|
|
awk to add text to each line of matching id
01-18-2019
.awk '
BEGIN{
SUBSEP=","
}
FNR==NR{
max[$1,$NF]=$3
min[$1,$NF]=$2
next
}
{
split($4,array,"_") # How do I change/modify this so it only looks a each line with this id `COL1A2` in it?
}
(($1,array[1]) in max){
if(($2>min[array[5],array[1]] && $2<max[array[5],array[1]]) || ($3>max[array[5],array[1]] && $3<max[array[5],array[1]])){
print array[5],array[1],min[array[5],array[1]],max[array[5],array[1]],"exon"
next
}
}
{
print $0,"intron"}' f f2
chr7 94024333 94024423 COL1A2_cds_0_0_chr7_94024344_f 0 + intron
chr7 94027049 94027080 COL1A2_cds_1_0_chr7_94027060_f 0 + intron
chr7 COL1A2 94027591 94027701 exon.... }' f1 f2 chr7 94024333 94024423 COL1A2_cds_0_0_chr7_94024344_f 0 + intron chr7 94027049 94027080 COL1A2_cds_1_0_chr7_94027060_f 0 + intron chr7 94027683 94027718 COL1A2_cds_2_0_chr7_94027694_f 0 + intron
contents of f single COL1A2 entry chr7 94027591 94027701 COL1A2
contents of f1 multiple COL1A2 entry, this is most of the actual data, very few are single entries though there are some chr7 94027591 94027701 COL1A2 chr7 94027799 94027811 COL1A2 chr7 94030799 94030847 COL1A2
contents of f2 always the same format chr7 94024333 94024423 COL1A2_cds_0_0_chr7_94024344_f 0 + chr7 94027049 94027080 COL1A2_cds_1_0_chr7_94027060_f 0 + chr7 94027683 94027718 COL1A2_cds_2_0_chr7_94027694_f 0 +
|
|