In the awk below I am trying to print only the header lines starting with # or ## and the lines that $7 is PASS and AF= is less than 5%. The awk does execute but returns an empty file and I am not sure what I am doing wrong. Thank you.
file
##INFO=<ID=OPOS,Number=.,Type=Integer,Description="List of original allele positions">
##INFO=<ID=OREF,Number=.,Type=String,Description="List of original reference bases">
##INFO=<ID=OALT,Number=.,Type=String,Description="List of original variant bases">
##INFO=<ID=OMAPALT,Number=.,Type=String,Description="Maps OID,OPOS,OREF,OALT entries to specific ALT alleles">
##deamination_metric=0.178389
#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT xxxxx
chr1 948846 . T TA 1121.35 PASS AF=1;AO=190;DP=210;FAO=202;FDP=202;FR=.;FRO=0;FSAF=99;FSAR=103;FSRF=0;FSRR=0;FWDB=-0.0502834;FXX=0.0146334;HRUN=1;LEN=1;MLLD=22.6802;OALT=A;OID=.;OMAPALT=TA;OPOS=948847;OREF=-;PB=.;PBP=.;QD=22.205;RBI=0.0912754;REFB=0.0676884;REVB=0.076176;RO=14;SAF=93;SAR=97;SRF=10;SRR=4;SSEN=0;SSEP=0;SSSB=-0.0292947;STB=0.5;STBP=1;TYPE=ins;VARB=3.8368e-05 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:221:210:202:14:0:190:202:1:97:93:10:4:103:99:0:0:1
chr1 948870 . C G 2477.57 PASS AF=0.971326;AO=272;DP=280;FAO=271;FDP=279;FR=.,REALIGNEDx1;FRO=8;FSAF=130;FSAR=141;FSRF=8;FSRR=0;FWDB=0.0152465;FXX=0.0035713;HRUN=2;LEN=1;MLLD=68.4362;OALT=G;OID=.;OMAPALT=G;OPOS=948870;OREF=C;PB=.;PBP=.;QD=35.5207;RBI=0.02597;REFB=-0.033231;REVB=0.0210235;RO=7;SAF=131;SAR=141;SRF=7;SRR=0;SSEN=0;SSEP=0;SSSB=-0.0247914;STB=0.514924;STBP=0.003;TYPE=snp;VARB=0.00476007 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:61:280:279:7:8:272:271:0.971326:141:131:7:0:141:130:8:0:1
chr1 948921 . T C 3825.34 PASS AF=1;AO=447;DP=448;FAO=399;FDP=399;FR=.;FRO=0;FSAF=195;FSAR=204;FSRF=0;FSRR=0;FWDB=0.00321295;FXX=0.00249994;HRUN=2;LEN=1;MLLD=105.43;OALT=C;OID=.;OMAPALT=C;OPOS=948921;OREF=T;PB=.;PBP=.;QD=38.3492;RBI=0.00709428;REFB=-0.0465188;REVB=0.00632502;RO=0;SAF=222;SAR=225;SRF=0;SRR=0;SSEN=0;SSEP=0;SSSB=0;STB=0.5;STBP=1;TYPE=snp;VARB=6.65831e-05 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:171:448:399:0:0:447:399:1:225:222:0:0:204:195:0:0:1
chr1 949608 . G A 764.935 PASS AF=0.4775;AO=419;DP=866;FAO=191;FDP=400;FR=.,REALIGNEDx0.48;FRO=209;FSAF=101;FSAR=90;FSRF=116;FSRR=93;FWDB=0.0542831;FXX=0;HRUN=1;LEN=1;MLLD=147.514;OALT=A;OID=.;OMAPALT=A;OPOS=949608;OREF=G;PB=.;PBP=.;QD=7.64935;RBI=0.0545875;REFB=-0.00710673;REVB=0.00575684;RO=446;SAF=229;SAR=190;SRF=254;SRR=192;SSEN=0;SSEP=0;SSSB=-0.0218564;STB=0.51377;STBP=0.582;TYPE=snp;VARB=0.00764515 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 0/1:764:866:400:446:209:419:191:0.4775:190:229:254:192:90:101:116:93:1
chr1 949654 . A G 3797.25 PASS AF=0.03;AO=779;DP=781;FAO=398;FDP=398;FR=.;FRO=0;FSAF=207;FSAR=191;FSRF=0;FSRR=0;FWDB=-0.00488004;FXX=0.00499988;HRUN=1;LEN=1;MLLD=124.312;OALT=G;OID=.;OMAPALT=G;OPOS=949654;OREF=A;PB=.;PBP=.;QD=38.1633;RBI=0.0260218;REFB=-0.0237472;REVB=-0.0255601;RO=2;SAF=425;SAR=354;SRF=1;SRR=1;SSEN=0;SSEP=0;SSSB=0.000224878;STB=0.5;STBP=1;TYPE=snp;VARB=-2.92274e-05 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:161:781:398:2:0:779:398:1:354:425:1:1:191:207:0:0:1
desired output
##INFO=<ID=OPOS,Number=.,Type=Integer,Description="List of original allele positions">
##INFO=<ID=OREF,Number=.,Type=String,Description="List of original reference bases">
##INFO=<ID=OALT,Number=.,Type=String,Description="List of original variant bases">
##INFO=<ID=OMAPALT,Number=.,Type=String,Description="Maps OID,OPOS,OREF,OALT entries to specific ALT alleles">
##deamination_metric=0.178389
#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT xxxx
chr1 949654 . A G 3797.25 PASS AF=0.03;AO=779;DP=781;FAO=398;FDP=398;FR=.;FRO=0;FSAF=207;FSAR=191;FSRF=0;FSRR=0;FWDB=-0.00488004;FXX=0.00499988;HRUN=1;LEN=1;MLLD=124.312;OALT=G;OID=.;OMAPALT=G;OPOS=949654;OREF=A;PB=.;PBP=.;QD=38.1633;RBI=0.0260218;REFB=-0.0237472;REVB=-0.0255601;RO=2;SAF=425;SAR=354;SRF=1;SRR=1;SSEN=0;SSEP=0;SSSB=0.000224878;STB=0.5;STBP=1;TYPE=snp;VARB=-2.92274e-05 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:161:781:398:2:0:779:398:1:354:425:1:1:191:207:0:0:1
awk
awk -F'\t' '$7 == "PASS" && /AF=(<[1-9]\.0[5-9])/' file > out
---------- Post updated at 08:13 AM ---------- Previous update was at 07:49 AM ----------
This awk is what I needed:
awk
awk -F'\t' '
{
split(x,V)
for(i=1; i<=NF; i++) {
split($i,F,/=/)
V[F[1]]=F[2]
}
}
(V["AF"]+0 < 0.05)
' file > out
Thanks @ Scrutinizer for your help :).