In the awk below I am trying to output those lines that Match between file1 and file2 , those Missing in file1, and those missing in file2. Using each $1,$2,$4,$5 value as a key to match on, that is if those 4 fields are found in both files the match, but if those 4 fields are not found then missing in whatever file. That seems to work, but what I can't seem to do in print the values for the patterns in bold for only the missing lines. The patterns are always in the second line so I set it to FNR==2 and I am also trying to print $6 in FNR==1 in my attempt to capture these is in bold in the awk .
file1
chr1 948846 . T TA 749.023 PASS AF=1;AO=127;DP=135;FAO=132;FDP=132;FR=.;FRO=0;FSAF=79;FSAR=53;FSRF=0;FSRR=0;FWDB=-0.0360682;FXX=0.0222206;HRUN=1;LEN=1;MLLD=26.1513;OALT=A;OID=.;OMAPALT=TA;OPOS=948847;OREF=-;PB=.;PBP=.;QD=22.6977;RBI=0.0451251;REFB=0.0429344;REVB=0.0271174;RO=4;SAF=76;SAR=51;SRF=3;SRR=1;SSEN=0;SSEP=0;SSSB=-0.00916056;STB=0.5;STBP=1;TYPE=ins;VARB=-0.00252488 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:150:135:132:4:0:127:132:1:51:76:3:1:53:79:0:0:1
chr1 948870 . C G 1696.85 PASS AF=0.973822;AO=186;DP=191;FAO=186;FDP=191;FR=.,REALIGNEDx0.9895;FRO=5;FSAF=110;FSAR=76;FSRF=3;FSRR=2;FWDB=0.0127239;FXX=0;HRUN=2;LEN=1;MLLD=64.7594;OALT=G;OID=.;OMAPALT=G;OPOS=948870;OREF=C;PB=.;PBP=.;QD=35.5361;RBI=0.0128295;REFB=-0.0404247;REVB=-0.00164304;RO=4;SAF=110;SAR=76;SRF=2;SRR=2;SSEN=0;SSEP=0;SSSB=0.00378587;STB=0.500233;STBP=0.994;TYPE=snp;VARB=0.00428411 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:46:191:191:4:5:186:186:0.973822:76:110:2:2:76:110:3:2:1
chr1 948921 . T C 3030.3 PASS AF=1;AO=320;DP=322;FAO=320;FDP=320;FR=.;FRO=0;FSAF=182;FSAR=138;FSRF=0;FSRR=0;FWDB=-0.0161106;FXX=0.00621099;HRUN=2;LEN=1;MLLD=100.549;OALT=C;OID=.;OMAPALT=C;OPOS=948921;OREF=T;PB=.;PBP=.;QD=37.8788;RBI=0.0184392;REFB=-0.0214439;REVB=0.00896955;RO=1;SAF=182;SAR=138;SRF=1;SRR=0;SSEN=0;SSEP=0;SSSB=-0.00261388;STB=0.5;STBP=1;TYPE=snp;VARB=8.95112e-05 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 1/1:127:322:320:1:0:320:320:1:138:182:1:0:138:182:0:0:1
chr1 2522204 . G T 24.0805 PASS AF=0.666667;AO=4;DP=6;FAO=4;FDP=6;FR=.;FRO=2;FSAF=4;FSAR=0;FSRF=2;FSRR=0;FWDB=0.0759261;FXX=0;HRUN=3;LEN=1;MLLD=55.4428;OALT=T;OID=.;OMAPALT=T;OPOS=2522204;OREF=G;PB=.;PBP=.;QD=16.0537;RBI=0.0759261;REFB=0.0417034;REVB=0;RO=2;SAF=4;SAR=0;SRF=2;SRR=0;SSEN=0;SSEP=0;SSSB=0;STB=0.5;STBP=1;TYPE=snp;VARB=-0.0143595 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR:QT 0/1:10:6:6:2:2:4:4:0.666667:0:4:2:0:0:4:2:0:1
file2
chr1 948846 . T TA 734.654 PASS AF=0.965035;AO=132;DP=147;FAO=138;FDP=143;FDVR=0;FR=.;FRO=5;FSAF=77;FSAR=61;FSRF=3;FSRR=2;FWDB=-0.0273468;FXX=0.027209;HRUN=1;LEN=1;MLLD=23.6556;OALT=A;OID=.;OMAPALT=TA;OPOS=948847;OREF=-;PB=.;PBP=.;QD=20.5498;RBI=0.0391463;REFB=0.0535759;REVB=0.0280105;RO=7;SAF=74;SAR=58;SRF=5;SRR=2;SSEN=0;SSEP=0;SSSB=-0.0149339;STB=0.50149;STBP=0.898;TYPE=ins;VARB=-0.00206507 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR 1/1:117:147:143:7:5:132:138:0.965035:58:74:5:2:61:77:3:2
chr1 948870 . C G 1748.84 PASS AF=0.973545;AO=182;DP=188;FAO=184;FDP=189;FDVR=-1;FR=.,REALIGNEDx1;FRO=5;FSAF=98;FSAR=86;FSRF=5;FSRR=0;FWDB=0.00560489;FXX=0;HRUN=2;LEN=1;MLLD=62.9653;OALT=G;OID=.;OMAPALT=G;OPOS=948870;OREF=C;PB=.;PBP=.;QD=37.0124;RBI=0.0287713;REFB=0.0167989;REVB=0.02822;RO=4;SAF=96;SAR=86;SRF=4;SRR=0;SSEN=0;SSEP=0;SSSB=-0.0194202;STB=0.512436;STBP=0.042;TYPE=snp;VARB=-0.00274912 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR 1/1:40:188:189:4:5:182:184:0.973545:86:96:4:0:86:98:5:0
chr1 948921 . T C 2717.47 PASS AF=0.982639;AO=283;DP=288;FAO=283;FDP=288;FDVR=5;FR=.;FRO=5;FSAF=142;FSAR=141;FSRF=4;FSRR=1;FWDB=-0.00608685;FXX=0;HRUN=2;LEN=1;MLLD=83.445;OALT=C;OID=.;OMAPALT=C;OPOS=948921;OREF=T;PB=.;PBP=.;QD=37.7426;RBI=0.00625429;REFB=-0.0135323;REVB=0.0014375;RO=4;SAF=142;SAR=141;SRF=4;SRR=0;SSEN=0;SSEP=0;SSSB=-0.0132404;STB=0.505178;STBP=0.214;TYPE=snp;VARB=0.000730702 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR 1/1:76:288:288:4:5:283:283:0.982639:141:142:4:0:141:142:4:1
chr1 985450 . G A 18.4743 PASS AF=0.307692;AO=3;DP=12;FAO=4;FDP=13;FDVR=-1;FR=.;FRO=9;FSAF=2;FSAR=2;FSRF=6;FSRR=3;FWDB=-0.0226987;FXX=0;HRUN=15;LEN=1;MLLD=115.792;OALT=A;OID=.;OMAPALT=A;OPOS=985450;OREF=G;PB=.;PBP=.;QD=5.68439;RBI=0.0253049;REFB=0.0610951;REVB=-0.0111851;RO=9;SAF=2;SAR=1;SRF=6;SRR=3;SSEN=0;SSEP=0;SSSB=0;STB=0.614838;STBP=0.651;TYPE=snp;VARB=-0.00351513 GT:GQ:DP:FDP:RO:FRO:AO:FAO:AF:SAR:SAF:SRF:SRR:FSAR:FSAF:FSRF:FSRR 0/1:18:12:13:9:9:3:4:0.307692:1:2:6:3:2:2:6:3
desired output
Match:
chr1 948846 T TA
chr1 948921 T C
chr1 948870 C G
Missing in file1:
chr1 985450 G A 18.4743 FR=.;HRUN=15;LEN=1;QD=5.68439;STB=0.614838
Missing in file2:
chr1 2522204 G T 24.0805 FR=.;HRUN=3;LEN=1;QD=16.0537;STB=0.5
awk
awk '
FNR == NR { file1[$1,$2,$4,$5] = $1 " " $2 " " $4 " " $5 }
FNR != NR { file2[$1,$2,$4,$5] = $1 " " $2 " " $4 " " $5 }
END { print "Match:"; for (k in file1) if (k in file2) print file1[k] # Or file2[k]
print "Missing in file1:"; for (k in file2) if (!(k in file1)) print file2[k] && FNR==1 $6 {print} && && FNR==2 /FR=/ && /HRUN=/ && /LEN=/ && /QD=/ && /STB=/ {print}
print "Missing in file2:"; for (k in file1) if (!(k in file2)) print file1[k] && FNR==1 $6 {print} && && FNR==2 /FR=/ && /HRUN=/ && /LEN=/ && /QD=/ && /STB=/ {print}
}' file1 file2
current output
Match:
chr1 948846 T TA
chr1 948921 T C
chr1 948870 C G
Missing in file1:
chr1 985450 G A
Missing in file2:
chr1 2522204 G T