Skip to content

Commit

Permalink
Fixing a bug in allele filtering (#7877)
Browse files Browse the repository at this point in the history
* [BIOIN-519] Looks like the alleles that were worse than the reference were not ordered correctly

* Tests updated
  • Loading branch information
ilyasoifer authored and jamesemery committed Jun 1, 2022
1 parent 0bc15ac commit 1ce04fd
Show file tree
Hide file tree
Showing 17 changed files with 202 additions and 190 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ int getAlleleLikelihoodVsInverse(final AlleleLikelihoods<GATKRead, Allele> allel
final int[] asPL = genotypingLikelihoods.sampleLikelihoods(0).getAsPLs();

logger.debug(() -> String.format("GAL:: %s: %d %d %d", allele.toString(), asPL[0], asPL[1], asPL[2]));
return (int)phredScaledConfidence;
return Math.min(asPL[1]-asPL[0], asPL[2]-asPL[0]);
}

}
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@
##INFO=<ID=RAW_MQandDP,Number=2,Type=Integer,Description="Raw data (sum of squared MQ and total depth) for improved RMS Mapping Quality calculation. Incompatible with deprecated RAW_MQ formulation.">
##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
##INFO=<ID=SUSP_NOISY_ADJACENT_TP_VARIANT,Number=0,Type=Flag,Description="Indicates a locus where false positive allele might be affecting a true positive allele">
##INFO=<ID=XC,Number=1,Type=Integer,Description="Indicates collapsing took place">
##INFO=<ID=XC,Number=1,Type=Integer,Description="Indicates longer hmer collapsing took place (this is a flow-based specific tag)">
##contig=<ID=chr1,length=248956422,assembly=38>
##contig=<ID=chr2,length=242193529,assembly=38>
##contig=<ID=chr3,length=198295559,assembly=38>
Expand Down Expand Up @@ -4674,10 +4674,14 @@ chr9 81156951 . T <NON_REF> . . END=81156987 GT:DP:GQ:MIN_DP:PL 0/0:42:99:37:0,1
chr9 81156988 . T <NON_REF> . . END=81156988 GT:DP:GQ:MIN_DP:PL 0/0:41:79:41:0,79,1731
chr9 81156989 . A <NON_REF> . . END=81157067 GT:DP:GQ:MIN_DP:PL 0/0:46:99:40:0,100,1560
chr9 81157068 . C <NON_REF> . . END=81157068 GT:DP:GQ:MIN_DP:PL 0/0:52:66:52:0,66,1938
chr9 81157069 . C <NON_REF> . . END=81157112 GT:DP:GQ:MIN_DP:PL 0/0:51:99:47:0,102,1705
chr9 81157113 . G <NON_REF> . . END=81157113 GT:DP:GQ:MIN_DP:PL 0/0:51:97:51:0,97,1361
chr9 81157114 . G <NON_REF> . . END=81157152 GT:DP:GQ:MIN_DP:PL 0/0:55:99:51:0,120,1800
chr9 81157153 . A <NON_REF> . . END=81157153 GT:DP:GQ:MIN_DP:PL 0/0:55:96:55:0,96,2280
chr9 81157069 . C <NON_REF> . . END=81157092 GT:DP:GQ:MIN_DP:PL 0/0:51:99:45:0,106,1800
chr9 81157093 . G <NON_REF> . . END=81157093 GT:DP:GQ:MIN_DP:PL 0/0:44:87:44:0,87,1547
chr9 81157094 . G <NON_REF> . . END=81157097 GT:DP:GQ:MIN_DP:PL 0/0:45:99:44:0,120,1800
chr9 81157098 . T TG,<NON_REF> 27.60 . ASSEMBLED_HAPS=24;BaseQRankSum=-1.149;DP=48;ExcessHet=0.0000;FILTERED_HAPS=22;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.000;RAW_MQandDP=172800,48;ReadPosRankSum=-0.312 GT:AD:DP:GQ:PL:SB 0/1:33,11,0:44:35:35,0,652,129,678,807:16,17,10,1
