Created
August 21, 2016 20:43
-
-
Save LeeBergstrand/b36cb06d773d344b06a83e55e25feec1 to your computer and use it in GitHub Desktop.
Shell script for selecting fastq files by number of seqs.
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
#!/usr/bin/env bash | |
if [ $# -eq 0 ] | |
then | |
echo "No arguments supplied..." | |
echo "Please provide a minimum number of seqs per file." | |
exit 1 | |
fi | |
MIN_LENGTH=$1 | |
FILE_LIST=$(find . -type f -name "*.fastq" | sort) | |
declare -a BAD_FILE_LIST | |
echo -e "\nThe following files have passed QC (They will be copied with '.out'):" | |
for FILE in $FILE_LIST | |
do | |
SEQ_COUNT=$(grep '^+' $FILE | wc -l) | |
SEQ_DATA="$FILE $SEQ_COUNT" | |
if (("$SEQ_COUNT" < "$MIN_LENGTH")) | |
then | |
BAD_FILE_LIST+=("$SEQ_DATA") | |
else | |
echo "$SEQ_DATA" | |
cp "$FILE" "$FILE.out" | |
fi | |
done | |
echo -e "\nThe following files did not pass QC:" | |
for FILE in "${BAD_FILE_LIST[@]}" | |
do | |
echo "$FILE" | |
done | |
exit 0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment