|
|
awk to update file with numerical difference if condition is met
03-31-2017
.R_Index Chr Start End Ref Alt Func.IDP.refGene Gene.IDP.refGene GeneDetail.IDP.refGene Inheritence ExonicFunc.IDP.refGene AAChange.IDP.refGene 1 chr1 948846 948846 - A upstream ISG15 . . . . 2 chr1 948870 948870 C G UTR5 ISG15 NM_005101.3:c.-84C>G . . 3 chr1 949608 949608 G A exonic ISG15 . . nonsynonymous SNV ISG15:NM_005101.3:exon2:c.248G>A:p.S83N 4 chr1 949925 949925 C T downstream ISG15 . . . . 5 chr1 207646923 207646923 G A intronic CR2 . . . . 6 chr2 3653844 3653844 T C intronic COLEC11 . . . . 7 chr1 154562623 154562625 CCG - intronic ADAR . . . . 8 chr1 948840 948840 - C upstream ISG15 . . . .
2 ISG15 NM_005101.3 948846-948956 949363-949919 19 CR2 NM_001006658.2 207627644-207627821 207639870-207640257 207641871-207642060 207642144-207642244 207642494-207642577 207643039-207643447 207644084-207644261 207644341-207644432 207644767-207644844 207646116-207646524 207647145-207647230 207647585-207647668 207648168-207648561 207649578-207649764 207651229-207651415 207652601-207652625 207653322-207653398 207658808-207658917 207662486-207663240 6 COLEC11 NM_024027.4 3642421-3642758 3651904-3652060 3660900-3660972 3687867-3687921 3691033-3691129 3691316-3692234 15 ADAR NM_001111.4 154554533-154557519 154557692-154557820 154558228-154558341 154558656-154558839 154560600-154560734 154561026-154561149 154561844-154561938 154562232-154562404 154562737-154562885 154569280-154569414 154569598-154569743 154570303-154570452 154570877-154571061 154573516-154575102 154580467-154580724
R_Index Chr Start End Ref Alt Func.IDP.refGene Gene.IDP.refGene GeneDetail.IDP.refGene Inheritence ExonicFunc.IDP.refGene AAChange.IDP.refGene 1 chr1 948846 948846 - A upstream ISG15 0 . . . 2 chr1 948870 948870 C G UTR5 ISG15 NM_005101.3:c.-84C>G . . . 3 chr1 949608 949608 G A exonic ISG15 . . nonsynonymous SNV ISG15:NM_005101.3:exon2:c.248G>A:p.S83N 4 chr1 949925 949925 C T downstream ISG15 +6 . . . 5 chr1 207646923 207646923 G A intronic CR2 >50 . . . 6 chr2 3653844 3653844 T C intronic COLEC11 >50 . . . 7 chr1 154562623 154562625 CCG - intronic ADAR >50 . . . 8 chr1 948840 948840 - C upstream ISG15 -6 . . .
line1:file1 $9 updated to 0 because ISG15 is matched to line 1, $2 of file2 and the value in $4 of file1, 948846 is a exact match to the first cordinate in $4 before the - line2:not updated, skipped because $9 or $12 in file1 have a value other then . in them line3:not updated, skipped because $9 or $12 in file1 have a value other then . in them line4:file1 $9 updated to +6 because ISG15 is matched to line 1, $2 of file2 and the value in $4 of file1, 949925 is a range match to the second coordinate in $5 after the - line5:file1 $9 updated to >50 because CR2 is matched to line 2, $2 of file2 and the value in $4 of file1, 207646923 is a range match to the first coordinate in $14 before the - but the difference of 222 is > 50 line6:file1 $9 updated to >50 because COLEC11 is matched to line 3, $2 of file2 and the value in $4 of file1, 3653844 is a range match to the second coordinate in $2 after the - but the difference of 1784 is > 50 line7:file1 $9 updated to >50 because ADAR is matched to line 4, $2 of file2 and the value in $4 of file1, 154562625 is a range match to the second coordinate in $12 after the - but the difference of112 is > 50 line8: file1 $9 updated to -6 because ISG15 is matched to line 1, $2 of file2 and the value in $4 of file1, 948840 is a range match to the first coordinate in $4 before the -
awk -F'\t' -v OFS='\t' '{if ($9=="." && $12==".") print }' file1
04-01-2017
04-01-2017
.
04-01-2017
04-01-2017
..awk ' # Run awk to process the following awk script...
BEGIN { OFS = "\t" # Set output field separator.
}
FNR == NR { # For each line in the 1st input file (file2)...
A[$1] = $2 # Read each 2nd field in file2 into array A
next # process next line in file2
}
{
for ( k in A ) # Read each line in file1 into Array k
{
if ( $9=="." && $12=="." == A[k] } # only store file1 lines where field 9 and 12 are a . in them and match them to Array A store the results in updated Array k
F[k] = $2 # match Array k from file1 with 2nd field of file2 and store in Array k
}
split($4, a, /[-]/) # Split the 4th field of file1 into b[] with hyphen and as subfield separator
s[++c] = a[1] # Save the symbol found at the start of this line.
# c is the current line number in the 1st file.
m[c] = b[2] # Save the minimum value found on this line. (left of hyphen)
M[c] = b[3] # Save the maximum value found on this line. (right of hyphen)
t[c] = $4 # Save the tag found on this line.
next # Skip the remaining steps in this script.
}
}
---- if then checks here?
END {
for ( k in F ) # read each K in variable F to update
print k, F[k] # update each k value
break # break out of this for loop.
}
}1 # Print the updated
' file2 file1 # End the awk script and name the input files to be processed.
04-01-2017
04-01-2017
.
awk -v m=50 ' # set maximum distance for difference and store as variable m
NR==FNR { # For each line in the 1st input file (file2)...
for(i=4; i<=NF; i++) { # start at field 4 and store in i as a loop (capture variable fields lenght of each line)
split($i,F,/-/) # split each i on the - (hyphen)
L[$2,i-3]=F[1] # store the left of the - as F[1]
R[$2,i-3]=F[2] # store the right of the - asF[2}
} # end file2 processing
if(NF>n)
n=NF
next
}
$9=="." && $12=="." { # only look at lines where fields 9 and 12 have a . (dot) in file1
d=">50"
for(i=1; i<=n; i++) { # create loop for file1 i variable
if( ($8,i) in L) { # loop hrough field 8 of file1 and store in variable L
if((d1=$4-L[$8,i])<0)
d1=-d1
if((d2=$4-R[$8,i])<0)
d2=-d2
if(d1<=50 || d2<=50) {
if(d1<=50 && d2<=50) {
if(d1<d2)
d=-d1
else
d=d2
}
else {
if(d1<=50)
d=-d1
else
d=d2
}
break # break out of this for loop.
}
}
}
$9=d
}
1
' file2 FS='\t' OFS='\t' file1 # End the awk script and name the input files to be processed with field seperators set as tab.|
|
|
|