chr9 81157099 . G <NON_REF> . . END=81157112 GT:DP:GQ:MIN_DP:PL 0/0:47:99:44:0,115,1466
chr9 81157113 . G <NON_REF> . . END=81157113 GT:DP:GQ:MIN_DP:PL 0/0:44:87:44:0,87,1232
chr9 81157114 . G <NON_REF> . . END=81157152 GT:DP:GQ:MIN_DP:PL 0/0:48:99:44:0,107,1800
chr9 81157153 . A <NON_REF> . . END=81157153 GT:DP:GQ:MIN_DP:PL 0/0:48:75:48:0,75,1990
chr9 81157154 . T <NON_REF> . . END=81157501 GT:DP:GQ:MIN_DP:PL 0/0:64:99:53:0,114,1800
chr9 81157502 . T <NON_REF> . . END=81157502 GT:DP:GQ:MIN_DP:PL 0/0:55:97:55:0,97,2304
chr9 81157503 . G <NON_REF> . . END=81157518 GT:DP:GQ:MIN_DP:PL 0/0:51:99:49:0,103,1800
Expand Down Expand Up @@ -5693,8 +5697,10 @@ chr9 81164856 . G <NON_REF> . . END=81164856 GT:DP:GQ:MIN_DP:PL 0/0:46:94:46:0,9
chr9 81164857 . G <NON_REF> . . END=81164871 GT:DP:GQ:MIN_DP:PL 0/0:47:99:46:0,107,1800
chr9 81164872 . A <NON_REF> . . END=81164872 GT:DP:GQ:MIN_DP:PL 0/0:46:98:46:0,98,1686
chr9 81164873 . A <NON_REF> . . END=81165191 GT:DP:GQ:MIN_DP:PL 0/0:51:99:45:0,100,1800
chr9 81165192 . C <NON_REF> . . END=81165192 GT:DP:GQ:MIN_DP:PL 0/0:48:73:48:0,73,1827
chr9 81165193 . T <NON_REF> . . END=81165233 GT:DP:GQ:MIN_DP:PL 0/0:46:99:43:0,100,1505
chr9 81165192 . C <NON_REF> . . END=81165192 GT:DP:GQ:MIN_DP:PL 0/0:47:70:47:0,70,1783
chr9 81165193 . T <NON_REF> . . END=81165211 GT:DP:GQ:MIN_DP:PL 0/0:45:99:42:0,117,1461
chr9 81165212 . C CAG,<NON_REF> 29.60 . ASSEMBLED_HAPS=24;BaseQRankSum=-0.087;DP=47;ExcessHet=0.0000;FILTERED_HAPS=22;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.509;RAW_MQandDP=166105,47;ReadPosRankSum=-2.369;SUSP_NOISY_ADJACENT_TP_VARIANT GT:AD:DP:GQ:PL:SB 0/1:40,4,0:44:37:37,0,1635,158,1647,1805:22,18,4,0
chr9 81165213 . G <NON_REF> . . END=81165233 GT:DP:GQ:MIN_DP:PL 0/0:46:99:44:0,120,1800
chr9 81165234 . T <NON_REF> . . END=81165234 GT:DP:GQ:MIN_DP:PL 0/0:46:59:46:0,59,1774
chr9 81165235 . C <NON_REF> . . END=81165253 GT:DP:GQ:MIN_DP:PL 0/0:46:99:43:0,100,1737
chr9 81165254 . A <NON_REF> . . END=81165254 GT:DP:GQ:MIN_DP:PL 0/0:44:97:44:0,97,1755
Expand Down Expand Up @@ -6601,12 +6607,12 @@ chr9 81171245 . A <NON_REF> . . END=81171245 GT:DP:GQ:MIN_DP:PL 0/0:22:21:22:0,2
chr9 81171246 . A <NON_REF> . . END=81171250 GT:DP:GQ:MIN_DP:PL 0/0:22:60:22:0,60,900
chr9 81171251 . T <NON_REF> . . END=81171251 GT:DP:GQ:MIN_DP:PL 0/0:24:27:24:0,27,957
chr9 81171252 . A <NON_REF> . . END=81171253 GT:DP:GQ:MIN_DP:PL 0/0:20:51:20:0,51,765
chr9 81171254 . T <NON_REF> . . END=81171254 GT:DP:GQ:MIN_DP:PL 0/0:20:45:20:0,45,675
chr9 81171255 . AGTGTGTGTGTGTGT A,<NON_REF> 51.60 . ASSEMBLED_HAPS=12;BaseQRankSum=0.349;DP=24;ExcessHet=0.0000;FILTERED_HAPS=6;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.319;RAW_MQandDP=83956,24;ReadPosRankSum=1.876;SUSP_NOISY_ADJACENT_TP_VARIANT GT:AD:DP:GQ:PL:SB 0/1:9,3,0:12:59:59,0,304,85,311,397:6,3,1,2
chr9 81171254 . TA T,<NON_REF> 22.60 . ASSEMBLED_HAPS=12;BaseQRankSum=0.000;DP=20;ExcessHet=0.0000;FILTERED_HAPS=2;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.500;RAW_MQandDP=69556,20;ReadPosRankSum=-1.392;SUSP_NOISY_ADJACENT_TP_VARIANT GT:AD:DP:GQ:PL:SB 0/1:18,2,0:20:30:30,0,750,84,756,840:14,4,2,0
chr9 81171255 . AGTGTGTGTGTGTGT A,*,<NON_REF> 48.75 . ASSEMBLED_HAPS=12;BaseQRankSum=0.349;DP=24;ExcessHet=0.0000;FILTERED_HAPS=2;MLEAC=1,0,0;MLEAF=0.500,0.00,0.00;MQRankSum=0.502;RAW_MQandDP=83956,24;ReadPosRankSum=0.141;SUSP_NOISY_ADJACENT_TP_VARIANT GT:AD:DP:GQ:PL:SB 0/1:8,3,2,0:13:23:59,0,304,23,230,686,110,340,657,759:6,2,3,2
chr9 81171270 . G <NON_REF> . . END=81171275 GT:DP:GQ:MIN_DP:PL 0/0:22:24:19:0,24,360
chr9 81171276 . G <NON_REF> . . END=81171279 GT:DP:GQ:MIN_DP:PL 0/0:16:27:14:0,27,405
chr9 81171280 . G <NON_REF> . . END=81171288 GT:DP:GQ:MIN_DP:PL 0/0:15:33:12:0,33,495
chr9 81171289 . T G,<NON_REF> 108.64 . ASSEMBLED_HAPS=12;BaseQRankSum=0.000;DP=12;ExcessHet=0.0000;FILTERED_HAPS=6;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.000;RAW_MQandDP=43200,12;ReadPosRankSum=-0.493 GT:AD:DP:GQ:PL:SB 0/1:8,4,0:12:99:116,0,208,138,220,358:1,7,1,3
chr9 81171289 . T G,<NON_REF> 108.64 . ASSEMBLED_HAPS=12;BaseQRankSum=0.000;DP=12;ExcessHet=0.0000;FILTERED_HAPS=2;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.000;RAW_MQandDP=43200,12;ReadPosRankSum=-0.493 GT:AD:DP:GQ:PL:SB 0/1:8,4,0:12:99:116,0,208,138,220,358:1,7,1,3
chr9 81171290 . G <NON_REF> . . END=81171290 GT:DP:GQ:MIN_DP:PL 0/0:11:33:11:0,33,482
chr9 81171291 . G <NON_REF> . . END=81171291 GT:DP:GQ:MIN_DP:PL 0/0:12:11:12:0,11,420
chr9 81171292 . T <NON_REF> . . END=81171292 GT:DP:GQ:MIN_DP:PL 0/0:11:33:11:0,33,477
Expand All @@ -6630,7 +6636,7 @@ chr9 81171389 . T <NON_REF> . . END=81171389 GT:DP:GQ:MIN_DP:PL 0/0:19:12:19:0,1
chr9 81171390 . T <NON_REF> . . END=81171398 GT:DP:GQ:MIN_DP:PL 0/0:18:51:17:0,51,761
chr9 81171399 . G <NON_REF> . . END=81171399 GT:DP:GQ:MIN_DP:PL 0/0:16:48:16:0,48,687
chr9 81171400 . A <NON_REF> . . END=81171415 GT:DP:GQ:MIN_DP:PL 0/0:18:54:18:0,54,735
chr9 81171416 . C T,<NON_REF> 343.64 . ASSEMBLED_HAPS=12;BaseQRankSum=0.000;DP=19;ExcessHet=0.0000;FILTERED_HAPS=6;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.000;RAW_MQandDP=68400,19;ReadPosRankSum=-0.821 GT:AD:DP:GQ:PL:SB 0/1:9,9,0:18:99:351,0,351,378,378,756:4,5,2,7
chr9 81171416 . C T,<NON_REF> 343.64 . ASSEMBLED_HAPS=12;BaseQRankSum=0.000;DP=19;ExcessHet=0.0000;FILTERED_HAPS=2;MLEAC=1,0;MLEAF=0.500,0.00;MQRankSum=0.000;RAW_MQandDP=68400,19;ReadPosRankSum=-0.821 GT:AD:DP:GQ:PL:SB 0/1:9,9,0:18:99:351,0,351,378,378,756:4,5,2,7
chr9 81171417 . T <NON_REF> . . END=81171417 GT:DP:GQ:MIN_DP:PL 0/0:18:54:18:0,54,806
chr9 81171418 . G <NON_REF> . . END=81171424 GT:DP:GQ:MIN_DP:PL 0/0:19:57:19:0,57,830
chr9 81171425 . T <NON_REF> . . END=81171460 GT:DP:GQ:MIN_DP:PL 0/0:22:60:20:0,60,862
Expand Down
Binary file not shown.
Loading

0 comments on commit 1ce04fd

Please sign in to comment.