	21120298	21120461
-chr20	21721451	21721646
-chr20	22082266	22083905
-chr20	23155578	23155857
-chr20	23560939	23561098
-chr20	24408073	24408820
-chr20	24682066	24682125
-chr20	25781790	25781791
-chr20	32723044	32723045
-chr20	34235898	34235981
-chr20	35539212	35539582
-chr20	35580686	35580756
-chr20	37361785	37361886
-chr20	38123799	38124003
-chr20	38463997	38464344
-chr20	41196370	41196495
-chr20	41257714	41258003
-chr20	44764150	44764203
-chr20	45600655	45600695
-chr20	48449794	48450385
-chr20	49834182	49834469
-chr20	50775646	50775832
-chr20	51953819	51953820
-chr20	53204099	53204252
-chr20	55624808	55625652
-chr20	55627638	55628305
-chr20	55944272	55945175
-chr20	56280541	56281913
-chr20	57090868	57091166
-chr20	57110450	57110593
-chr20	57190256	57190428
-chr20	57350856	57350920
-chr20	57949001	57949346
-chr20	59384366	59384743
-chr20	60314443	60314711
-chr20	60703005	60703087
-chr20	61100921	61102405
-chr20	61201822	61202242
-chr20	61282925	61283479
-chr20	61289662	61290273
-chr20	61329345	61329441
-chr20	61562109	61562252
-chr20	61744401	61744592
-chr20	61783958	61784698
-chr20	62057602	62058768
-chr20	62270413	62270827
-chr20	62321396	62321730
-chr20	62349641	62349826
-chr20	62360410	62360602
-chr20	62830650	62830697
-chr20	62875241	62875404
-chr20	63028066	63029030
-chr20	63049093	63049159
-chr20	63154687	63154921
-chr20	63167473	63167564
-chr20	63221509	63221721
-chr20	63372214	63372400
-chr20	63491957	63492390
-chr20	63535751	63536002
-chr20	63559415	63559719
-chr20	63641847	63642015
-chr20	63693449	63693732
-chr20	63770936	63771014
-chr20	63948594	63948653
-chr20	63964805	63966113
-chr20	64065882	64065883
-chr20	64090733	64091007
-chr20	64097039	64097040
-chr20	64125360	64127875
-chr20	64131913	64133856
-chr20	64134990	64136330
-chr20	64173438	64176330
+chr20	278919	279079
+chr20	641902	642430
+chr20	2240950	2241300
+chr20	4032347	4033238
+chr20	5040466	5040487
+chr20	5041931	5042278
+chr20	7720942	7720978
+chr20	8661934	8662129
+chr20	10802717	10802854
+chr20	13848262	13848554
+chr20	14862044	14862654
+chr20	16257844	16259215
+chr20	16395191	16395383
+chr20	17081283	17081375
+chr20	18209129	18210144
+chr20	20296004	20296340
+chr20	20320329	20320529
+chr20	20337275	20337634
+chr20	20354902	20355445
+chr20	20356520	20357820
+chr20	21120288	21120471
+chr20	21721441	21721656
+chr20	22082256	22083915
+chr20	23155568	23155867
+chr20	23560929	23561108
+chr20	24408063	24408830
+chr20	24682056	24682135
+chr20	25781780	25781801
+chr20	32723034	32723055
+chr20	34235888	34235991
+chr20	35539202	35539592
+chr20	35580676	35580766
+chr20	37361775	37361896
+chr20	38123789	38124013
+chr20	38463987	38464354
+chr20	41196360	41196505
+chr20	41257704	41258013
+chr20	44764140	44764213
+chr20	45600645	45600705
+chr20	48449784	48450395
+chr20	49834172	49834479
+chr20	50775636	50775842
+chr20	51953809	51953830
+chr20	53204089	53204262
+chr20	55624798	55625662
+chr20	55627628	55628315
+chr20	55944262	55945185
+chr20	56280531	56281923
+chr20	57090858	57091176
+chr20	57110440	57110603
+chr20	57190246	57190438
+chr20	57350846	57350930
+chr20	57948991	57949356
+chr20	59384356	59384753
+chr20	60314433	60314721
+chr20	60702995	60703097
+chr20	61100911	61102415
+chr20	61201812	61202252
+chr20	61282915	61283489
+chr20	61289652	61290283
+chr20	61329335	61329451
+chr20	61562099	61562262
+chr20	61744391	61744602
+chr20	61783948	61784708
+chr20	62057592	62058778
+chr20	62270403	62270837
+chr20	62321386	62321740
+chr20	62349631	62349836
+chr20	62360400	62360612
+chr20	62830640	62830707
+chr20	62875231	62875414
+chr20	63028056	63029040
+chr20	63049083	63049169
+chr20	63154677	63154931
+chr20	63167463	63167574
+chr20	63221499	63221731
+chr20	63372204	63372410
+chr20	63491947	63492400
+chr20	63535741	63536012
+chr20	63559405	63559729
+chr20	63641837	63642025
+chr20	63693439	63693742
+chr20	63770926	63771024
+chr20	63948584	63948663
+chr20	63964795	63966123
+chr20	64065872	64065893
+chr20	64090723	64091017
+chr20	64097029	64097050
+chr20	64125350	64127885
+chr20	64131903	64133866
+chr20	64134980	64136340
+chr20	64173428	64176340

repo_utils/answer_key/refine/refine_output_three/log.txt

@@ -1,6 +1,6 @@
-2023-12-23 20:14:37,407 [INFO] Truvari v4.2.0rc1
-2023-12-23 20:14:37,409 [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_three
-2023-12-23 20:14:37,410 [INFO] Params:
+2024-02-21 18:25:35,871 [INFO] Truvari v4.2.2.dev0+detached
+2024-02-21 18:25:35,873 [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_three
+2024-02-21 18:25:35,875 [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",
@@ -28,10 +28,10 @@
     "check_monref": true,
     "check_multi": true
 }
-2023-12-23 20:14:37,491 [INFO] Including 225 bed regions
-2023-12-23 20:14:39,399 [INFO] Zipped 7158 variants Counter({'comp': 5303, 'base': 1855})
-2023-12-23 20:14:39,401 [INFO] 211 chunks of 7158 variants Counter({'__filtered': 6120, 'base': 587, 'comp': 451})
-2023-12-23 20:14:39,612 [INFO] Stats: {
+2024-02-21 18:25:36,006 [INFO] Including 225 bed regions
+2024-02-21 18:25:38,811 [INFO] Zipped 7157 variants Counter({'comp': 5302, 'base': 1855})
+2024-02-21 18:25:38,812 [INFO] 211 chunks of 7157 variants Counter({'__filtered': 6119, 'base': 587, 'comp': 451})
+2024-02-21 18:25:39,002 [INFO] Stats: {
     "TP-base": 387,
     "TP-comp": 387,
     "FP": 64,
@@ -61,26 +61,6 @@
             "(1, 0)": 2,
             "(0, 1)": 2
         }
-    },
-    "weighted": {
-        "sequence": {
-            "TP": 503.5764002194628,
-            "FP": 38.596499651670456,
-            "FN": 84.44959977362305,
-            "precision": 0.9288114554216113,
-            "recall": 0.8563845820174345,
-            "f1": 0.8911288097696113,
-            "total": 604
-        },
-        "size": {
-            "TP": 485.95460002683103,
-            "FP": 44.582299776375294,
-            "FN": 101.60089997388422,
-            "precision": 0.9159675796482538,
-            "recall": 0.8270786334673736,
-            "f1": 0.8692566018909569,
-            "total": 604
-        }
     }
 }
-2023-12-23 20:14:39,614 [INFO] Finished bench
+2024-02-21 18:25:39,003 [INFO] Finished bench

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

@@ -1,18 +1,19 @@
-chr20	2240960	2241271
-chr20	4032357	4033228
-chr20	14862139	14862610
-chr20	18209139	18210065
-chr20	20356530	20357713
-chr20	22082266	22083534
-chr20	23155578	23155857
-chr20	35580690	35580756
-chr20	38123861	38123977
-chr20	55944272	55944971
-chr20	56280541	56281714
-chr20	57949001	57949268
-chr20	62349641	62349741
-chr20	62360435	62360602
-chr20	63491957	63492174
-chr20	63948627	63948633
-chr20	64131947	64133823
-chr20	64173541	64176330
+chr20	2240950	2241281
+chr20	4032347	4033346
+chr20	14861956	14862620
+chr20	18209129	18210249
+chr20	20356520	20357861
+chr20	22082256	22083544
+chr20	23155541	23155867
+chr20	35580680	35580870
+chr20	38123851	38124122
+chr20	50775888	50775909
+chr20	55944262	55945295
+chr20	56280531	56281724
+chr20	57948991	57949450
+chr20	62349631	62349904
+chr20	62360425	62360692
+chr20	63693446	63693676
+chr20	63948617	63948750
+chr20	64131937	64133833
+chr20	64173531	64176450

repo_utils/answer_key/refine/refine_output_three/phab_bench/params.json

@@ -1 +1 @@
-{"base": "test_results/refine_output_three/phab.output.vcf.gz", "comp": "test_results/refine_output_three/phab.output.vcf.gz", "output": "test_results/refine_output_three/phab_bench", "includebed": "/tmp/4rq8mghm.bed", "extend": 0, "debug": false, "reference": null, "refdist": 500, "pctseq": 0.7, "minhaplen": 50, "pctsize": 0.7, "pctovl": 0.0, "typeignore": false, "chunksize": 1000, "bSample": "syndip", "cSample": "p:HG002", "dup_to_ins": false, "sizemin": 5, "sizefilt": 5, "sizemax": 50000, "passonly": false, "no_ref": "a", "pick": "single", "check_monref": true, "check_multi": true}
+{"base": "test_results/refine_output_three/phab.output.vcf.gz", "comp": "test_results/refine_output_three/phab.output.vcf.gz", "output": "test_results/refine_output_three/phab_bench", "includebed": "/tmp/2b8u_17f.bed", "extend": 0, "debug": false, "reference": null, "refdist": 500, "pctseq": 0.7, "minhaplen": 50, "pctsize": 0.7, "pctovl": 0.0, "typeignore": false, "chunksize": 1000, "bSample": "syndip", "cSample": "p:HG002", "dup_to_ins": false, "sizemin": 5, "sizefilt": 5, "sizemax": 50000, "passonly": false, "no_ref": "a", "pick": "single", "check_monref": true, "check_multi": true}

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

@@ -1,50 +1,30 @@
 {
-    "TP-base": 94,
-    "TP-comp": 94,
-    "FP": 21,
-    "FN": 42,
-    "precision": 0.8173913043478261,
-    "recall": 0.6911764705882353,
-    "f1": 0.7490039840637451,
-    "base cnt": 136,
-    "comp cnt": 115,
-    "TP-comp_TP-gt": 92,
-    "TP-comp_FP-gt": 2,
-    "TP-base_TP-gt": 92,
-    "TP-base_FP-gt": 2,
-    "gt_concordance": 0.9787234042553191,
+    "TP-base": 138,
+    "TP-comp": 138,
+    "FP": 29,
+    "FN": 41,
+    "precision": 0.8263473053892215,
+    "recall": 0.770949720670391,
+    "f1": 0.7976878612716763,
+    "base cnt": 179,
+    "comp cnt": 167,
+    "TP-comp_TP-gt": 134,
+    "TP-comp_FP-gt": 4,
+    "TP-base_TP-gt": 134,
+    "TP-base_FP-gt": 4,
+    "gt_concordance": 0.9710144927536232,
     "gt_matrix": {
         "(1, 1)": {
-            "(0, 1)": 1,
-            "(1, 1)": 12
+            "(0, 1)": 2,
+            "(1, 1)": 14,
+            "(1, 0)": 2
         },
         "(1, 0)": {
-            "(0, 1)": 42,
-            "(1, 1)": 1
+            "(0, 1)": 60
         },
         "(0, 1)": {
-            "(1, 0)": 35,
-            "(0, 1)": 3
-        }
-    },
-    "weighted": {
-        "sequence": {
-            "TP": 121.41469976585358,
-            "FP": 9.313800107687712,
-            "FN": 16.106600251980126,
-            "precision": 0.9287546318002784,
-            "recall": 0.8828792321633708,
-            "f1": 0.9052360882656332,
-            "total": 139
-        },
-        "size": {
-            "TP": 117.62869990803301,
-            "FP": 11.260100107640028,
-            "FN": 19.847500076517463,
-            "precision": 0.9126370940976192,
-            "recall": 0.8556295556703785,
-            "f1": 0.8832143855831983,
-            "total": 139
+            "(1, 0)": 56,
+            "(0, 1)": 4
         }
     }
 }

repo_utils/answer_key/refine/refine_output_three/refine.log.txt

@@ -1,6 +1,6 @@
-2023-12-23 20:14:41,887 [INFO] Truvari v4.2.0rc1
-2023-12-23 20:14:41,889 [INFO] Command /data/truvari/__main__.py refine --recount -U -r test_results/refine_output_three/candidate.refine.bed -f repo_utils/test_files/refine_data/chr20.fa.gz test_results/refine_output_three
-2023-12-23 20:14:41,890 [INFO] Params:
+2024-02-21 18:25:40,683 [INFO] Truvari v4.2.2.dev0+detached
+2024-02-21 18:25:40,684 [INFO] Command /data/truvari/__main__.py refine --recount -U -r test_results/refine_output_three/candidate.refine.bed -f repo_utils/test_files/refine_data/chr20.fa.gz test_results/refine_output_three
+2024-02-21 18:25:40,684 [INFO] Params:
 {
     "benchdir": "test_results/refine_output_three",
     "reference": "repo_utils/test_files/refine_data/chr20.fa.gz",
@@ -13,16 +13,17 @@
     "mafft_params": "--auto --thread 1",
     "debug": false
 }
-2023-12-23 20:14:41,893 [INFO] Setting up regions
-2023-12-23 20:14:41,968 [INFO] 92 --regions reduced to 92 after intersecting with 225 from --includebed
-2023-12-23 20:14:42,797 [INFO] 41 regions to be refined
-2023-12-23 20:14:42,812 [INFO] Preparing regions
-2023-12-23 20:14:42,821 [INFO] Extracting haplotypes
-2023-12-23 20:14:43,270 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:883: CoverageWarning:No data was collected. (no-data-collected)
-2023-12-23 20:14:43,276 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:883: CoverageWarning:No data was collected. (no-data-collected)
-2023-12-23 20:14:43,319 [INFO] Harmonizing variants
-2023-12-23 20:14:45,119 [INFO] Running bench
-2023-12-23 20:14:45,178 [INFO] Including 41 bed regions
-2023-12-23 20:14:45,638 [INFO] Zipped 2824 variants Counter({'base': 1412, 'comp': 1412})
-2023-12-23 20:14:45,640 [INFO] 35 chunks of 2824 variants Counter({'__filtered': 2573, 'base': 136, 'comp': 115})
-2023-12-23 20:14:47,173 [INFO] Finished refine
+2024-02-21 18:25:40,685 [INFO] Setting up regions
+2024-02-21 18:25:40,735 [INFO] 92 --regions reduced to 92 after intersecting with 225 from --includebed
+2024-02-21 18:25:40,735 [INFO] Extending the regions by 100 bases
+2024-02-21 18:25:41,090 [INFO] 41 regions to be refined
+2024-02-21 18:25:41,096 [INFO] Preparing regions
+2024-02-21 18:25:41,101 [INFO] Extracting haplotypes
+2024-02-21 18:25:41,375 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:887: CoverageWarning:No data was collected. (no-data-collected)
+2024-02-21 18:25:41,377 [WARNING] /usr/local/lib/python3.10/dist-packages/coverage/control.py:887: CoverageWarning:No data was collected. (no-data-collected)
+2024-02-21 18:25:41,390 [INFO] Harmonizing variants
+2024-02-21 18:25:53,795 [INFO] Running bench
+2024-02-21 18:25:53,821 [INFO] Including 41 bed regions
+2024-02-21 18:25:54,241 [INFO] Zipped 3534 variants Counter({'base': 1767, 'comp': 1767})
+2024-02-21 18:25:54,242 [INFO] 41 chunks of 3534 variants Counter({'__filtered': 3188, 'base': 179, 'comp': 167})
+2024-02-21 18:25:54,642 [INFO] Finished refine