#!/bin/bash # RNA-Seq Pipeline # 2025 May # ============================================================================================================================================================= # == Settings for SLURM == # ============================================================================================================================================================= #SBATCH --nodes=1 #SBATCH --ntasks-per-node=16 #SBATCH --mem=32GB #SBATCH --job-name=RNAseq #SBATCH --time=24:00:00 #SBATCH --output=slurm-Bowtie2-%j.log # ============================================================================================================================================================= # == Load modules == # ============================================================================================================================================================= module load SAMtools/1.19.2-GCC-13.2.0 module load BEDTools/2.30.0-GCC-11.3.0 module load Bowtie2/2.5.4-GCC-13.2.0 source /userapps/hb-molgen/conda_envs/venvs/PythonTensor/bin/activate # setting global parameters cpu=$SLURM_JOB_CPUS_PER_NODE cpu=16 AnneTools=/userapps/hb-molgen/AnneTools # ============================================================================================================================================================= # == Functions == # ============================================================================================================================================================= function my_bowtie_SE { # Map the reads (from the fastq file) to the reference genome ( .fna ) this will generate a SAM file (Sequence Alignment Map) name=$1 forward=$2 printf "\n\n========= Bowtie2 SE: "$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 SAM_2_BAM $name } function SAM_2_BAM { # convert SAM to sorted BAM (binairy SAM) and remove unmapped reads with option -F 4 name=$1 printf "\n========== Convert "$name" ======================================\n" samtools view -S -b -F 4 -o $resultsdir/$name.bam $resultsdir/$name.sam samtools sort -@ $cpu $resultsdir/$name.bam > $resultsdir/$name.sorted.bam samtools index $resultsdir/$name.sorted.bam rm $resultsdir/$name.sam # save space by removing the SAM file rm $resultsdir/$name.bam # save space by removing the non sorted BAM file # 3) save space by removing the SAM file } 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=/scratch/p127804/PROJECTS/Wilfried/202505_023/results datadir=/scratch/hb-molgen/NGSdata/20250507_023 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=/scratch/p127804/PROJECTS/Wilfried/genomes/Bacillus_subtilis_subsp_subtilis_str_168_ASM904v1_pLS20 my_bowtie_SE AJ023_01 AJ023_01_S365_L001_R1_001.fastq.gz my_bowtie_SE AJ023_02 AJ023_02_S366_L001_R1_001.fastq.gz my_bowtie_SE AJ023_03 AJ023_03_S253_L001_R1_001.fastq.gz my_bowtie_SE AJ023_04 AJ023_04_S254_L001_R1_001.fastq.gz my_bowtie_SE AJ023_05 AJ023_05_S367_L001_R1_001.fastq.gz my_bowtie_SE AJ023_06 AJ023_06_S368_L001_R1_001.fastq.gz my_bowtie_SE WM023_01 WM023_01_S334_L001_R1_001.fastq.gz my_bowtie_SE WM023_02 WM023_02_S335_L001_R1_001.fastq.gz my_bowtie_SE WM023_03 WM023_03_S336_L001_R1_001.fastq.gz my_bowtie_SE WM023_04 WM023_04_S337_L001_R1_001.fastq.gz my_bowtie_SE WM023_05 WM023_05_S338_L001_R1_001.fastq.gz my_bowtie_SE WM023_06 WM023_06_S339_L001_R1_001.fastq.gz my_bowtie_SE WM023_07 WM023_07_S340_L001_R1_001.fastq.gz my_bowtie_SE WM023_08 WM023_08_S341_L001_R1_001.fastq.gz my_bowtie_SE WM023_09 WM023_09_S342_L001_R1_001.fastq.gz my_bowtie_SE WM023_10 WM023_10_S343_L001_R1_001.fastq.gz my_bowtie_SE WM023_11 WM023_11_S344_L001_R1_001.fastq.gz my_bowtie_SE WM023_12 WM023_12_S345_L001_R1_001.fastq.gz my_bowtie_SE WM023_13 WM023_13_S346_L001_R1_001.fastq.gz my_bowtie_SE WM023_14 WM023_14_S347_L001_R1_001.fastq.gz my_bowtie_SE WM023_15 WM023_15_S348_L001_R1_001.fastq.gz my_bowtie_SE WM023_16 WM023_16_S349_L001_R1_001.fastq.gz my_bowtie_SE WM023_17 WM023_17_S350_L001_R1_001.fastq.gz my_bowtie_SE WM023_18 WM023_18_S351_L001_R1_001.fastq.gz my_bowtie_SE WM023_19 WM023_19_S352_L001_R1_001.fastq.gz my_bowtie_SE WM023_20 WM023_20_S353_L001_R1_001.fastq.gz my_bowtie_SE WM023_21 WM023_21_S354_L001_R1_001.fastq.gz my_bowtie_SE WM023_22 WM023_22_S355_L001_R1_001.fastq.gz my_bowtie_SE WM023_23 WM023_23_S356_L001_R1_001.fastq.gz my_bowtie_SE WM023_24 WM023_24_S357_L001_R1_001.fastq.gz my_bowtie_SE WM023_25 WM023_25_S358_L001_R1_001.fastq.gz my_bowtie_SE WM023_26 WM023_26_S359_L001_R1_001.fastq.gz my_bowtie_SE WM023_27 WM023_27_S360_L001_R1_001.fastq.gz my_bowtie_SE WM023_28 WM023_28_S361_L001_R1_001.fastq.gz my_bowtie_SE WM023_29 WM023_29_S362_L001_R1_001.fastq.gz my_bowtie_SE WM023_30 WM023_30_S363_L001_R1_001.fastq.gz my_bowtie_SE WM023_31 WM023_31_S364_L001_R1_001.fastq.gz # Make a report summary cat $resultsdir/*.bowtie2.log > $resultsdir/03.bowtie2_all.log python3 $AnneTools/Bowtie2LogTable.py -query $resultsdir/03.bowtie2_all.log > $resultsdir/03.bowtie2_table.txt