Homec4science
Diffusion eSCT pipeline interoperability (master) Browse

R2915/Vital-IT/bsub-docker-singularity-pipeline1.sh
1bd341d02d96master

Last Change
Raw File

bsub-docker-singularity-pipeline1.sh
View Options

#!/bin/bash
#BSUB -L /bin/bash
#BSUB -R "rusage[mem=40000]"
#BSUB -M 40194304
#BSUB -J singularity-docker-pipeline1
#BSUB -e singularity-pipeline1-error.txt
#BSUB -o singularity-pipeline1-output.txt
#BSUB -u severine.duvaud@sib.swiss
#BSUB -q normal
export PATH=/scratch/ul/projects/singularity/2.3/bin:$PATH
# define the singularity container to use
export SINGULARITY_CONTAINER="./pipeline1.img"
# define the number of cpus to use
# you can use env vars provided by your scheduler or hardcode the number of cpus to use
export NUM_CPUS=8
# define $TMPDIR=/tmp if $TMPDIR is not defined
if [ -z ${TMPDIR+x} ]; then
export TMPDIR=/tmp
fi
##########################################################
# YOU SHOULD NOT NEED TO CHANGE ANYTHING BELOW THIS LINE
##########################################################
#create output directories if they don't exist
[ -d output/STAR ] || mkdir -p output/STAR
[ -d output/htseq-count ] || mkdir -p output/htseq-count
# step 1 . Index the reference genome using the STAR utility.
singularity exec ${SINGULARITY_CONTAINER} STAR --runThreadN ${NUM_CPUS} --outTmpDir $TMPDIR/star_tmp --runMode genomeGenerate --genomeDir ./scicore-pipeline1-input-data/GRCm38_Genome/ --genomeFastaFiles ./scicore-pipeline1-input-data/GRCm38_Genome/Ensembl_GRCm38.fa --sjdbGTFfile ./scicore-pipeline1-input-data/GRCm38_Genome/Ensembl_GRCm38_genes.gtf --outFileNamePrefix=output/STAR/
# step 2. Align reads from fastq to indexed reference genome using STAR utility.
singularity exec ${SINGULARITY_CONTAINER} STAR --runThreadN ${NUM_CPUS} --outTmpDir $TMPDIR/star_tmp --readFilesCommand zcat --genomeDir ./scicore-pipeline1-input-data/GRCm38_Genome/ --outSAMstrandField intronMotif --outSAMtype BAM SortedByCoordinate --outReadsUnmapped Fastx --outFileNamePrefix output/STAR/TAM3_ --readFilesIn ./scicore-pipeline1-input-data/fastq/SRR3180540_pass_1.fastq.gz
# step 3. Summarize alignment BAM file to counts table by gene feature using HTSeq utility.
singularity exec ${SINGULARITY_CONTAINER} htseq-count -f bam -r pos -s no output/STAR/TAM3_Aligned.sortedByCoord.out.bam ./scicore-pipeline1-input-data/GRCm38_Genome/Ensembl_GRCm38_genes.gtf > output/htseq-count/TAM3.counts
c4science · Help