Last active
March 17, 2023 00:12
-
-
Save jfear/f6a837e50d1c129efcada3febca69276 to your computer and use it in GitHub Desktop.
Example using loops and regular expressions
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 | |
# I personally would merge sample across lane. Gzip file can just be concated | |
# together and as long as R1 and R2 are done in the same order it should work | |
# fine. | |
# | |
# going from | |
# - 1860_Time_0_S1_L001_R1_001.fastq.gz | |
# - 1860_Time_0_S1_L002_R1_001.fastq.gz | |
# - 1860_Time_0_S1_L002_R1_001.fastq.gz | |
# - 1860_Time_0_S1_L004_R1_001.fastq.gz | |
# to | |
# - 1860_Time_0_R1.fastq.gz | |
pattern='([[:digit:]]+)_(Time_[[:digit:]]+)_(S[[:digit:]])_(L[[:digit:]]{3})_(R[12])_001.fastq.gz' | |
for file_name in *_001.fastq.gz | |
do | |
[[ "$file_name" =~ $pattern ]] | |
sample_name="${BASH_REMATCH[1]}" | |
time="${BASH_REMATCH[2]}" | |
lane="${BASH_REMATCH[4]}" | |
read="${BASH_REMATCH[5]}" | |
cat $file_name >> "${sample_name}_${time}_${read}.fastq.gz" | |
done | |
# Then we can do the same thing but iterate over the new files only. Since I | |
# want R1 and R2 together, I will just iterate over the new R1s. | |
# | |
pattern2='(.*)_R1.fastq.gz' | |
for file_name in *R1.fastq.gz | |
do | |
[[ "$file_name" =~ $pattern2 ]] | |
prefix="${BASH_REMATCH[1]}" | |
read1="${prefix}_R1.fastq.gz" | |
read2="${prefix}_R2.fastq.gz" | |
/usr/local/usrapps/florfenicolamr/fastp \ | |
-i $read1 -I $read2 \ | |
-o "new${prefix}_R1.fastq.gz" -O "new${prefix}_R2.fastq.gz" \ | |
-l 36 \ | |
-c \ | |
-f 4 -F 4 \ | |
-t 4 -T 4 \ | |
-m --merged_out "${prefix}_merged.fastq.gz" \ | |
--unpaired1 "${prefix}_U1.fastq.gz" --unpaired2 "${prefix}_U2.fastq.gz" \ | |
-h "${prefix}.html" | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment