Last active
January 1, 2016 17:20
-
-
Save RonaldFindling/5b3868f8da3b10130b38 to your computer and use it in GitHub Desktop.
FIlter bam-file by chromosome and range
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
############################## | |
#set the following variables | |
############################## | |
#use the bamfile without .bam | |
myfile="alignment" | |
#the chromosome to filter for | |
mychrom="chr1" | |
# reads that start inbetween $from and $to get selected | |
from="43500000" | |
to= "43600000" | |
#how many reads should be in the resultfile at max | |
readnumber="50" | |
############################## | |
#script starts here | |
############################## | |
samfile="${myfile}.sam" | |
bamfile="${myfile}.bam" | |
samchromfile="${myfile}_${mychrom}".sam | |
samchromtargetfile="${myfile}_${mychrom}_from_${from}_to_${to}.sam" | |
bamchromtargetfile="${myfile}_${mychrom}_from_${from}_to_${to}.bam" | |
sortedbamchromtargetfile="${myfile}_${mychrom}_from_${from}_to_${to}_sorted.bam" | |
tmpfile="tmp.txt" | |
##convert initial bam to sam | |
samtools view -h "${bamfile}" > "${samfile}" | |
#filter by chromosome | |
cat ${samfile} | awk -v mychrom=${mychrom} 'BEGIN{FS="\t";} {if($3==mychrom) print $0}' > ${samchromfile} | |
#filter by given target (start and end) | |
cat ${samchromfile} | awk -v from=${from} -v to=${to} '{FS="\t"} $4>=from && $4<=to' from=$from to=$to > ${samchromtargetfile} | |
#take the first x lines | |
head -n ${readnumber} ${samchromtargetfile} > ${tmpfile} && mv ${tmpfile} ${samchromtargetfile} | |
#push the original header to the beginning of the new file | |
head -n 1000 ${samfile} | grep "^@" | cat - ${samchromtargetfile} > ${tmpfile} && mv ${tmpfile} ${samchromtargetfile} | |
#convert sam to bam | |
samtools view -bS ${samchromtargetfile} > ${bamchromtargetfile} | |
tmpfilename=`echo "${sortedbamchromtargetfile}" | sed "s/.bam$//"` | |
# create sorted bam | |
samtools sort "${bamchromtargetfile}" "${tmpfilename}" | |
tmpfilename=`echo "${sortedbamchromtargetfile}" | sed "s/.bam$//"` | |
#create bai | |
samtools index "${sortedbamchromtargetfile}" "${tmpfilename}.bai" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment