metatran_LBE/20200723_file_preparation.sh
2c0be68cc796master

20200723_file_preparation.sh
View Options

			cd /media/bioinfoteam/SCRATCH_850GB/temp_metatranscriptomic/sequences


			# change for a simpler name: keep the first part of the file name
			for filename in $(ls *'.fastq.gz')

			do
			echo $filename

			fileID=`expr match "$filename" '$[0-9]C_L1_R[1-2]$'`

			new_filename=$fileID'.fastq.gz'
			echo $new_filename

			mv $filename $new_filename
			done


			# unzip files
			for filename in $(ls *'.fastq.gz')

			do

			gzip -d $filename

			done


			# transform fastq to fasta
			for filename in $(ls *'.fastq')

			do

			basename="${filename%.*}"

			fastaname=$basename'.fasta'

			echo $fastaname

			sed -n '1~4s/^@/>/p;2~4p' $filename > $fastaname

			done

			## tranform fastq to fasta on specific samples
			for i in {58..60}

			do
			filename1=${i}C_L1_R1.fastq
			filename2=${i}C_L1_R2.fastq

			fastaname1=${i}C_L1_R1.fasta
			fastaname2=${i}C_L1_R2.fasta

			echo $fastaname1 $fastaname2

			sed -n '1~4s/^@/>/p;2~4p' $filename1 > $fastaname1
			sed -n '1~4s/^@/>/p;2~4p' $filename2 > $fastaname2

			done