|
|
awk to update field using matching value in file1 and substring in field in file2
06-17-2017
.awk -v OFS='\t' 'NR==FNR{split($2,a,"[.]"); k=a[1]; c[k]++} { # split $2 in file1 on the . and strore valvue in array k using array c to iterate over each line
for(i=1;i<=num;i++){ # start for loop in file2 on fields
if($7 == /exonic/){ # check value in $7 and if it is exonic
k=sub(/NM_*;/,"",$12,array[i]); # match the k array from file1 to the string starting with NM_ in $12 up to the ; and read the value into array i
$14=array[i] # set $14 to array i
}; # close block
if($7 != /exonic/){ # check value in $7 and if it is not exonic
k=sub(/NM_*;/,"",$9,array[i); match the k array from file1 to the string starting with NM_ in $9 up to the ; and read the value into array i
$14=array[i] # set $14 to array i
}; # close block
}
next # process next line
}1' file1 file2ATP13A2 NM_022089.3 PPT1 NM_000310.3
2 chr1 17314702 17314702 C T exonic ATP13A2 . . synonymous SNV ATP13A2:NM_001141974:exon24:c.2658G>A:p.S886S;ATP13A2:NM_001141973:exon25:c.2775G>A:p.S925S;ATP13A2:NM_022089:exon25:c.2790G>A:p.S930S rs3738815 . 3 chr1 40562993 40562993 T C UTR5 PPT1 NM_001142604:c.-83A>G;NM_000310:c.-83A>G . . . rs6600313 .
2 chr1 17314702 17314702 C T exonic ATP13A2 . . synonymous SNV ATP13A2:NM_001141974:exon24:c.2658G>A:p.S886S;ATP13A2:NM_001141973:exon25:c.2775G>A:p.S925S;ATP13A2:NM_022089:exon25:c.2790G>A:p.S930S rs3738815 NM_022089.3:exon25:c.2790G>A:p.S930S 3 chr1 40562993 40562993 T C UTR5 PPT1 NM_001142604:c.-83A>G;NM_000310:c.-83A>G . . . rs6600313 NM_000310.3:c.-83A>G
06-18-2017
.|
|
