Created
March 22, 2017 14:37
-
-
Save decodebiology/b3a22223534bfb5d68b0a56c750d404a to your computer and use it in GitHub Desktop.
Check the Phred Scale quality of sequencing files
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 | |
# ./CheckPhredScale.sh <FASTQ_FILE> <NUMBER OF LINES TO CHECK> | |
echo "Shell:"; | |
zcat $1 | head -n $2 | awk '{if(NR%4==0) printf("%s",$0);}' | od -A n -t u1 | awk 'BEGIN{min=100;max=0;}{for(i=1;i<=NF;i++) {if($i>max) max=$i; if($i<min) min=$i;}}END{if(max<=74 && min<59) print "Phred+33"; else if(max>73 && min>=64) print "Phred+64"; else if(min>=59 && min<64 && max>73) print "Solexa+64"; else print "Unknown score encoding";}'; | |
echo ""; | |
echo "python:"; | |
zcat $1 | awk 'NR % 4 == 0' | head -n $2 | python ./guess-encoding.py | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment