bio-vcf 0.0.3 → 0.7.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (22) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +145 -20
  3. data/VERSION +1 -1
  4. data/bin/bio-vcf +204 -62
  5. data/bio-vcf.gemspec +7 -3
  6. data/features/cli.feature +16 -0
  7. data/features/multisample.feature +10 -0
  8. data/features/sfilter.feature +60 -0
  9. data/features/step_definitions/cli-feature.rb +1 -1
  10. data/features/step_definitions/multisample.rb +32 -0
  11. data/features/step_definitions/sfilter.rb +90 -0
  12. data/lib/bio-vcf/utils.rb +12 -6
  13. data/lib/bio-vcf/vcfgenotypefield.rb +4 -1
  14. data/lib/bio-vcf/vcfheader.rb +24 -0
  15. data/lib/bio-vcf/vcfrdf.rb +15 -8
  16. data/lib/bio-vcf/vcfrecord.rb +45 -9
  17. data/lib/bio-vcf/vcfsample.rb +94 -5
  18. data/test/data/regression/sfilter_seval_s.dp.ref +31 -0
  19. data/test/data/regression/{sfilter001.ref → thread4.ref} +5 -0
  20. data/test/data/regression/thread4_4.ref +150 -0
  21. data/test/performance/metrics.md +53 -19
  22. metadata +7 -3
data/lib/bio-vcf/vcfsample.rb CHANGED
@@ -2,8 +2,7 @@ module BioVcf
2
2
  module VcfSample
3
3
 
4
4
  # Check whether a sample is empty (on the raw string value)
5
- def VcfSample::empty? raw_sample
6
- s = raw_sample.strip
5
+ def VcfSample::empty? s
7
6
  s == './.' or s == '' or s == nil
8
7
  end
9
8
 
@@ -16,6 +15,10 @@ module BioVcf
16
15
  @values = @sample.values
17
16
  end
18
17
 
18
+ def empty?
19
+ cache_empty ||= VcfSample::empty?(@sample.to_s)
20
+ end
21
+
19
22
  def eval expr, ignore_missing_data, quiet
20
23
  begin
21
24
  if not respond_to?(:call_cached_eval)
@@ -31,14 +34,100 @@ module BioVcf
31
34
  end
32
35
  call_cached_eval(@rec,self)
33
36
  rescue NoMethodError => e
34
- empty = VcfSample::empty?(@sample.values.to_s)
35
- $stderr.print "\nTrying to evaluate on an empty sample #{@sample.values.to_s}!\n" if not empty
37
+ $stderr.print "\nTrying to evaluate on an empty sample #{@sample.values.to_s}!\n" if not empty? and not quiet
38
+ if not quiet
39
+ $stderr.print [@format,@values],"\n"
40
+ $stderr.print expr,"\n"
41
+ end
42
+ if ignore_missing_data
43
+ $stderr.print e.message if not quiet and not empty?
44
+ return false
45
+ else
46
+ raise
47
+ end
48
+ end
49
+ end
50
+
51
+ def sfilter expr, ignore_missing_data, quiet
52
+ begin
53
+ if not respond_to?(:call_cached_sfilter)
54
+ code =
55
+ """
56
+ def call_cached_sfilter(rec,sample)
57
+ r = rec
58
+ s = sample
59
+ #{expr}
60
+ end
61
+ """
62
+ self.class.class_eval(code)
63
+ end
64
+ call_cached_sfilter(@rec,self)
65
+ rescue NoMethodError => e
66
+ $stderr.print "\nTrying to evaluate on an empty sample #{@sample.values.to_s}!\n" if not empty? and not quiet
67
+ if not quiet
68
+ $stderr.print [@format,@values],"\n"
69
+ $stderr.print expr,"\n"
70
+ end
71
+ if ignore_missing_data
72
+ $stderr.print e.message if not quiet and not empty?
73
+ return false
74
+ else
75
+ raise
76
+ end
77
+ end
78
+ end
79
+
80
+ def ifilter expr, ignore_missing_data, quiet
81
+ begin
82
+ if not respond_to?(:call_cached_ifilter)
83
+ code =
84
+ """
85
+ def call_cached_ifilter(rec,sample)
86
+ r = rec
87
+ s = sample
88
+ #{expr}
89
+ end
90
+ """
91
+ self.class.class_eval(code)
92
+ end
93
+ call_cached_ifilter(@rec,self)
94
+ rescue NoMethodError => e
95
+ $stderr.print "\nTrying to evaluate on an empty sample #{@sample.values.to_s}!\n" if not empty? and not quiet
96
+ if not quiet
97
+ $stderr.print [@format,@values],"\n"
98
+ $stderr.print expr,"\n"
99
+ end
100
+ if ignore_missing_data
101
+ $stderr.print e.message if not quiet and not empty?
102
+ return false
103
+ else
104
+ raise
105
+ end
106
+ end
107
+ end
108
+
109
+ def efilter expr, ignore_missing_data, quiet
110
+ begin
111
+ if not respond_to?(:call_cached_efilter)
112
+ code =
113
+ """
114
+ def call_cached_efilter(rec,sample)
115
+ r = rec
116
+ s = sample
117
+ #{expr}
118
+ end
119
+ """
120
+ self.class.class_eval(code)
121
+ end
122
+ call_cached_efilter(@rec,self)
123
+ rescue NoMethodError => e
124
+ $stderr.print "\nTrying to evaluate on an empty sample #{@sample.values.to_s}!\n" if not empty? and not quiet
36
125
  if not quiet
37
126
  $stderr.print [@format,@values],"\n"
38
127
  $stderr.print expr,"\n"
39
128
  end
40
129
  if ignore_missing_data
41
- $stderr.print e.message if not quiet and not empty
130
+ $stderr.print e.message if not quiet and not empty?
