0.4.1 (#23)

* 📝 Add more examples regarding #20

* 🐛 Fix devpars by default a Namespace rather than a dict (#21, #22)

* 🔖 0.4.1

Co-authored-by: osdaf <[email protected]>

docs/CHANGELOG.md

@@ -1,3 +1,8 @@
+# 0.4.1
+
+- 📝 Add more examples regarding #20
+- 🐛 Fix devpars by default a Namespace rather than a dict (#21, #22)
+
 # 0.4.0
 
 - ⬆️ Drop support for python 3.8 (brentp/cyvcf2#181)

examples/multiallelic.vcf

@@ -0,0 +1,84 @@
+##fileformat=VCFv4.1
+##samtoolsVersion=0.1.18-r572
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth">
+##INFO=<ID=DP4,Number=4,Type=Integer,Description="# high-quality ref-forward bases, ref-reverse, alt-forward and alt-reverse bases">
+##INFO=<ID=MQ,Number=1,Type=Integer,Description="Root-mean-square mapping quality of covering reads">
+##INFO=<ID=FQ,Number=1,Type=Float,Description="Phred probability of all samples being the same">
+##INFO=<ID=AF1,Number=1,Type=Float,Description="Max-likelihood estimate of the first ALT allele frequency (assuming HWE)">
+##INFO=<ID=AC1,Number=1,Type=Float,Description="Max-likelihood estimate of the first ALT allele count (no HWE assumption)">
+##INFO=<ID=G3,Number=3,Type=Float,Description="ML estimate of genotype frequencies">
+##INFO=<ID=HWE,Number=1,Type=Float,Description="Chi^2 based HWE test P-value based on G3">
+##INFO=<ID=CLR,Number=1,Type=Integer,Description="Log ratio of genotype likelihoods with and without the constraint">
+##INFO=<ID=UGT,Number=1,Type=String,Description="The most probable unconstrained genotype configuration in the trio">
+##INFO=<ID=CGT,Number=1,Type=String,Description="The most probable constrained genotype configuration in the trio">
+##INFO=<ID=PV4,Number=4,Type=Float,Description="P-values for strand bias, baseQ bias, mapQ bias and tail distance bias">
+##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL.">
+##INFO=<ID=PC2,Number=2,Type=Integer,Description="Phred probability of the nonRef allele frequency in group1 samples being larger (,smaller) than in group2.">
+##INFO=<ID=PCHI2,Number=1,Type=Float,Description="Posterior weighted chi^2 P-value for testing the association between group1 and group2 samples.">
+##INFO=<ID=QCHI2,Number=1,Type=Integer,Description="Phred scaled PCHI2.">
+##INFO=<ID=PR,Number=1,Type=Integer,Description="# permutations yielding a smaller PCHI2.">
+##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GL,Number=3,Type=Float,Description="Likelihoods for RR,RA,AA genotypes (R=ref,A=alt)">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="# high-quality bases">
+##FORMAT=<ID=DV,Number=1,Type=Integer,Description="# high-quality non-reference bases">
+##FORMAT=<ID=SP,Number=1,Type=Integer,Description="Phred-scaled strand bias P-value">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods">
+##source_20120424.1=vcf-annotate(r735) --fill-AC-AN -f +
+##FILTER=<ID=StrandBias,Description="Min P-value for strand bias (INFO/PV4) [0.0001]">
+##FILTER=<ID=EndDistBias,Description="Min P-value for end distance bias (INFO/PV4) [0.0001]">
+##FILTER=<ID=MaxDP,Description="Maximum read depth (INFO/DP or INFO/DP4) [10000000]">
+##FILTER=<ID=BaseQualBias,Description="Min P-value for baseQ bias (INFO/PV4) [0]">
+##FILTER=<ID=MinAB,Description="Minimum number of alternate bases (INFO/DP4) [2]">
+##FILTER=<ID=Qual,Description="Minimum value of the QUAL field [10]">
+##FILTER=<ID=VDB,Description="Minimum Variant Distance Bias (INFO/VDB) [0]">
+##FILTER=<ID=GapWin,Description="Window size for filtering adjacent gaps [3]">
+##FILTER=<ID=MapQualBias,Description="Min P-value for mapQ bias (INFO/PV4) [0]">
+##FILTER=<ID=SnpGap,Description="SNP within INT bp around a gap to be filtered [10]">
+##FILTER=<ID=RefN,Description="Reference base is N []">
+##FILTER=<ID=MinDP,Description="Minimum read depth (INFO/DP or INFO/DP4) [2]">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##source_20120424.2=vcf-annotate(r735) --fill-AC-AN -f +
+##FILTER=<ID=MinMQ,Description="Minimum RMS mapping quality for SNPs (INFO/MQ) [30]">
+##source_20120710.1=vcf-annotate(r761) -f q=30 mpileup-v1/merged.filt.vcf.gz
+#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT A B C D
+1 10492 . C T 999 PASS DP=213;VDB=0.0102;AF1=0.375;AC1=3;DP4=84,74,34,19;MQ=32;FQ=999;PV4=0.2,0.11,0.057,0.13;AN=8;AC=3 GT:PL:DP:SP:GQ 0/1:85,0,255:57:3:86 0/0:0,123,255:41:0:99 0/1:255,0,255:47:0:99 0/1:114,0,255:66:4:99
+1 10583 . G A,C 20 PASS DP=134;VDB=0.0071;AF1=0.1242;AC1=1;DP4=78,41,6,6;MQ=32;FQ=20;PV4=0.35,0.29,0.052,1;AN=8;AC=1 GT:PL:DP:SP:GQ 0/1:26,0,227:40:8:21 2/2:0,35,255:21:0:40 0/0:0,108,255:36:0:99 0/0:0,21,255:34:0:26
+1 10821 . T A,C 49.7 PASS DP=9;VDB=0.0091;AF1=1;AC1=5;DP4=1,3,0,4;MQ=12;FQ=7.75;PV4=1,1,1,1;AN=8;AC=6 GT:PL:DP:SP:GQ 1/1:42,9,0:33:0:20 0/1:0,3,4:1:0:2 1/1:12,1,0:2:0:4 0/1:0,6,8:2:0:2
+2 16103 . T G,C,A 24.3 PASS DP=110;VDB=0.0122;AF1=0.2119;AC1=2;DP4=49,26,23,2;MQ=31;FQ=24.3;PV4=0.01,1,6.9e-13,0.33;AN=8;AC=1 GT:PL:DP:SP:GQ 0/0:0,2,228:39:11:5 0/0:0,7,189:15:6:10 0/0:0,0,218:25:0:4 0/1:26,0,192:21:5:24
+3 30923 . G T,A,C 999 PASS DP=107;VDB=0.0022;AF1=1;AC1=8;DP4=0,0,47,50;MQ=37;FQ=-36;AN=8;AC=8 GT:PL:DP:SP:GQ 1/1:255,75,0:25:0:99 1/1:221,30,0:10:0:72 1/1:255,117,0:39:0:99 1/1:255,69,0:23:0:99
+4 51898 . C A,T 22.2 PASS DP=128;VDB=0.0230;AF1=0.1272;AC1=1;DP4=56,50,14,2;MQ=41;FQ=22.2;PV4=0.013,0.069,9.8e-17,1;AN=8;AC=1 GT:PL:DP:SP:GQ 0/1:28,0,255:23:13:23 0/0:0,35,255:19:3:40 0/0:0,59,255:44:0:64 0/0:0,11,255:36:9:16
+4 51928 . G A 54.1 PASS DP=149;VDB=0.0311;AF1=0.1269;AC1=1;DP4=67,52,22,5;MQ=41;FQ=54.1;PV4=0.017,0.0073,7.3e-34,0.37;AN=8;AC=1 GT:PL:DP:SP:GQ 0/1:60,0,255:29:13:55 0/0:0,27,255:19:0:32 0/0:0,30,255:51:2:35 0/0:0,13,255:47:11:18
+4 52058 . G C,T 17.5 PASS DP=132;VDB=0.0277;AF1=0.2308;AC1=2;DP4=55,57,15,2;MQ=35;FQ=17.5;PV4=0.0031,0.036,0.00091,0.03;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:13,0,178:20:7:11 0/0:0,60,255:20:0:62 0/1:12,0,255:51:8:10 0/0:0,15,255:38:9:17
+4 52238 . T G,A 999 PASS DP=138;VDB=0.0125;AF1=1;AC1=8;DP4=0,0,65,60;MQ=37;FQ=-42;AN=8;AC=8 GT:PL:DP:SP:GQ 1/1:255,63,0:21:0:99 1/1:255,36,0:12:0:84 1/1:255,166,0:55:0:99 1/1:255,111,0:37:0:99
+4 54586 . T C,A,G 51.1 PASS DP=116;VDB=0.0136;AF1=0.236;AC1=2;DP4=47,45,14,7;MQ=36;FQ=51.1;PV4=0.23,1,6.1e-11,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:48,0,186:24:0:46 0/0:0,26,252:14:0:28 0/1:11,0,255:32:7:9 0/0:0,40,255:43:9:42
+4 54676 . C T 999 PASS DP=143;VDB=0.0244;AF1=0.4969;G3=1.224e-08,1,4.851e-96;HWE=0.0191;AC1=4;DP4=54,48,19,21;MQ=40;FQ=999;PV4=0.58,0.47,8.6e-13,0.2;AN=8;AC=4 GT:PL:DP:SP:GQ 0/1:82,0,233:23:7:85 0/1:121,0,237:20:2:99 0/1:173,0,255:49:6:99 0/1:13,0,255:50:2:16
+4 54753 . T G,A 61.5 PASS DP=177;VDB=0.0130;AF1=0.2019;AC1=2;DP4=48,82,1,5;MQ=40;FQ=61.5;PV4=0.42,1,0.27,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:5,0,237:20:3:4 0/1:63,0,193:16:0:60 0/0:0,160,255:53:0:99 0/0:0,141,255:47:0:99
+5 61442 . A G,T 999 PASS DP=96;VDB=0.0348;AF1=1;AC1=8;DP4=0,0,41,47;MQ=30;FQ=-27;AN=8;AC=8 GT:PL:DP:SP:GQ 1/1:197,42,0:14:0:75 1/1:108,21,0:7:0:54 1/1:255,99,0:33:0:99 1/1:255,102,0:34:0:99
+6 61499 . G A 87.1 PASS DP=140;VDB=0.0120;AF1=0.3006;AC1=2;DP4=54,55,18,12;MQ=35;FQ=87.1;PV4=0.41,0.3,2.4e-12,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:61,0,243:24:2:60 0/0:0,1,231:14:7:4 0/1:32,0,255:43:3:31 0/0:0,48,255:58:6:49
+6 61987 . A G,T,C 999 PASS DP=206;VDB=0.0287;AF1=0.5;G3=1.244e-38,1,7.859e-46;HWE=0.0185;AC1=4;DP4=46,65,42,48;MQ=39;FQ=999;PV4=0.48,0.072,0.00033,1;AN=8;AC=4 GT:PL:DP:SP:GQ 0/1:255,0,255:58:0:99 0/1:182,0,218:22:2:99 0/1:255,0,255:62:3:99 0/1:220,0,255:59:6:99
+6 61989 . G C 999 PASS DP=208;VDB=0.0311;AF1=0.5;G3=3.141e-40,1,8.15e-49;HWE=0.0185;AC1=4;DP4=47,65,42,49;MQ=39;FQ=999;PV4=0.57,0.058,8.7e-05,1;AN=8;AC=4 GT:PL:DP:SP:GQ 0/1:255,0,255:59:1:99 0/1:190,0,233:22:2:99 0/1:255,0,255:62:3:99 0/1:216,0,255:60:6:99
+6 62203 . T C 999 PASS DP=258;VDB=0.0354;AF1=0.5;G3=3.125e-31,1,5e-52;HWE=0.0185;AC1=4;DP4=77,73,47,52;MQ=40;FQ=999;PV4=0.61,1,2.6e-25,1;AN=8;AC=4 GT:PL:DP:SP:GQ 0/1:255,0,255:66:5:99 0/1:145,0,255:38:1:99 0/1:252,0,255:84:1:99 0/1:210,0,255:61:0:99
+7 62271 . A G,T 134 PASS DP=187;VDB=0.0101;AF1=0.498;G3=2.233e-09,1,4.959e-103;HWE=0.0189;AC1=4;DP4=92,56,14,20;MQ=41;FQ=134;PV4=0.033,0.013,1.9e-22,0.0028;AN=8;AC=4 GT:PL:DP:SP:GQ 0/1:65,0,255:35:1:68 0/1:19,0,255:28:2:22 0/1:17,0,255:60:11:20 0/1:39,0,255:59:14:42
+7 66162 . A T,G 999 PASS DP=215;VDB=0.0231;AF1=0.4998;G3=1.238e-10,1,1.58e-77;HWE=0.0186;AC1=4;DP4=62,67,26,36;MQ=39;FQ=999;PV4=0.44,1,3.3e-21,1;AN=8;AC=4 GT:PL:DP:SP:GQ 0/1:170,0,255:45:3:99 0/1:77,0,255:30:0:80 0/1:183,0,255:69:3:99 0/1:26,0,255:47:0:29
+7 66507 . T A,C 999 PASS DP=202;VDB=0.0385;AF1=0.626;AC1=5;DP4=25,14,63,82;MQ=42;FQ=999;PV4=0.03,0.023,1,0.0014;AN=8;AC=5 GT:PL:DP:SP:GQ 0/1:255,0,205:42:7:99 0/1:255,0,20:37:12:21 0/1:255,0,155:57:4:99 1/1:255,72,0:48:0:71
+8 73841 . C T 999 PASS DP=182;VDB=0.0366;AF1=0.3748;AC1=3;DP4=50,64,12,26;MQ=30;FQ=999;PV4=0.25,1.6e-10,0.084,1;AN=8;AC=3 GT:PL:DP:SP:GQ 0/1:95,0,255:33:3:96 0/1:174,0,204:27:9:99 0/1:28,0,255:53:17:29 0/0:0,64,255:39:6:63
+8 79418 . G C 28.5 PASS DP=99;VDB=0.0139;AF1=0.2016;AC1=2;DP4=31,59,1,5;MQ=39;FQ=28.5;PV4=0.66,0.015,0.045,0.00068;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:5,0,236:21:3:4 0/1:30,0,229:18:0:27 0/0:0,78,255:26:0:81 0/0:0,93,255:31:0:96
+8 79772 . C G 999 PASS DP=138;VDB=0.0342;AF1=0.25;AC1=2;DP4=68,47,11,9;MQ=30;FQ=999;PV4=0.81,1,0.41,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:132,0,127:29:6:99 0/1:84,0,219:27:2:82 0/0:0,117,255:39:0:99 0/0:0,120,255:40:0:99
+9 82303 . T C 21 PASS DP=111;VDB=0.0241;AF1=0.1243;AC1=1;DP4=47,50,3,8;MQ=38;FQ=21;PV4=0.22,1,1.5e-14,1;AN=8;AC=1 GT:PL:DP:SP:GQ 0/1:27,0,255:20:5:22 0/0:0,24,255:21:0:29 0/0:0,96,255:32:0:99 0/0:0,75,255:35:0:80
+9 82676 . T G,A 999 PASS DP=152;VDB=0.0213;AF1=0.25;AC1=2;DP4=70,59,9,11;MQ=34;FQ=999;PV4=0.48,0.37,0.0004,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:124,0,255:34:0:99 0/1:89,0,255:31:6:87 0/0:0,138,255:46:0:99 0/0:0,114,255:38:0:99
+9 83084 . T A,G 999 PASS DP=84;VDB=0.0128;AF1=1;AC1=8;DP4=0,0,38,37;MQ=37;FQ=-33;AN=8;AC=8 GT:PL:DP:SP:GQ 1/1:255,48,0:16:0:87 1/1:203,27,0:9:0:66 1/1:255,72,0:24:0:99 1/1:255,78,0:26:0:99
+9 84010 . G A,T 37 PASS DP=190;VDB=0.0033;AF1=0.125;AC1=1;DP4=85,71,6,3;MQ=38;FQ=37;PV4=0.73,0.2,1,0.14;AN=8;AC=1 GT:PL:DP:SP:GQ 0/0:0,126,255:42:0:99 0/0:0,81,255:27:0:86 0/1:43,0,255:38:2:38 0/0:0,64,255:58:2:69
+9 84014 . G A,T 38 PASS DP=192;VDB=0.0055;AF1=0.125;AC1=1;DP4=89,67,3,4;MQ=39;FQ=38;PV4=0.47,0.21,1,0.021;AN=8;AC=1 GT:PL:DP:SP:GQ 0/1:44,0,255:42:0:39 0/0:0,84,255:28:0:89 0/0:0,72,255:36:0:77 0/0:0,172,255:57:0:99
+10 84018 . G A,T 79.6 PASS DP=188;VDB=0.0107;AF1=0.2497;AC1=2;DP4=77,64,8,3;MQ=41;FQ=79.6;PV4=0.35,0.17,1,0.0032;AN=8;AC=2 GT:PL:DP:SP:GQ 0/0:0,120,255:40:0:99 0/1:28,0,255:24:0:26 0/0:0,108,255:36:0:99 0/1:60,0,255:52:6:58
+10 84244 . A C 999 PASS DP=213;VDB=0.0276;AF1=0.25;AC1=2;DP4=83,93,14,22;MQ=41;FQ=999;PV4=0.46,0.29,0.019,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:255,0,255:47:6:99 0/1:208,0,255:49:1:99 0/0:0,178,255:59:0:99 0/0:0,172,255:57:0:99
+10 85597 . A C 999 PASS DP=139;VDB=0.0342;AF1=0.25;AC1=2;DP4=47,60,16,14;MQ=30;FQ=999;PV4=0.41,0.057,1,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:198,0,135:26:0:99 0/1:184,0,221:35:5:99 0/0:0,114,255:38:0:99 0/0:0,114,255:38:0:99
+10 86018 . C G 999 PASS DP=181;VDB=0.0399;AF1=0.25;AC1=2;DP4=70,69,13,26;MQ=42;FQ=999;PV4=0.07,1,7e-14,0.12;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:200,0,255:36:11:99 0/1:240,0,255:46:2:99 0/0:0,129,255:43:0:99 0/0:0,160,255:53:0:99
+10 86303 . G T 999 PASS DP=182;VDB=0.0329;AF1=0.25;AC1=2;DP4=76,66,17,22;MQ=40;FQ=999;PV4=0.28,1,3.7e-11,0.31;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:255,0,255:44:3:99 0/1:207,0,255:31:1:99 0/0:0,138,255:46:0:99 0/0:0,181,255:60:0:99
+10 86331 . A G 999 PASS DP=187;VDB=0.0331;AF1=0.25;AC1=2;DP4=69,74,18,23;MQ=40;FQ=999;PV4=0.72,1,2.4e-05,1;AN=8;AC=2 GT:PL:DP:SP:GQ 0/1:255,0,255:51:1:99 0/1:216,0,255:34:0:99 0/0:0,120,255:40:0:99 0/0:0,178,255:59:0:99
+10 101686 . A G,T,C 89 PASS DP=304;VDB=0.0327;AF1=0.125;AC1=1;DP4=99,171,10,15;MQ=30;FQ=89;PV4=0.83,0.3,0.035,1;AN=8;AC=1 GT:PL:DP:SP:GQ 0/1:95,0,255:58:0:90 0/0:0,72,255:24:0:77 0/0:0,101,255:102:0:99 0/0:0,255,255:111:0:99
+X 1 . A G 89 PASS DP=304;VDB=0.0327;AF1=0.125;AC1=1;DP4=99,171,10,15;MQ=30;FQ=89;PV4=0.83,0.3,0.035,1;AN=8;AC=1 GT:PL:DP 0/1:95,0,255:11 0/0:0,72,255:11 0/0:0,101,255:11 0:0,255:11
+X 2 . A G 89 PASS DP=304;VDB=0.0327;AF1=0.125;AC1=1;DP4=99,171,10,15;MQ=30;FQ=89;PV4=0.83,0.3,0.035,1;AN=8;AC=1 GT:PL:DP 0/1:95,0,255:11 0/0:0,72,255:11 0/0:0,101,255:11 1:255,0:11
+X 3 . A G 89 PASS DP=304;VDB=0.0327;AF1=0.125;AC1=1;DP4=99,171,10,15;MQ=30;FQ=89;PV4=0.83,0.3,0.035,1;AN=8;AC=1 GT:PL:DP 0/0:0,95,255:11 0/0:0,72,255:11 0/0:0,101,255:11 1:255,0:11

examples/mymacros.py

@@ -1,4 +1,4 @@
-from vcfstats.macros import continuous
+from vcfstats.macros import continuous, categorical
 
 
 @continuous
@@ -27,3 +27,15 @@ def N_MISSING(variant):
 def Percent_HETs(variant):
  """Get % of HETs per locus"""
  return variant.num_het / float(len(variant.gt_types))
+
+
+@categorical
+def Allelic_Type(variant):
+ """Get allelic type, either biallelic or multiallelic"""
+ return "biallelic" if len(variant.ALT) == 1 else "multi-allelic"
+
+
+@categorical
+def N_Allelic(variant):
+ """Get number of alleles"""
+ return len(variant.ALT) + 1