Snakemake/template_dev/resources_SLURM.yaml

-__default__:
-    mem: "1G"
-    cpus: 1
-    time: 01:00:00
-
-star_index:
-    cpus: 8
-
-star_map_pe:
-    cpus: 4
-
-star_map_se:
-    cpus: 4

Snakemake/template_dev/rules/cutadapt.smk

-rule cutadapt_pe:
-    input:
-        r1 = os.path.join(READS_DIR, "{sample}_R1.fastq.gz"),
-        r2 = os.path.join(READS_DIR, "{sample}_R2.fastq.gz")
-    output:
-        r1 = os.path.join("Results", "cutadapt_pe", "{sample}_R1.fastq.gz"),
-        r2 = os.path.join("Results", "cutadapt_pe", "{sample}_R2.fastq.gz")
-    shell:
-        "cutadapt -a {ADAPT_1} -A {ADAPT_2} -o {output.r1} -p {output.r2} {input}"
-
-rule cutadapt_se:
-    input:
-        r = os.path.join(READS_DIR, "{sample}.fastq.gz")
-    output:
-        r = os.path.join("Results", "cutadapt_se", "{sample}.fastq.gz")
-    shell:
-        "cutadapt -a {ADAPT_1} -o {output.r} {input}"

Snakemake/template_dev/rules/fastqc.smk

-rule fastqc_pe:
-    input:
-        r1 = os.path.join(READS_DIR, "{sample}_R1.fastq.gz"),
-        r2 = os.path.join(READS_DIR, "{sample}_R2.fastq.gz")
-    output:
-        "Results/fastqc_pe/{sample}_R1_fastqc.zip"
-    params:
-        dir = "Results/fastqc_pe"
-    shell:
-        "fastqc -o {params.dir} {input.r1} {input.r2}"
-        
-rule fastqc_se:
-    input:
-        r = os.path.join(READS_DIR, "{sample}.fastq.gz")
-    output:
-        "Results/fastqc_se/{sample}_fastqc.zip"
-    params:
-        dir = "Results/fastqc_se"
-    shell:
-        "fastqc -o {params.dir} {input.r}"

Snakemake/template_dev/rules/star_index.smk

-rule star_index:
-    input:
-        ref = REFERENCE
-    output:
-        expand("{dir}/Genome",dir=STAR_INDEX),
-        dir = STAR_INDEX
-    params:
-        cpu = config["star_index"]["cpus"]
-    shell:
-        """
-        STAR --runThreadN {params.cpu} --runMode genomeGenerate --genomeDir {output.dir} --genomeFastaFiles {input.ref} \
-        --outFileNamePrefix {output.dir}/
-        """

Snakemake/template_dev/rules/star_map.smk

-rule star_map_pe:
-    input:
-        ref = STAR_INDEX,
-        r1 = os.path.join("Results", "cutadapt_pe", "{sample}_R1.fastq.gz"),
-        r2 = os.path.join("Results", "cutadapt_pe", "{sample}_R2.fastq.gz")
-    output:
-        bam = os.path.join("Results","star_map", "{sample}_Aligned.sortedByCoord.out.bam")
-    params:
-        cpu = config["star_map_pe"]["cpus"],
-        dir = "Results/star_map"
-    shell:
-        """
-        STAR --genomeDir {input.ref} --readFilesIn {input.r1} {input.r2} --readFilesCommand zcat \
-        --outFileNamePrefix {params.dir}/{wildcards.sample}_ --runThreadN {params.cpu} --outSAMtype BAM SortedByCoordinate
-        """
-
-rule star_map_se:
-    input:
-        ref = STAR_INDEX,
-        reads = os.path.join("Results", "cutadapt_se", "{sample}.fastq.gz")
-    output:
-        bam = os.path.join("Results", "star_map", "{sample}_Aligned.sortedByCoord.out.bam")
-    params:
-        cpu = config["star_map_se"]["cpus"],
-        dir = "Results/star_map"
-    shell:
-        """
-        STAR --genomeDir {input.ref} --readFilesIn {input.reads} --readFilesCommand zcat \
-        --outFileNamePrefix {params.dir}/{wildcards.sample}_ --runThreadN {params.cpu} --outSAMtype BAM SortedByCoordinate
-        """

Snakemake/template_dev/test_SGE.sh

-#! /bin/sh
-
-##############################################################################
-## launch workflow
-
-WORKFLOW_DIR=/usr/local/bioinfo/workflows/Snakemake/template_dev/
-
-SGE_LOG_DIR=SGE_out
-mkdir -p $SGE_LOG_DIR
-
-/usr/local/bioinfo/src/python/Python-3.6.1/bin/snakemake -s $WORKFLOW_DIR/Snakefile --jobs 99 \
-    --configfile $WORKFLOW_DIR/config.yaml \
-    --cluster-config $WORKFLOW_DIR/resources_SGE.yaml \
-    --cluster "qsub -q unlimitq -pe parallel_smp {cluster.cpus} -l mem={cluster.mem} -l h_vmem={cluster.vmem} -o $SGE_LOG_DIR -e $SGE_LOG_DIR" \
-    --printshellcmds --latency-wait 30
-
-## use the exact same command to rerun the workflow
\ No newline at end of file

Snakemake/template_dev/test_SLURM.sh

-#! /bin/sh
-
-##############################################################################
-## export and module load
-module load /tools/share/Modules/system/Python-3.6.3
-
-##############################################################################
-## launch workflow
-
-WORKFLOW_DIR=/usr/local/bioinfo/workflows/Snakemake/template_dev/
-SLURM_out=$WORKFLOW_DIR/logs
-mkdir -p SLURM_out
-
-snakemake -s Snakefile --jobs 99 \
-           --configfile config.yaml \
-           --cluster-config resources_SLURM.yaml \
-           --cluster "sbatch -p unlimitq --cpus-per-task={cluster.cpus} --time={cluster.time} --mem-per-cpu={cluster.mem} -e SLURM_out/%x.err -o SLURM_out/%x.out" \
-           --printshellcmds --latency-wait 30
-
-## use the exact same command to rerun the workflow

data/reference/get_index.cmd

-wget http://genoweb.toulouse.inra.fr/~cnoirot/WorkflowFrameworkComparison/StarIndex.tgz
-tar -xvzf StarIndex.tgz
\ No newline at end of file