42
131
  return false
43
132
  else
44
133
  raise
data/test/data/regression/sfilter_seval_s.dp.ref ADDED
@@ -0,0 +1,31 @@
1
+ 1 10257 159 242 249 249 186 212 218
2
+ 1 10291 165 249 249 247 161 163 189
3
+ 1 10297 182 246 250 246 165 158 183
4
+ 1 10303 198 247 248 248 172 157 182
5
+ 1 10315 212 246 242 245 190 157 189
6
+ 1 10321 218 246 248 248 193 164 196
7
+ 1 10327 237 238 229 237 209 183 210
8
+ 1 12783 58 164 144 182 126 103 158
9
+ 1 13116 32 131 102 152 104 88 109
10
+ 1 13118 34 129 101 145 99 85 108
11
+ 1 13178 52 172 137 172 129 119 148
12
+ 1 13302 36 136 99 146 90 65 117
13
+ 1 13757 53 201 181 250 152 130 182
14
+ 1 13868 75 192 182 224 142 111 167
15
+ 1 13896 62 135 143 175 112 81 121
16
+ 1 14464 51 155 141 150 83 89 140
17
+ 1 14673 36 142 117 157 95 76 131
18
+ 1 14699 43 128 109 147 98 78 114
19
+ 1 14907 57 216 162 205 153 118 158
20
+ 1 14930 68 216 170 210 136 125 164
21
+ 1 14933 68 216 169 212 132 128 164
22
+ 1 14948 63 192 181 211 129 121 153
23
+ 1 14976 56 166 161 196 109 116 135
24
+ 1 15118 46 198 129 230 113 126 158
25
+ 1 15190 53 208 170 200 126 145 179
26
+ 1 15211 54 183 161 171 120 134 168
27
+ 1 15274 37 121 102 137 71 67 98
28
+ 1 15447 46 242 183 226 137 173 175
29
+ 1 15688 37 182 147 184 100 101 148
30
+ 1 16068 33 57 68 81 49 49 58
31
+ 1 16103 50 79 86 106 60 61 84
data/test/data/regression/{sfilter001.ref → thread4.ref} RENAMED
@@ -119,6 +119,10 @@
119
119
  1 10315 . C T 108.20 . AC=3;AF=0.214;AN=14;BaseQRankSum=-3.769;DP=1500;Dels=0.01;FS=1.493;HaplotypeScore=169.3933;MLEAC=3;MLEAF=0.214;MQ=26.95;MQ0=241;MQRankSum=-4.511;QD=0.19;ReadPosRankSum=2.373 GT:AD:DP:GQ:PL 0/1:181,26:212:41:41,0,618 0/0:223,17:246:99:0,102,832 0/0:219,20:242:66:0,66,924 0/0:217,23:245:99:0,109,1384 0/1:155,27:190:97:97,0,328 0/1:130,20:157:10:10,0,531 0/0:163,24:189:5:0,5,450
120
120
  1 10321 . C T 106.30 . AC=5;AF=0.357;AN=14;BaseQRankSum=3.045;DP=1537;Dels=0.01;FS=5.835;HaplotypeScore=220.1531;MLEAC=5;MLEAF=0.357;MQ=26.69;MQ0=258;MQRankSum=-4.870;QD=0.10;ReadPosRankSum=0.815 GT:AD:DP:GQ:PL 0/1:189,25:218:30:30,0,810 0/0:219,22:246:24:0,24,593 0/1:218,27:248:34:34,0,1134 0/0:220,22:248:56:0,56,1207 0/1:168,23:193:19:19,0,493 0/1:139,22:164:46:46,0,689 0/1:167,26:196:20:20,0,522
121
121
  1 10327 . T C 1215.15 . AC=7;AF=0.500;AN=14;BaseQRankSum=3.585;DP=1641;Dels=0.02;FS=6.639;HaplotypeScore=237.4339;MLEAC=7;MLEAF=0.500;MQ=25.22;MQ0=321;MQRankSum=4.402;QD=0.74;ReadPosRankSum=3.957 GT:AD:DP:GQ:PL 0/1:178,56:237:99:178,0,848 0/1:178,60:238:99:320,0,575 0/1:185,40:229:99:236,0,679 0/1:184,52:237:99:358,0,544 0/1:165,43:209:57:57,0,726 0/1:151,31:183:9:9,0,780 0/1:164,46:210:96:96,0,550
122
+ 1 10583 . G A 699.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-4.714;DP=129;Dels=0.00;FS=7.556;HaplotypeScore=0.6677;MLEAC=7;MLEAF=0.500;MQ=41.33;MQ0=2;MQRankSum=-2.309;QD=5.43;ReadPosRankSum=-0.296 GT:AD:DP:GQ:PL 0/1:5,3:8:58:58,0,133 0/1:12,12:24:99:231,0,287 0/1:16,4:21:38:38,0,491 0/1:19,4:23:57:57,0,494 0/1:9,6:15:99:140,0,180 0/1:11,8:19:99:173,0,235 0/1:15,4:19:42:42,0,344
123
+ 1 10665 . C G 56.61 . AC=2;AF=0.250;AN=8;BaseQRankSum=2.219;DP=28;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=0.250;MQ=25.41;MQ0=15;MQRankSum=0.185;QD=4.72;ReadPosRankSum=1.849 GT:AD:DP:GQ:PL ./. ./. 0/1:4,3:7:57:57,0,78 0/1:3,2:5:23:30,0,23 ./. 0/0:2,0:2:3:0,3,26 0/0:6,1:7:6:0,6,49
124
+ 1 10694 . C G 85.78 . AC=4;AF=1.00;AN=4;DP=22;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=4;MLEAF=1.00;MQ=17.21;MQ0=17;QD=8.58 GT:AD:DP:GQ:PL ./. ./. 1/1:2,3:5:6:74,6,0 1/1:3,2:5:3:35,3,0 ./. ./. ./.
125
+ 1 10723 . C G 73.85 . AC=4;AF=0.667;AN=6;BaseQRankSum=1.300;DP=18;Dels=0.00;FS=3.680;HaplotypeScore=0.0000;MLEAC=4;MLEAF=0.667;MQ=20.49;MQ0=11;MQRankSum=1.754;QD=8.21;ReadPosRankSum=0.000 GT:AD:DP:GQ:PL ./. ./. 1/1:2,2:4:6:66,6,0 1/1:4,1:5:3:36,3,0 ./. ./. 0/0:6,0:6:3:0,3,33
122
126
  1 12783 . G A 4330.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=12.671;DP=939;Dels=0.00;FS=0.000;HaplotypeScore=1.4998;MLEAC=7;MLEAF=0.500;MQ=14.64;MQ0=602;MQRankSum=-3.992;QD=4.61;ReadPosRankSum=0.195 GT:AD:DP:GQ:PL 0/1:24,34:58:82:174,0,82 0/1:80,84:164:99:658,0,433 0/1:59,85:144:99:670,0,407 0/1:68,114:182:99:1074,0,463 0/1:58,68:126:99:437,0,310 0/1:37,66:103:99:446,0,369 0/1:62,96:158:99:911,0,417
123
127
  1 13116 . T G 2592.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-5.563;DP=721;Dels=0.00;FS=381.256;HaplotypeScore=2.5606;MLEAC=7;MLEAF=0.500;MQ=23.97;MQ0=222;MQRankSum=-14.896;QD=3.60;ReadPosRankSum=3.079 GT:AD:DP:GQ:PL 0/1:20,12:32:92:92,0,300 0/1:84,47:131:99:479,0,1548 0/1:65,37:102:99:441,0,1153 0/1:94,57:152:99:584,0,1993 0/1:61,43:104:99:360,0,1199 0/1:54,33:88:99:221,0,986 0/1:62,47:109:99:455,0,1128
124
128
  1 13118 . A G 2317.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-9.647;DP=703;Dels=0.00;FS=362.380;HaplotypeScore=2.3393;MLEAC=7;MLEAF=0.500;MQ=23.54;MQ0=228;MQRankSum=-14.592;QD=3.30;ReadPosRankSum=3.437 GT:AD:DP:GQ:PL 0/1:21,13:34:95:95,0,277 0/1:82,47:129:99:444,0,1445 0/1:65,36:101:99:412,0,1179 0/1:92,53:145:99:455,0,1989 0/1:58,40:99:99:312,0,1216 0/1:52,33:85:99:186,0,1000 0/1:61,47:108:99:453,0,1079
@@ -127,6 +131,7 @@
127
131
  1 13757 . G A 271.89 . AC=2;AF=0.143;AN=14;BaseQRankSum=2.916;DP=1149;Dels=0.00;FS=11.172;HaplotypeScore=7.1466;MLEAC=2;MLEAF=0.143;MQ=18.17;MQ0=374;MQRankSum=3.990;QD=0.87;ReadPosRankSum=1.309 GT:AD:DP:GQ:PL 0/0:47,4:53:16:0,16,344 0/0:185,16:201:60:0,60,2690 0/1:157,24:181:99:162,0,2556 0/0:232,18:250:99:0,137,3600 0/0:139,13:152:15:0,15,2266 0/1:114,16:130:99:147,0,1525 0/0:168,14:182:2:0,2,2230
