Genome Informatics Laboratory at KRIBB

This page is read only. You can view the source, but not change it. Ask your administrator if you think this is wrong.

====== Custom scripts for 16S rRNA sequence analysis ======
===== merge_paired_fastq.sh =====

  #!/bin/bash
  #
  # modified from 'Merge_Reads_Script.sh' available from:
  # https://github.com/edamame-course/Amplicon_Analysis/blob/master/resources/Merged_Reads_Script.sh
  #
  
  out=merged_dir
  
  if [ ! -d merged_reads ]; then
      echo Creating ${out} directory...
      mkdir ${out}
  fi
  
  for f in *F_sub.*
  do
  
      if [ ! -e ${f} ]; then
          echo Can\'t find 'F_sub' reads!
          echo You have to set fwd/rev read indicators in this script!
          exit
      fi
  
      r=$(sed -e "s/F_sub/R_sub/" <<< "$f")
      file=$(cut -d_ -f1 <<< "$f")
      echo Processing ${f} and ${r} '===>' ${out}/${file}_merged.fastx
      join_paired_ends.py -f ${f} -r ${r} -o ${file}/
      mv ${file}/fastqjoin.join.fastq ${out}/${file}_merged.fastq
      convert_fastaqual_fastq.py -c fastq_to_fastaqual -f ${out}/${file}_merged.fastq -o ${out}/${file}
      mv ${out}/${file}/${file}_merged.fna ${out}/${file}_merged.fasta
      rm -r ${out}/${file}
      rm -r ${file}/
  done