awk -F '[\t;]' '{if($3~/mRNA/) {print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9";"$14";"$10} else{print $0}}' Tcacao_523_v2.1.gene.gff3ne_check.gff3
JGI处理前
##gff-version 3
##annot-version v2.1
##species Theobroma cacao
Chromosome_1 phytozomev13 gene 5179 6646 . + . ID=Thecc.01G000100.v2.1;Name=Thecc.01G000100;ancestorIdentifier=Thecc1EG000001.CGDv1.1
Chromosome_1 phytozomev13 mRNA 5179 6646 . + . ID=Thecc.01G000100.1.v2.1;Name=Thecc.01G000100.1;pacid=42014905;longest=1;ancestorIdentifier=Thecc1EG000001t1.CGDv1.1;Parent=Thecc.01G000100.v2.1
Chromosome_1 phytozomev13 five_prime_UTR 5179 5317 . + . ID=Thecc.01G000100.1.v2.1.five_prime_UTR.1;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 5318 5563 . + 0 ID=Thecc.01G000100.1.v2.1.CDS.1;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 5705 5777 . + 0 ID=Thecc.01G000100.1.v2.1.CDS.2;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 5865 6047 . + 2 ID=Thecc.01G000100.1.v2.1.CDS.3;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 6307 6554 . + 2 ID=Thecc.01G000100.1.v2.1.CDS.4;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 three_prime_UTR 6555 6646 . + . ID=Thecc.01G000100.1.v2.1.three_prime_UTR.1;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
处理后
##gff-version 3
##annot-version v2.1
##species Theobroma cacao
Chromosome_1 phytozomev13 gene 5179 6646 . + . ID=Thecc.01G000100.v2.1;Name=Thecc.01G000100;ancestorIdentifier=Thecc1EG000001.CGDv1.1
Chromosome_1 phytozomev13 mRNA 5179 6646 . + . ID=Thecc.01G000100.1.v2.1;Parent=Thecc.01G000100.v2.1;Name=Thecc.01G000100.1
Chromosome_1 phytozomev13 five_prime_UTR 5179 5317 . + . ID=Thecc.01G000100.1.v2.1.five_prime_UTR.1;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 5318 5563 . + 0 ID=Thecc.01G000100.1.v2.1.CDS.1;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 5705 5777 . + 0 ID=Thecc.01G000100.1.v2.1.CDS.2;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 5865 6047 . + 2 ID=Thecc.01G000100.1.v2.1.CDS.3;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 CDS 6307 6554 . + 2 ID=Thecc.01G000100.1.v2.1.CDS.4;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
Chromosome_1 phytozomev13 three_prime_UTR 6555 6646 . + . ID=Thecc.01G000100.1.v2.1.three_prime_UTR.1;Parent=Thecc.01G000100.1.v2.1;pacid=42014905
网友评论