128
132
  1 13868 . A G 1481.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=2.036;DP=1108;Dels=0.00;FS=4.601;HaplotypeScore=6.7136;MLEAC=7;MLEAF=0.500;MQ=13.23;MQ0=622;MQRankSum=1.659;QD=1.34;ReadPosRankSum=0.283 GT:AD:DP:GQ:PL 0/1:60,15:75:80:80,0,568 0/1:146,46:192:99:289,0,1030 0/1:146,36:182:99:203,0,1001 0/1:172,52:224:99:222,0,1150 0/1:106,36:142:99:181,0,621 0/1:79,32:111:99:126,0,467 0/1:129,38:167:99:420,0,767
129
133
  1 13896 . C A 389.42 . AC=6;AF=0.429;AN=14;BaseQRankSum=-0.743;DP=830;Dels=0.00;FS=0.000;HaplotypeScore=1.6931;MLEAC=6;MLEAF=0.429;MQ=11.88;MQ0=518;MQRankSum=-1.292;QD=0.54;ReadPosRankSum=0.433 GT:AD:DP:GQ:PL 0/1:50,12:62:99:107,0,367 0/1:107,28:135:40:40,0,660 0/1:120,23:143:37:37,0,675 0/1:144,31:175:99:172,0,690 0/0:98,14:112:42:0,42,577 0/1:65,16:81:34:34,0,290 0/1:102,19:121:41:41,0,677
134
+ 1 14354 . C A 109.72 . AC=3;AF=0.250;AN=12;BaseQRankSum=-2.527;DP=764;Dels=0.00;FS=0.000;HaplotypeScore=0.3231;MLEAC=3;MLEAF=0.250;MQ=5.02;MQ0=710;MQRankSum=1.079;QD=0.47;ReadPosRankSum=-0.178 GT:AD:DP:GQ:PL 0/1:36,7:43:68:68,0,75 0/0:141,17:158:9:0,9,86 0/1:103,12:115:42:42,0,72 0/0:132,13:145:21:0,21,201 ./. 0/1:62,10:72:38:38,0,117 0/0:108,11:119:9:0,9,86
130
135
  1 14464 . A T 3945.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=0.104;DP=809;Dels=0.00;FS=38.588;HaplotypeScore=5.8354;MLEAC=7;MLEAF=0.500;MQ=23.21;MQ0=241;MQRankSum=6.859;QD=4.88;ReadPosRankSum=-0.294 GT:AD:DP:GQ:PL 0/1:41,10:51:99:183,0,569 0/1:107,48:155:99:829,0,1388 0/1:99,42:141:99:691,0,1103 0/1:114,36:150:99:454,0,1544 0/1:48,35:83:99:781,0,561 0/1:64,25:89:99:409,0,781 0/1:102,38:140:99:638,0,1310
131
136
  1 14673 . G C 1012.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=3.674;DP=754;Dels=0.00;FS=115.496;HaplotypeScore=14.9167;MLEAC=7;MLEAF=0.500;MQ=23.97;MQ0=268;MQRankSum=-1.459;QD=1.34;ReadPosRankSum=-3.039 GT:AD:DP:GQ:PL 0/1:28,8:36:34:34,0,409 0/1:117,25:142:99:125,0,1964 0/1:87,30:117:99:214,0,1506 0/1:130,27:157:99:193,0,2076 0/1:77,18:95:99:114,0,1273 0/1:49,27:76:99:200,0,719 0/1:103,28:131:99:172,0,1620
132
137
  1 14699 . C G 64.65 . AC=2;AF=0.143;AN=14;BaseQRankSum=6.064;DP=719;Dels=0.00;FS=29.480;HaplotypeScore=5.5900;MLEAC=2;MLEAF=0.143;MQ=24.79;MQ0=233;MQRankSum=-8.066;QD=0.27;ReadPosRankSum=-0.696 GT:AD:DP:GQ:PL 0/0:35,6:43:51:0,51,720 0/1:91,37:128:59:59,0,1859 0/0:80,29:109:99:0,101,1700 0/0:113,34:147:14:0,14,1987 0/0:72,26:98:37:0,37,1319 0/0:53,25:78:78:0,78,1035 0/1:84,30:114:44:44,0,1326
data/test/data/regression/thread4_4.ref ADDED
@@ -0,0 +1,150 @@
1
+ ##fileformat=VCFv4.1
2
+ ##FILTER=<ID=LowQual,Description="Low quality">
3
+ ##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
4
+ ##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
5
+ ##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
6
+ ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
7
+ ##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
8
+ ##GATKCommandLine=<ID=UnifiedGenotyper,Version=2.8-1-g932cd3a,Date="Sat Jan 25 10:33:56 CET 2014",Epoch=1390642436187,CommandLineOptions="analysis_type=UnifiedGenotyper input_file=[/data_fedor12/BAM/sander/Liver_clones/BIOPSY17513D/mapping/BIOPSY17513D_dedup_realigned_recalibrated.bam, /data_fedor12/BAM/sander/Liver_clones/clone3/mapping/clone3_dedup_realigned_recalibrated.bam, /data_fedor12/BAM/sander/Liver_clones/clone4/mapping/clone4_dedup_realigned_recalibrated.bam, /data_fedor12/BAM/sander/Liver_clones/clone10/mapping/clone10_dedup_realigned_recalibrated.bam, /data_fedor12/BAM/sander/Liver_clones/subclone33/mapping/subclone33_dedup_realigned_recalibrated.bam, /data_fedor12/BAM/sander/Liver_clones/subclone46/mapping/subclone46_dedup_realigned_recalibrated.bam, /data_fedor12/BAM/sander/Liver_clones/subclone105/mapping/subclone105_dedup_realigned_recalibrated.bam] read_buffer_size=null phone_home=AWS gatk_key=null tag=NA read_filter=[] intervals=[/data_fedor13/sander/variant_calling/Liver_clones/.queue/scatterGather/UnifiedGenotyper_noref-1-sg/temp_001_of_500/scatter.intervals] excludeIntervals=null interval_set_rule=UNION interval_merging=ALL interval_padding=0 reference_sequence=/data_fedor13/common_data/references/H_sapiens/GATK_b37_bundle_reference/basespace/human_g1k_v37.fasta nonDeterministicRandomSeed=false disableDithering=false maxRuntime=-1 maxRuntimeUnits=MINUTES downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 fix_misencoded_quality_scores=false allow_potentially_misencoded_quality_scores=false useOriginalQualities=false defaultBaseQualities=-1 performanceLog=null BQSR=null quantize_quals=0 disable_indel_quals=false emit_original_quals=false preserve_qscores_less_than=6 globalQScorePrior=-1.0 allow_bqsr_on_reduced_bams_despite_repeated_warnings=false validation_strictness=SILENT remove_program_records=false keep_program_records=false sample_rename_mapping_file=null unsafe=null disable_auto_index_creation_and_locking_when_reading_rods=false num_threads=1 num_cpu_threads_per_data_thread=1 num_io_threads=0 monitorThreadEfficiency=false num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false generateShadowBCF=false variant_index_type=DYNAMIC_SEEK variant_index_parameter=-1 logging_level=INFO log_to_file=null help=false version=false genotype_likelihoods_model=SNP pcr_error_rate=1.0E-4 computeSLOD=false annotateNDA=false pair_hmm_implementation=LOGLESS_CACHING min_base_quality_score=17 max_deletion_fraction=0.05 allSitePLs=false min_indel_count_for_genotyping=5 min_indel_fraction_per_sample=0.25 indelGapContinuationPenalty=10 indelGapOpenPenalty=45 indelHaplotypeSize=80 indelDebug=false ignoreSNPAlleles=false allReadsSP=false ignoreLaneInfo=false reference_sample_calls=(RodBinding name= source=UNBOUND) reference_sample_name=null sample_ploidy=2 min_quality_score=1 max_quality_score=40 site_quality_prior=20 min_power_threshold_for_calling=0.95 min_reference_depth=100 exclude_filtered_reference_sites=false output_mode=EMIT_VARIANTS_ONLY heterozygosity=0.001 indel_heterozygosity=1.25E-4 genotyping_mode=DISCOVERY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 alleles=(RodBinding name= source=UNBOUND) max_alternate_alleles=6 input_prior=[] contamination_fraction_to_filter=0.0 contamination_fraction_per_sample_file=null p_nonref_model=EXACT_INDEPENDENT exactcallslog=null dbsnp=(RodBinding name= source=UNBOUND) comp=[] out=org.broadinstitute.sting.gatk.io.stubs.VariantContextWriterStub no_cmdline_in_header=org.broadinstitute.sting.gatk.io.stubs.VariantContextWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VariantContextWriterStub bcf=org.broadinstitute.sting.gatk.io.stubs.VariantContextWriterStub onlyEmitSamples=[] debug_file=null metrics_file=null annotation=[] excludeAnnotation=[] filter_reads_with_N_cigar=false filter_mismatching_base_and_quals=false filter_bases_not_stored=false">
9
+ ##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
10
+ ##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
11
+ ##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
12
+ ##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
13
+ ##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
14
+ ##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
15
+ ##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">
16
+ ##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
17
+ ##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
18
+ ##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
19
+ ##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
20
+ ##INFO=<ID=MLEAF,Number=A,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
21
+ ##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
22
+ ##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">
23
+ ##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
24
+ ##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
25
+ ##INFO=<ID=RPA,Number=.,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
26
+ ##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
27
+ ##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
28
+ ##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
29
+ ##contig=<ID=1,length=249250621,assembly=b37>
30
+ ##contig=<ID=2,length=243199373,assembly=b37>
31
+ ##contig=<ID=3,length=198022430,assembly=b37>
32
+ ##contig=<ID=4,length=191154276,assembly=b37>
33
+ ##contig=<ID=5,length=180915260,assembly=b37>
34
+ ##contig=<ID=6,length=171115067,assembly=b37>
35
+ ##contig=<ID=7,length=159138663,assembly=b37>
36
+ ##contig=<ID=8,length=146364022,assembly=b37>
37
+ ##contig=<ID=9,length=141213431,assembly=b37>
38
+ ##contig=<ID=10,length=135534747,assembly=b37>
39
+ ##contig=<ID=11,length=135006516,assembly=b37>
40
+ ##contig=<ID=12,length=133851895,assembly=b37>
41
+ ##contig=<ID=13,length=115169878,assembly=b37>
42
+ ##contig=<ID=14,length=107349540,assembly=b37>
43
+ ##contig=<ID=15,length=102531392,assembly=b37>
44
+ ##contig=<ID=16,length=90354753,assembly=b37>
45
+ ##contig=<ID=17,length=81195210,assembly=b37>
46
+ ##contig=<ID=18,length=78077248,assembly=b37>
47
+ ##contig=<ID=19,length=59128983,assembly=b37>
48
+ ##contig=<ID=20,length=63025520,assembly=b37>
49
+ ##contig=<ID=21,length=48129895,assembly=b37>
50
+ ##contig=<ID=22,length=51304566,assembly=b37>
51
+ ##contig=<ID=X,length=155270560,assembly=b37>
52
+ ##contig=<ID=Y,length=59373566,assembly=b37>
53
+ ##contig=<ID=MT,length=16569,assembly=b37>
54
+ ##contig=<ID=GL000207.1,length=4262,assembly=b37>
55
+ ##contig=<ID=GL000226.1,length=15008,assembly=b37>
56
+ ##contig=<ID=GL000229.1,length=19913,assembly=b37>
57
+ ##contig=<ID=GL000231.1,length=27386,assembly=b37>
58
+ ##contig=<ID=GL000210.1,length=27682,assembly=b37>
59
+ ##contig=<ID=GL000239.1,length=33824,assembly=b37>
60
+ ##contig=<ID=GL000235.1,length=34474,assembly=b37>
61
+ ##contig=<ID=GL000201.1,length=36148,assembly=b37>
62
+ ##contig=<ID=GL000247.1,length=36422,assembly=b37>
63
+ ##contig=<ID=GL000245.1,length=36651,assembly=b37>
64
+ ##contig=<ID=GL000197.1,length=37175,assembly=b37>
65
+ ##contig=<ID=GL000203.1,length=37498,assembly=b37>
66
+ ##contig=<ID=GL000246.1,length=38154,assembly=b37>
67
+ ##contig=<ID=GL000249.1,length=38502,assembly=b37>
68
+ ##contig=<ID=GL000196.1,length=38914,assembly=b37>
69
+ ##contig=<ID=GL000248.1,length=39786,assembly=b37>
70
+ ##contig=<ID=GL000244.1,length=39929,assembly=b37>
71
+ ##contig=<ID=GL000238.1,length=39939,assembly=b37>
72
+ ##contig=<ID=GL000202.1,length=40103,assembly=b37>
73
+ ##contig=<ID=GL000234.1,length=40531,assembly=b37>
74
+ ##contig=<ID=GL000232.1,length=40652,assembly=b37>
75
+ ##contig=<ID=GL000206.1,length=41001,assembly=b37>
76
+ ##contig=<ID=GL000240.1,length=41933,assembly=b37>
77
+ ##contig=<ID=GL000236.1,length=41934,assembly=b37>
78
+ ##contig=<ID=GL000241.1,length=42152,assembly=b37>
79
+ ##contig=<ID=GL000243.1,length=43341,assembly=b37>
80
+ ##contig=<ID=GL000242.1,length=43523,assembly=b37>
81
+ ##contig=<ID=GL000230.1,length=43691,assembly=b37>
82
+ ##contig=<ID=GL000237.1,length=45867,assembly=b37>
83
+ ##contig=<ID=GL000233.1,length=45941,assembly=b37>
84
+ ##contig=<ID=GL000204.1,length=81310,assembly=b37>
85
+ ##contig=<ID=GL000198.1,length=90085,assembly=b37>
86
+ ##contig=<ID=GL000208.1,length=92689,assembly=b37>
87
+ ##contig=<ID=GL000191.1,length=106433,assembly=b37>
88
+ ##contig=<ID=GL000227.1,length=128374,assembly=b37>
89
+ ##contig=<ID=GL000228.1,length=129120,assembly=b37>
90
+ ##contig=<ID=GL000214.1,length=137718,assembly=b37>
91
+ ##contig=<ID=GL000221.1,length=155397,assembly=b37>
92
+ ##contig=<ID=GL000209.1,length=159169,assembly=b37>
93
+ ##contig=<ID=GL000218.1,length=161147,assembly=b37>
94
+ ##contig=<ID=GL000220.1,length=161802,assembly=b37>
95
+ ##contig=<ID=GL000213.1,length=164239,assembly=b37>
96
+ ##contig=<ID=GL000211.1,length=166566,assembly=b37>
97
+ ##contig=<ID=GL000199.1,length=169874,assembly=b37>
98
+ ##contig=<ID=GL000217.1,length=172149,assembly=b37>
99
+ ##contig=<ID=GL000216.1,length=172294,assembly=b37>
100
+ ##contig=<ID=GL000215.1,length=172545,assembly=b37>
101
+ ##contig=<ID=GL000205.1,length=174588,assembly=b37>
102
+ ##contig=<ID=GL000219.1,length=179198,assembly=b37>
103
+ ##contig=<ID=GL000224.1,length=179693,assembly=b37>
104
+ ##contig=<ID=GL000223.1,length=180455,assembly=b37>
105
+ ##contig=<ID=GL000195.1,length=182896,assembly=b37>
106
+ ##contig=<ID=GL000212.1,length=186858,assembly=b37>
107
+ ##contig=<ID=GL000222.1,length=186861,assembly=b37>
108
+ ##contig=<ID=GL000200.1,length=187035,assembly=b37>
109
+ ##contig=<ID=GL000193.1,length=189789,assembly=b37>
110
+ ##contig=<ID=GL000194.1,length=191469,assembly=b37>
111
+ ##contig=<ID=GL000225.1,length=211173,assembly=b37>
112
+ ##contig=<ID=GL000192.1,length=547496,assembly=b37>
113
+ ##reference=file:human_g1k_v37.fasta
114
+ #CHROM POS ID REF ALT QUAL FILTER INFO FORMAT Original s1t1 s2t1 s3t1 s1t2 s2t2 s3t2
115
+ 1 10257 . A C 77.69 . AC=1;AF=0.071;AN=14;BaseQRankSum=-0.066;DP=1518;Dels=0.00;FS=24.214;HaplotypeScore=226.5209;MLEAC=1;MLEAF=0.071;MQ=25.00;MQ0=329;MQRankSum=-1.744;QD=0.37;ReadPosRankSum=1.551 GT:AD:DP:GQ:PL 0/0:151,8:159:99:0,195,2282 0/0:219,22:242:99:0,197,2445 0/0:227,22:249:90:0,90,2339 0/0:226,22:249:99:0,159,2695 0/0:166,18:186:99:0,182,1989 0/1:185,27:212:99:111,0,2387 0/0:201,15:218:24:0,24,1972
116
+ 1 10291 . C T 1031.89 . AC=7;AF=0.500;AN=14;BaseQRankSum=4.367;DP=1433;Dels=0.00;FS=0.696;HaplotypeScore=101.0885;MLEAC=7;MLEAF=0.500;MQ=26.96;MQ0=225;MQRankSum=0.087;QD=0.72;ReadPosRankSum=-1.640 GT:AD:DP:GQ:PL 0/1:145,16:165:23:23,0,491 0/1:218,26:249:29:29,0,611 0/1:214,30:249:99:145,0,801 0/1:213,32:247:20:20,0,1031 0/1:122,36:161:99:347,0,182 0/1:131,27:163:99:255,0,508 0/1:156,31:189:99:252,0,372
117
+ 1 10297 . C T 187.21 . AC=5;AF=0.357;AN=14;BaseQRankSum=-2.778;DP=1440;Dels=0.00;FS=0.000;HaplotypeScore=123.6373;MLEAC=5;MLEAF=0.357;MQ=27.26;MQ0=217;MQRankSum=-2.914;QD=0.18;ReadPosRankSum=1.927 GT:AD:DP:GQ:PL 0/1:155,18:182:44:44,0,654 0/1:218,23:246:21:21,0,673 0/1:219,26:250:41:41,0,898 0/0:207,30:246:39:0,39,963 0/0:137,20:165:21:0,21,363 0/1:124,27:158:65:65,0,435 0/1:151,27:183:63:63,0,485
118
+ 1 10303 . C T 166.50 . AC=3;AF=0.214;AN=14;BaseQRankSum=-3.960;DP=1460;Dels=0.00;FS=2.121;HaplotypeScore=138.0883;MLEAC=2;MLEAF=0.143;MQ=27.29;MQ0=220;MQRankSum=-2.873;QD=0.27;ReadPosRankSum=1.756 GT:AD:DP:GQ:PL 0/1:169,25:198:99:195,0,609 0/1:211,31:247:1:1,0,656 0/0:214,28:248:7:0,7,982 0/0:214,32:248:25:0,25,980 0/0:146,17:172:2:0,2,353 0/1:123,23:157:17:17,0,541 0/0:156,22:182:19:0,19,413
119
+ 1 10315 . C T 108.20 . AC=3;AF=0.214;AN=14;BaseQRankSum=-3.769;DP=1500;Dels=0.01;FS=1.493;HaplotypeScore=169.3933;MLEAC=3;MLEAF=0.214;MQ=26.95;MQ0=241;MQRankSum=-4.511;QD=0.19;ReadPosRankSum=2.373 GT:AD:DP:GQ:PL 0/1:181,26:212:41:41,0,618 0/0:223,17:246:99:0,102,832 0/0:219,20:242:66:0,66,924 0/0:217,23:245:99:0,109,1384 0/1:155,27:190:97:97,0,328 0/1:130,20:157:10:10,0,531 0/0:163,24:189:5:0,5,450
120
+ 1 10321 . C T 106.30 . AC=5;AF=0.357;AN=14;BaseQRankSum=3.045;DP=1537;Dels=0.01;FS=5.835;HaplotypeScore=220.1531;MLEAC=5;MLEAF=0.357;MQ=26.69;MQ0=258;MQRankSum=-4.870;QD=0.10;ReadPosRankSum=0.815 GT:AD:DP:GQ:PL 0/1:189,25:218:30:30,0,810 0/0:219,22:246:24:0,24,593 0/1:218,27:248:34:34,0,1134 0/0:220,22:248:56:0,56,1207 0/1:168,23:193:19:19,0,493 0/1:139,22:164:46:46,0,689 0/1:167,26:196:20:20,0,522
121
+ 1 10327 . T C 1215.15 . AC=7;AF=0.500;AN=14;BaseQRankSum=3.585;DP=1641;Dels=0.02;FS=6.639;HaplotypeScore=237.4339;MLEAC=7;MLEAF=0.500;MQ=25.22;MQ0=321;MQRankSum=4.402;QD=0.74;ReadPosRankSum=3.957 GT:AD:DP:GQ:PL 0/1:178,56:237:99:178,0,848 0/1:178,60:238:99:320,0,575 0/1:185,40:229:99:236,0,679 0/1:184,52:237:99:358,0,544 0/1:165,43:209:57:57,0,726 0/1:151,31:183:9:9,0,780 0/1:164,46:210:96:96,0,550
122
+ 1 10583 . G A 699.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-4.714;DP=129;Dels=0.00;FS=7.556;HaplotypeScore=0.6677;MLEAC=7;MLEAF=0.500;MQ=41.33;MQ0=2;MQRankSum=-2.309;QD=5.43;ReadPosRankSum=-0.296 GT:AD:DP:GQ:PL 0/1:5,3:8:58:58,0,133 0/1:12,12:24:99:231,0,287 0/1:16,4:21:38:38,0,491 0/1:19,4:23:57:57,0,494 0/1:9,6:15:99:140,0,180 0/1:11,8:19:99:173,0,235 0/1:15,4:19:42:42,0,344
123
+ 1 10665 . C G 56.61 . AC=2;AF=0.250;AN=8;BaseQRankSum=2.219;DP=28;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=0.250;MQ=25.41;MQ0=15;MQRankSum=0.185;QD=4.72;ReadPosRankSum=1.849 GT:AD:DP:GQ:PL ./. ./. 0/1:4,3:7:57:57,0,78 0/1:3,2:5:23:30,0,23 ./. 0/0:2,0:2:3:0,3,26 0/0:6,1:7:6:0,6,49
124
+ 1 10694 . C G 85.78 . AC=4;AF=1.00;AN=4;DP=22;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=4;MLEAF=1.00;MQ=17.21;MQ0=17;QD=8.58 GT:AD:DP:GQ:PL ./. ./. 1/1:2,3:5:6:74,6,0 1/1:3,2:5:3:35,3,0 ./. ./. ./.
