#!/bin/bash # RNA-Seq Pipeline # 2022 Februari # ============================================================================================================================================================= # == Settings for SLURM == # ============================================================================================================================================================= #SBATCH --nodes=1 #SBATCH --ntasks-per-node=8 #SBATCH --mem=32GB #SBATCH --job-name=RNAseq #SBATCH --time=24:00:00 # Personal stuff; Change this to your personal settings #SBATCH --job-name=Bowtie2 #SBATCH --mail-type=END #SBATCH --mail-user=youremail@student.rug.nl #SBATCH --output=slurm-Bowtie2-%j.log # ============================================================================================================================================================= # == Load modules == # ============================================================================================================================================================= module load SAMtools/1.10-GCC-9.3.0 module load BEDTools/2.29.2-GCC-9.3.0 module load BioPerl/1.7.7-GCCcore-9.3.0 module load Bowtie2/2.4.4-GCC-9.3.0 # setting global parameters cpu=8 SOFTWAREDIR=/data/pg-molgen/software export PERL5LIB=$SOFTWAREDIR/molgentools_mirror/lib # ============================================================================================================================================================= # == Functions == # ============================================================================================================================================================= function my_bowtie_SE { name=$1 forward=$2 ## Map the reads (from the fastq file) to the reference genome ( .fna ) this will generate a SAM file (Sequence Alignment Map) printf "\n\n========= Bowtie2 SE: "$name" =================================\n" >> $resultsdir/02.$name.bowtie2.log (bowtie2 --local -U $datadir/$forward -p $cpu -S $resultsdir/$name.sam -x $genome) 2>>$resultsdir/02.$name.bowtie2.log process_bam $name } function my_bowtie_PE { name=$1 genome=$2 forward=$3 reverse=$4 printf "\n\n========= Bowtie2 PE: "$name" =================================\n" >> $resultsdir/02.$name.bowtie2.log (bowtie2 --local -1 $datadir/$forward -2 $datadir/$reverse -p $cpu -S $resultsdir/$name.sam -x $genome) 2>>$resultsdir/02.$name.bowtie2.log process_bam $name } function process_bam { name=$1 ## Process the SAM file: a) convert to BAM (binairy SAM), b) sort and index the BAM file printf "\n========== process_bam "$name" ======================================\n" samtools view -S -b -F 4 -o $resultsdir/$name.bam $resultsdir/$name.sam rm $resultsdir/$name.sam # save space by removing the SAM file samtools sort -@ $cpu $resultsdir/$name.bam > $resultsdir/$name.sorted.bam samtools index $resultsdir/$name.sorted.bam samtools depth $resultsdir/$name.sorted.bam > $resultsdir/$name.depth } function my_mkdir { if [ ! -d $1 ]; then mkdir $1 ; fi } # ============================================================================================================================================================= # == Main script == # ============================================================================================================================================================= # 1. FOLDERS # NOTE change the folder names to your own SCRATCHDIR and resultsdir datadir=/data/pg-molgen/rnaseq/20230211_008/fastq resultsdir=/data/p127804/PROJECTS/wilfried/20230212_008/results my_mkdir $resultsdir # 2. # NOTE to get all filenames use : ls -aR >TOC.txt # The main function needs 4 parameters; Sample_name Foward_Reads Reverse_Reads Genome_base_Name # 1) Sample Name: Choose a short name. This prefix will be used to name the result files # 2) The genome filename is normally stored in the $genome variable # 3) Foward_Reads: Name of the fastq file containing the forward reads # 4) Reverse_Reads: Name of the fastq file containing the reverse reads, but only when Paired End (PE) sequencing is done # 3. For Transcriptomics usually Single End (SE) sequencing is done genome=/data/p127804/PROJECTS/wilfried/genomes/Bamyloliquefasciens_B1895_genome-plus-pBamB1895_startRapat75 my_bowtie_SE WM008_01 4A_S17_R1_001.fastq.gz my_bowtie_SE WM008_02 4B_S18_R1_001.fastq.gz genome=/data/p127804/PROJECTS/wilfried/genomes/Bpumilus_NRS576_genome-plus-p576_startRapAt75 my_bowtie_SE WM008_03 4C_S19_R1_001.fastq.gz my_bowtie_SE WM008_04 4D_S20_R1_001.fastq.gz genome=/data/p127804/PROJECTS/wilfried/genomes/Bthuringiensis_kurstaki_HD73_chromosome-plus-pAW63_startRapAt75 my_bowtie_SE WM008_05 4E_S21_R1_001.fastq.gz my_bowtie_SE WM008_06 4F_S22_R1_001.fastq.gz genome=/data/p127804/PROJECTS/wilfried/genomes/Bsp_NMCC4_genome-plus-pBspNMCC4_startRapAt75 my_bowtie_SE WM008_07 4G_S23_R1_001.fastq.gz my_bowtie_SE WM008_08 4H_S24_R1_001.fastq.gz genome=/data/p127804/PROJECTS/wilfried/genomes/Blicheniformis_B4092_genomic-plus-pBli4092_reconstructed_startRapAt75 my_bowtie_SE WM008_09 5A_S25_R1_001.fastq.gz my_bowtie_SE WM008_10 5B_S26_R1_001.fastq.gz genome=/data/p127804/PROJECTS/wilfried/genomes/Batrophaeus_NRS213_genomic-plus-pBatNRS213_startRapAt75 my_bowtie_SE WM008_11 5C_S27_R1_001.fastq.gz my_bowtie_SE WM008_12 5D_S28_R1_001.fastq.gz genome=/data/pg-molgen/rnaseq/genomes/Bacillus_subtilis_subsp_subtilis_str_168_ASM904v1_pLS20 my_bowtie_SE WM008_13 5E_S29_R1_001.fastq.gz my_bowtie_SE WM008_14 5F_S30_R1_001.fastq.gz genome=/data/pg-molgen/rnaseq/genomes/Bacillus_subtilis_subsp_subtilis_str_168_ASM904v1_pLS20 my_bowtie_SE WM008_15 5G_S31_R1_001.fastq.gz my_bowtie_SE WM008_16 5H_S32_R1_001.fastq.gz # 4. Make a report summary cat $resultsdir/02.*.bowtie2.log > $resultsdir/02.bowtie2_all.log $SOFTWAREDIR/molgentools_mirror/rnaseq/RNAseq_bowtie_report_peregrine.pl -i $resultsdir/02.bowtie2_all.log > $resultsdir/02.bowtie2_all.log.table