125
+ 1 10723 . C G 73.85 . AC=4;AF=0.667;AN=6;BaseQRankSum=1.300;DP=18;Dels=0.00;FS=3.680;HaplotypeScore=0.0000;MLEAC=4;MLEAF=0.667;MQ=20.49;MQ0=11;MQRankSum=1.754;QD=8.21;ReadPosRankSum=0.000 GT:AD:DP:GQ:PL ./. ./. 1/1:2,2:4:6:66,6,0 1/1:4,1:5:3:36,3,0 ./. ./. 0/0:6,0:6:3:0,3,33
126
+ 1 12783 . G A 4330.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=12.671;DP=939;Dels=0.00;FS=0.000;HaplotypeScore=1.4998;MLEAC=7;MLEAF=0.500;MQ=14.64;MQ0=602;MQRankSum=-3.992;QD=4.61;ReadPosRankSum=0.195 GT:AD:DP:GQ:PL 0/1:24,34:58:82:174,0,82 0/1:80,84:164:99:658,0,433 0/1:59,85:144:99:670,0,407 0/1:68,114:182:99:1074,0,463 0/1:58,68:126:99:437,0,310 0/1:37,66:103:99:446,0,369 0/1:62,96:158:99:911,0,417
127
+ 1 13116 . T G 2592.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-5.563;DP=721;Dels=0.00;FS=381.256;HaplotypeScore=2.5606;MLEAC=7;MLEAF=0.500;MQ=23.97;MQ0=222;MQRankSum=-14.896;QD=3.60;ReadPosRankSum=3.079 GT:AD:DP:GQ:PL 0/1:20,12:32:92:92,0,300 0/1:84,47:131:99:479,0,1548 0/1:65,37:102:99:441,0,1153 0/1:94,57:152:99:584,0,1993 0/1:61,43:104:99:360,0,1199 0/1:54,33:88:99:221,0,986 0/1:62,47:109:99:455,0,1128
128
+ 1 13118 . A G 2317.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-9.647;DP=703;Dels=0.00;FS=362.380;HaplotypeScore=2.3393;MLEAC=7;MLEAF=0.500;MQ=23.54;MQ0=228;MQRankSum=-14.592;QD=3.30;ReadPosRankSum=3.437 GT:AD:DP:GQ:PL 0/1:21,13:34:95:95,0,277 0/1:82,47:129:99:444,0,1445 0/1:65,36:101:99:412,0,1179 0/1:92,53:145:99:455,0,1989 0/1:58,40:99:99:312,0,1216 0/1:52,33:85:99:186,0,1000 0/1:61,47:108:99:453,0,1079
129
+ 1 13178 . G A 72.69 . AC=2;AF=0.143;AN=14;BaseQRankSum=-2.194;DP=929;Dels=0.00;FS=8.154;HaplotypeScore=1.8585;MLEAC=2;MLEAF=0.143;MQ=13.49;MQ0=590;MQRankSum=-3.030;QD=0.38;ReadPosRankSum=-0.383 GT:AD:DP:GQ:PL 0/1:49,3:52:11:11,0,292 0/0:161,11:172:60:0,60,1328 0/1:122,15:137:99:99,0,936 0/0:164,8:172:99:0,112,1436 0/0:120,9:129:62:0,62,771 0/0:113,6:119:12:0,12,885 0/0:138,10:148:99:0,112,1596
130
+ 1 13302 . C T 1067.42 . AC=6;AF=0.429;AN=14;BaseQRankSum=11.584;DP=692;Dels=0.00;FS=86.736;HaplotypeScore=2.8260;MLEAC=6;MLEAF=0.429;MQ=27.08;MQ0=150;MQRankSum=-14.794;QD=1.63;ReadPosRankSum=-9.193 GT:AD:DP:GQ:PL 0/0:26,10:36:41:0,41,616 0/1:91,45:136:99:183,0,2085 0/1:71,28:99:86:86,0,1557 0/1:96,50:146:99:333,0,2098 0/1:55,34:90:99:283,0,1321 0/1:47,18:65:99:157,0,943 0/1:89,28:117:67:67,0,1921
131
+ 1 13757 . G A 271.89 . AC=2;AF=0.143;AN=14;BaseQRankSum=2.916;DP=1149;Dels=0.00;FS=11.172;HaplotypeScore=7.1466;MLEAC=2;MLEAF=0.143;MQ=18.17;MQ0=374;MQRankSum=3.990;QD=0.87;ReadPosRankSum=1.309 GT:AD:DP:GQ:PL 0/0:47,4:53:16:0,16,344 0/0:185,16:201:60:0,60,2690 0/1:157,24:181:99:162,0,2556 0/0:232,18:250:99:0,137,3600 0/0:139,13:152:15:0,15,2266 0/1:114,16:130:99:147,0,1525 0/0:168,14:182:2:0,2,2230
132
+ 1 13868 . A G 1481.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=2.036;DP=1108;Dels=0.00;FS=4.601;HaplotypeScore=6.7136;MLEAC=7;MLEAF=0.500;MQ=13.23;MQ0=622;MQRankSum=1.659;QD=1.34;ReadPosRankSum=0.283 GT:AD:DP:GQ:PL 0/1:60,15:75:80:80,0,568 0/1:146,46:192:99:289,0,1030 0/1:146,36:182:99:203,0,1001 0/1:172,52:224:99:222,0,1150 0/1:106,36:142:99:181,0,621 0/1:79,32:111:99:126,0,467 0/1:129,38:167:99:420,0,767
133
+ 1 13896 . C A 389.42 . AC=6;AF=0.429;AN=14;BaseQRankSum=-0.743;DP=830;Dels=0.00;FS=0.000;HaplotypeScore=1.6931;MLEAC=6;MLEAF=0.429;MQ=11.88;MQ0=518;MQRankSum=-1.292;QD=0.54;ReadPosRankSum=0.433 GT:AD:DP:GQ:PL 0/1:50,12:62:99:107,0,367 0/1:107,28:135:40:40,0,660 0/1:120,23:143:37:37,0,675 0/1:144,31:175:99:172,0,690 0/0:98,14:112:42:0,42,577 0/1:65,16:81:34:34,0,290 0/1:102,19:121:41:41,0,677
134
+ 1 14354 . C A 109.72 . AC=3;AF=0.250;AN=12;BaseQRankSum=-2.527;DP=764;Dels=0.00;FS=0.000;HaplotypeScore=0.3231;MLEAC=3;MLEAF=0.250;MQ=5.02;MQ0=710;MQRankSum=1.079;QD=0.47;ReadPosRankSum=-0.178 GT:AD:DP:GQ:PL 0/1:36,7:43:68:68,0,75 0/0:141,17:158:9:0,9,86 0/1:103,12:115:42:42,0,72 0/0:132,13:145:21:0,21,201 ./. 0/1:62,10:72:38:38,0,117 0/0:108,11:119:9:0,9,86
135
+ 1 14464 . A T 3945.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=0.104;DP=809;Dels=0.00;FS=38.588;HaplotypeScore=5.8354;MLEAC=7;MLEAF=0.500;MQ=23.21;MQ0=241;MQRankSum=6.859;QD=4.88;ReadPosRankSum=-0.294 GT:AD:DP:GQ:PL 0/1:41,10:51:99:183,0,569 0/1:107,48:155:99:829,0,1388 0/1:99,42:141:99:691,0,1103 0/1:114,36:150:99:454,0,1544 0/1:48,35:83:99:781,0,561 0/1:64,25:89:99:409,0,781 0/1:102,38:140:99:638,0,1310
136
+ 1 14673 . G C 1012.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=3.674;DP=754;Dels=0.00;FS=115.496;HaplotypeScore=14.9167;MLEAC=7;MLEAF=0.500;MQ=23.97;MQ0=268;MQRankSum=-1.459;QD=1.34;ReadPosRankSum=-3.039 GT:AD:DP:GQ:PL 0/1:28,8:36:34:34,0,409 0/1:117,25:142:99:125,0,1964 0/1:87,30:117:99:214,0,1506 0/1:130,27:157:99:193,0,2076 0/1:77,18:95:99:114,0,1273 0/1:49,27:76:99:200,0,719 0/1:103,28:131:99:172,0,1620
137
+ 1 14699 . C G 64.65 . AC=2;AF=0.143;AN=14;BaseQRankSum=6.064;DP=719;Dels=0.00;FS=29.480;HaplotypeScore=5.5900;MLEAC=2;MLEAF=0.143;MQ=24.79;MQ0=233;MQRankSum=-8.066;QD=0.27;ReadPosRankSum=-0.696 GT:AD:DP:GQ:PL 0/0:35,6:43:51:0,51,720 0/1:91,37:128:59:59,0,1859 0/0:80,29:109:99:0,101,1700 0/0:113,34:147:14:0,14,1987 0/0:72,26:98:37:0,37,1319 0/0:53,25:78:78:0,78,1035 0/1:84,30:114:44:44,0,1326
138
+ 1 14907 . A G 9688.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=3.299;DP=1083;Dels=0.00;FS=20.983;HaplotypeScore=11.4413;MLEAC=7;MLEAF=0.500;MQ=33.27;MQ0=51;MQRankSum=1.076;QD=8.95;ReadPosRankSum=0.653 GT:AD:DP:GQ:PL 0/1:27,30:57:99:603,0,550 0/1:117,99:216:99:2024,0,2888 0/1:91,71:162:99:1489,0,1990 0/1:119,86:205:99:1876,0,2588 0/1:100,53:153:99:1001,0,2297 0/1:59,59:118:99:1240,0,1241 0/1:91,67:158:99:1495,0,2003
139
+ 1 14930 . A G 8665.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-13.760;DP=1092;Dels=0.00;FS=17.240;HaplotypeScore=20.0469;MLEAC=7;MLEAF=0.500;MQ=34.72;MQ0=22;MQRankSum=1.127;QD=7.94;ReadPosRankSum=0.785 GT:AD:DP:GQ:PL 0/1:32,36:68:99:609,0,659 0/1:123,92:216:99:1636,0,3225 0/1:92,78:170:99:1449,0,2202 0/1:123,86:210:99:1748,0,3028 0/1:85,50:136:99:802,0,2117 0/1:62,63:125:99:1072,0,1437 0/1:92,71:164:99:1389,0,2055
140
+ 1 14933 . G A 248.54 . AC=3;AF=0.214;AN=14;BaseQRankSum=1.588;DP=1089;Dels=0.00;FS=14.333;HaplotypeScore=19.7793;MLEAC=3;MLEAF=0.214;MQ=34.91;MQ0=18;MQRankSum=1.439;QD=0.45;ReadPosRankSum=0.752 GT:AD:DP:GQ:PL 0/0:59,9:68:1:0,1,1361 0/1:192,24:216:99:125,0,4941 0/0:160,9:169:99:0,142,4118 0/1:191,21:212:39:39,0,4848 0/0:126,6:132:99:0,210,3367 0/1:113,15:128:99:124,0,2578 0/0:154,10:164:99:0,158,3934
141
+ 1 14948 . G A 570.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=9.167;DP=1050;Dels=0.00;FS=11.131;HaplotypeScore=6.4398;MLEAC=7;MLEAF=0.500;MQ=32.69;MQ0=53;MQRankSum=0.017;QD=0.54;ReadPosRankSum=-1.181 GT:AD:DP:GQ:PL 0/1:56,7:63:79:79,0,1134 0/1:168,24:192:70:70,0,3900 0/1:160,21:181:99:147,0,3515 0/1:188,23:211:57:57,0,4113 0/1:115,14:129:32:32,0,2406 0/1:103,18:121:99:173,0,2016 0/1:132,21:153:52:52,0,2861
142
+ 1 14976 . G A 195.07 . AC=3;AF=0.214;AN=14;BaseQRankSum=7.340;DP=939;Dels=0.00;FS=32.492;HaplotypeScore=4.6786;MLEAC=3;MLEAF=0.214;MQ=27.87;MQ0=167;MQRankSum=1.477;QD=0.53;ReadPosRankSum=-0.560 GT:AD:DP:GQ:PL 0/1:50,6:56:12:12,0,929 0/0:152,14:166:81:0,81,3159 0/0:152,9:161:99:0,113,2885 0/1:174,22:196:99:127,0,3211 0/0:100,9:109:97:0,97,1900 0/1:103,13:116:97:97,0,1548 0/0:122,13:135:55:0,55,2246
143
+ 1 15118 . A G 2503.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-5.645;DP=1004;Dels=0.00;FS=0.313;HaplotypeScore=4.1078;MLEAC=7;MLEAF=0.500;MQ=21.49;MQ0=207;MQRankSum=-0.007;QD=2.49;ReadPosRankSum=-0.291 GT:AD:DP:GQ:PL 0/1:38,8:46:50:50,0,575 0/1:148,50:198:99:671,0,2598 0/1:97,32:129:99:358,0,1911 0/1:176,53:230:99:700,0,2989 0/1:91,19:113:99:146,0,1741 0/1:92,31:126:99:347,0,1543 0/1:126,30:158:99:271,0,2193
144
+ 1 15190 . G A 2564.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=11.094;DP=1090;Dels=0.00;FS=0.297;HaplotypeScore=4.3151;MLEAC=7;MLEAF=0.500;MQ=26.11;MQ0=187;MQRankSum=-0.724;QD=2.35;ReadPosRankSum=0.530 GT:AD:DP:GQ:PL 0/1:42,11:53:99:177,0,696 0/1:157,51:208:99:839,0,3145 0/1:142,28:170:91:91,0,2919 0/1:160,40:200:99:499,0,2815 0/1:109,17:126:99:167,0,2363 0/1:111,34:145:99:554,0,2268 0/1:141,38:179:99:277,0,2827
145
+ 1 15211 . T G 14032.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-11.292;DP=992;Dels=0.00;FS=0.281;HaplotypeScore=11.0809;MLEAC=7;MLEAF=0.500;MQ=27.20;MQ0=159;MQRankSum=3.859;QD=14.15;ReadPosRankSum=-1.972 GT:AD:DP:GQ:PL 0/1:19,35:54:99:858,0,183 0/1:63,120:183:99:2771,0,960 0/1:50,111:161:99:2213,0,740 0/1:58,113:171:99:2326,0,685 0/1:39,81:120:99:1707,0,678 0/1:38,96:134:99:2126,0,499 0/1:61,107:168:99:2071,0,895
146
+ 1 15274 . A G,T 8909.81 . AC=7,7;AF=0.500,0.500;AN=14;BaseQRankSum=2.416;DP=636;Dels=0.00;FS=0.000;HaplotypeScore=5.1061;MLEAC=7,7;MLEAF=0.500,0.500;MQ=22.77;MQ0=195;MQRankSum=2.299;QD=14.01;ReadPosRankSum=1.707 GT:AD:DP:GQ:PL 1/2:1,14,22:37:99:717,494,467,224,0,170 1/2:1,45,75:121:99:1922,1334,1265,588,0,441 1/2:0,31,71:102:99:1960,1563,1515,396,0,222 1/2:1,59,77:137:99:2009,1376,1298,633,0,486 1/2:0,18,52:71:62:938,789,771,149,0,62 1/2:0,29,38:67:99:1141,883,853,258,0,162 1/2:0,38,60:98:99:1464,1064,1016,399,0,285
147
+ 1 15447 . A G 109.56 . AC=3;AF=0.214;AN=14;BaseQRankSum=-9.704;DP=1213;Dels=0.00;FS=0.000;HaplotypeScore=16.4636;MLEAC=3;MLEAF=0.214;MQ=19.12;MQ0=346;MQRankSum=-0.997;QD=0.20;ReadPosRankSum=-1.088 GT:AD:DP:GQ:PL 0/0:42,4:46:34:0,34,690 0/0:220,22:242:99:0,99,3639 0/0:167,16:183:42:0,42,2582 0/1:201,25:226:78:78,0,2854 0/1:121,16:137:39:39,0,1877 0/0:160,13:173:99:0,139,2724 0/1:157,18:175:34:34,0,2472
148
+ 1 15688 . C T 54.29 . AC=2;AF=0.143;AN=14;BaseQRankSum=-8.686;DP=904;Dels=0.00;FS=11.971;HaplotypeScore=3.1454;MLEAC=2;MLEAF=0.143;MQ=16.75;MQ0=361;MQRankSum=-0.069;QD=0.16;ReadPosRankSum=0.355 GT:AD:DP:GQ:PL 0/0:34,3:37:15:0,15,335 0/0:166,16:182:61:0,61,2190 0/1:131,16:147:69:69,0,1563 0/1:167,17:184:22:22,0,1894 0/0:88,12:100:15:0,15,1099 0/0:88,13:101:1:0,1,1126 0/0:132,16:148:18:0,18,1706
149
+ 1 16068 . T C 377.22 . AC=4;AF=0.286;AN=14;BaseQRankSum=-7.618;DP=398;Dels=0.00;FS=12.349;HaplotypeScore=1.8069;MLEAC=4;MLEAF=0.286;MQ=26.64;MQ0=64;MQRankSum=-4.589;QD=1.80;ReadPosRankSum=-0.448 GT:AD:DP:GQ:PL 0/1:18,15:33:99:182,0,404 0/0:51,6:57:31:0,31,815 0/1:52,16:68:64:64,0,1101 0/0:68,13:81:99:0,99,1505 0/0:41,8:49:51:0,51,1010 0/1:40,9:49:21:21,0,702 0/1:38,19:58:99:153,0,760
150
+ 1 16103 . T G 2348.85 . AC=7;AF=0.500;AN=14;BaseQRankSum=-1.646;DP=526;Dels=0.00;FS=2.577;HaplotypeScore=0.9645;MLEAC=7;MLEAF=0.500;MQ=26.64;MQ0=82;MQRankSum=-2.736;QD=4.47;ReadPosRankSum=-2.044 GT:AD:DP:GQ:PL 0/1:21,29:50:99:504,0,450 0/1:55,24:79:99:209,0,838 0/1:49,37:86:99:456,0,1002 0/1:74,32:106:99:193,0,1519 0/1:41,19:60:99:141,0,740 0/1:38,23:61:99:257,0,548 0/1:38,46:84:99:628,0,641
data/test/performance/metrics.md CHANGED
@@ -42,19 +42,19 @@ Cache sample index
42
42
 
43
43
  Run the profiler
44
44
 
45
- ruby -rprofile ./bin/bio-vcf -i --filter 'r.info.dp>20' --sfilter 's.dp>10' < test/tmp/test.vcf > /dev/null
46
- vcf 0.0.3-pre4 (biogem Ruby 2.1.0) by Pjotr Prins 2014
47
- Options: {:show_help=>false, :ignore_missing=>true, :filter=>"r.info.dp>20", :sfilter=>"s.dp>10"}
48
- % cumulative self self total
49
- time seconds seconds calls ms/call ms/call name
50
- 9.45 2.19 2.19 34968 0.06 0.76 Object#parse_line
51
- 7.25 3.87 1.68 75031 0.02 0.03 BioVcf::VcfRecordInfo#[]=
52
- 7.12 5.52 1.65 34968 0.05 0.29 Kernel.eval
53
- 6.86 7.11 1.59 87481 0.02 0.10 BioVcf::VcfRecordInfo#initialize
54
- 5.57 8.40 1.29 35994 0.04 0.47 Array#each
55
- 4.14 9.36 0.96 34253 0.03 0.65 BioVcf::VcfRecord#each_sample
56
- 3.93 10.27 0.91 93880 0.01 0.03 BioVcf::VcfRecordParser.get_format
57
- 3.88 11.17 0.90 145920 0.01 0.01 String#split
45
+ ruby -rprofile ./bin/bio-vcf -i --filter 'r.info.dp>20' --sfilter 's.dp>10' < test/tmp/test.vcf > /dev/null
46
+ vcf 0.0.3-pre4 (biogem Ruby 2.1.0) by Pjotr Prins 2014
47
+ Options: {:show_help=>false, :ignore_missing=>true, :filter=>"r.info.dp>20", :sfilter=>"s.dp>10"}
48
+ % cumulative self self total
49
+ time seconds seconds calls ms/call ms/call name
50
+ 9.45 2.19 2.19 34968 0.06 0.76 Object#parse_line
51
+ 7.25 3.87 1.68 75031 0.02 0.03 BioVcf::VcfRecordInfo#[]=
52
+ 7.12 5.52 1.65 34968 0.05 0.29 Kernel.eval
53
+ 6.86 7.11 1.59 87481 0.02 0.10 BioVcf::VcfRecordInfo#initialize
54
+ 5.57 8.40 1.29 35994 0.04 0.47 Array#each
55
+ 4.14 9.36 0.96 34253 0.03 0.65 BioVcf::VcfRecord#each_sample
56
+ 3.93 10.27 0.91 93880 0.01 0.03 BioVcf::VcfRecordParser.get_format
57
+ 3.88 11.17 0.90 145920 0.01 0.01 String#split
58
58
 
59
59
  Late parsing of info field without split:
60
60
 
@@ -76,12 +76,12 @@ Assign some repeated Hash queries
76
76
 
77
77
  Profiler now picking out eval for further optimization
78
78
 
79
- % cumulative self self total
80
- time seconds seconds calls ms/call ms/call name
81
- 10.45 1.80 1.80 34968 0.05 0.59 Object#parse_line
82
- 7.89 3.16 1.36 34968 0.04 0.17 Kernel.eval
83
- 5.69 4.14 0.98 34253 0.03 0.57 BioVcf::VcfRecord#each_sample
84
- 4.93 4.99 0.85 12497 0.07 1.37 nil#
79
+ % cumulative self self total
80
+ time seconds seconds calls ms/call ms/call name
81
+ 10.45 1.80 1.80 34968 0.05 0.59 Object#parse_line
82
+ 7.89 3.16 1.36 34968 0.04 0.17 Kernel.eval
83
+ 5.69 4.14 0.98 34253 0.03 0.57 BioVcf::VcfRecord#each_sample
84
+ 4.93 4.99 0.85 12497 0.07 1.37 nil#
85
85
 
86
86
  Compiling sample eval
87
87
 
@@ -95,4 +95,38 @@ Compiling record eval
95
95
  user 0m0.644s
96
96
  sys 0m0.000s
97
97
 
98
+ Walk examples by index, rather than by name
99
+
100
+ real 0m0.612s
101
+ user 0m0.596s
102
+ sys 0m0.012s
103
+
104
+ More caching
105
+
106
+ real 0m0.600s
107
+ user 0m0.592s
108
+ sys 0m0.004s
109
+
110
+ And the latest profiling
111
+
112
+ % cumulative self self total
113
+ time seconds seconds calls ms/call ms/call name
114
+ 12.98 2.02 2.02 34968 0.06 0.51 Object#parse_line
115
+ 7.78 3.23 1.21 22518 0.05 0.14 BioVcf::VcfRecord#sample_by_index
116
+ 5.59 4.10 0.87 34253 0.03 0.47 BioVcf::VcfRecord#each_sample
117
+ 4.82 4.85 0.75 34968 0.02 0.03 BioVcf::ConvertStringToValue.integer?
118
+ 4.50 5.55 0.70 12450 0.06 0.13 BioVcf::VcfRecordInfo#method_missing
119
+ 4.31 6.22 0.67 69974 0.01 0.03 Class#new
120
+ 4.24 6.88 0.66 12499 0.05 1.23 nil#
121
+ 3.79 7.47 0.59 12450 0.05 0.06 BioVcf::VcfLine.parse
122
+
123
+ Introduced --num-threads
124
+
125
+ time ./bin/bio-vcf -i --num-threads --filter 'r.info.dp>20' --sfilter 's.dp>10' < test/tmp/test.vcf > /dev/null
126
+
127
+ on a dual-core running Linux
128
+
129
+ real 0m0.389s
130
+ user 0m1.132s
131
+ sys 0m0.148s
98
132
 
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: bio-vcf
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.3
4
+ version: 0.7.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Pjotr Prins
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2014-05-24 00:00:00.000000000 Z
11
+ date: 2014-06-24 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: rspec
@@ -87,11 +87,13 @@ files:
87
87
  - features/cli.feature
88
88
  - features/diff_count.feature
89
89
  - features/multisample.feature
90
+ - features/sfilter.feature
90
91
  - features/somaticsniper.feature
91
92
  - features/step_definitions/bio-vcf_steps.rb
92
93
  - features/step_definitions/cli-feature.rb
93
94
  - features/step_definitions/diff_count.rb
94
95
  - features/step_definitions/multisample.rb
96
+ - features/step_definitions/sfilter.rb
95
97
  - features/step_definitions/somaticsniper.rb
96
98
  - features/support/env.rb
97
99
  - lib/bio-vcf.rb
@@ -112,7 +114,9 @@ files:
112
114
  - test/data/regression/rewrite.info.sample.ref
113
115
  - test/data/regression/s.dp.ref
114
116
  - test/data/regression/seval_s.dp.ref
115
- - test/data/regression/sfilter001.ref
117
+ - test/data/regression/sfilter_seval_s.dp.ref
118
+ - test/data/regression/thread4.ref
119
+ - test/data/regression/thread4_4.ref
116
120
  - test/performance/metrics.md
117
121
  homepage: http://github.com/pjotrp/bioruby-vcf
118
122
  licenses: