Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
M
m2reprod
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
TRON Kelly
m2reprod
Commits
242be1ed
Commit
242be1ed
authored
5 months ago
by
TRON Kelly
Browse files
Options
Downloads
Patches
Plain Diff
tp
parent
b2d7fe09
No related branches found
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
D.Puthier/Makefile
+40
-0
40 additions, 0 deletions
D.Puthier/Makefile
D.Puthier/Snakefile
+119
-0
119 additions, 0 deletions
D.Puthier/Snakefile
with
159 additions
and
0 deletions
D.Puthier/Makefile
0 → 100644
+
40
−
0
View file @
242be1ed
#The list of subcommands
help
:
@
echo
"Available subcommands"
@
echo
"
\t
- run"
@
echo
"
\t
- dry"
@
echo
"
\t
- clean"
@
echo
"
\t
- graph"
@
echo
"
\t
- rulegraph"
@
echo
"
\t
- queue"
# To start the workflow
run
:
@
bash
-c
"module unload snakemake;
\
module load snakemake/7.25.0 ;
\
snakemake --cluster 'sbatch -c {params.cpu} --mem {params.mem} --partition=fast --account=2427_data_master' -c 3000 -j 500 --rerun-incomplete --rerun-trigger mtime"
dry
:
@
bash
-c
"module unload snakemake;
\
module load snakemake/7.25.0 ;
\
snakemake --cluster 'sbatch -c {params.cpu} --mem {params.mem} --partition=fast --account=2427_data_master' -c 3000 -j 500 --rerun-incomplete --rerun-trigger mtime -n -p"
# Clean unnecessary files
clean
:
@
rm
-f
slurm
*
.out
graph
:
@
bash
-c
"module unload snakemake;
\
module load snakemake/7.25.0;
\
module load graphviz/2.40.1;
\
snakemake --dag | dot -Tpng > graph.png"
rulegraph
:
@
bash
-c
"module unload snakemake;
\
module load snakemake/7.25.0;
\
module load graphviz/2.40.1;
\
snakemake --rulegraph | dot -Tpng > rulegraph.png"
queue
:
@
squeue
-u
$$
USER
This diff is collapsed.
Click to expand it.
D.Puthier/Snakefile
0 → 100644
+
119
−
0
View file @
242be1ed
#singularity: "docker://continuumio/miniconda3:4.4.10"
import os
import re
import sys
workdir:os.getcwd()
DIR="/shared/projects/2427_data_master/datasets/E-MTAB-8560/"
STARINDEX="/shared/bank/mus_musculus/mm10/star-2.7.5a"
GTF ="/shared/bank/mus_musculus/mm10/gff/Mus_musculus.GRCm38.97.gtf"
SZ="/shared/bank/mus_musculus/mm10/star-2.7.5a/chrNameLength.txt"
SAMPLE=os.listdir(DIR)
SAMPLE=[x for x in SAMPLE if ".fq.gz" in x]
SAMPLE=[re.sub("_R[12]\\.fq\\.gz","",x)for x in SAMPLE]
SAMPLE=list(set(SAMPLE))
SAMPLE=sorted(SAMPLE)
#SAMPLE=SAMPLE[:10]
rule all:
input: expand("fastqc/{smp}_R1_fastqc.zip" , smp=SAMPLE), \
expand("fastqctrim/{smp}_R1_fastqc.zip" , smp=SAMPLE) , \
expand("star/{smp}.bam.bai" , smp=SAMPLE) , \
expand("coverage/{smp}.bw" , smp=SAMPLE) , \
expand("featurecounts/{smp}.txt" , smp=SAMPLE) , \
expand("star/{smp}.bam" , smp=SAMPLE)
rule fastqc:
input: r1 = DIR + "{smp}_R1.fq.gz", \
r2 = DIR + "{smp}_R2.fq.gz"
output: r1 ="fastqc/{smp}_R1_fastqc.zip", \
r2 ="fastqc/{smp}_R2_fastqc.zip"
params : cpu="1" , mem="4G"
shell:"""
module load fastqc/0.12.1
fastqc --outdir fastqc {input.r1} {input.r2}
"""
rule trimmomatic:
input: r1 = DIR + "{smp}_R1.fq.gz", \
r2 = DIR + "{smp}_R2.fq.gz"
output: r1 ="trimmomatic/{smp}_R1.fq.gz", \
r2 ="trimmomatic/{smp}_R2.fq.gz", \
r1u ="trimmomatic/{smp}_R1U.fq.gz", \
r2u ="trimmomatic/{smp}_R2U.fq.gz"
params : cpu="4" , mem="4G"
shell:"""
module load trimmomatic/0.39
trimmomatic PE -threads 1 -phred33 \
{input.r1} {input.r2} \
{output.r1} {output.r1u} \
{output.r2} {output.r2u} \
SLIDINGWINDOW:4:20 MINLEN:20
"""
rule fastqc_trim:
input: r1 = "trimmomatic/{smp}_R1.fq.gz", \
r2 = "trimmomatic/{smp}_R2.fq.gz"
output: r1 ="fastqctrim/{smp}_R1_fastqc.zip", \
r2 ="fastqctrim/{smp}_R2_fastqc.zip"
params : cpu="1" , mem="4G"
shell:"""
module load fastqc/0.12.1
fastqc --outdir fastqctrim {input.r1} {input.r2}
"""
rule star:
input: r1="trimmomatic/{smp}_R1.fq.gz", \
r2="trimmomatic/{smp}_R2.fq.gz"
output: "star/{smp}.bam"
params: cpu="20", mem="50G", index=STARINDEX
shell: """
module unload star
module load star/2.7.5a
STAR --genomeDir {params.index} \
--runThreadN {params.cpu} \
--readFilesIn {input.r1} {input.r2} \
--outFileNamePrefix star/{wildcards.smp} \
--outSAMtype BAM SortedByCoordinate \
--readFilesCommand zcat \
--outFilterMultimapNmax 1
mv star/{wildcards.smp}Aligned.sortedByCoord.out.bam {output}
"""
rule samtools_index:
input: "star/{smp}.bam"
output: "star/{smp}.bam.bai"
params: cpu="1" , mem="4G"
shell:"""
module unload samtools
module load samtools/1.18
samtools index {input}
"""
rule big_wig:
input: "star/{smp}.bam"
output: "coverage/{smp}.bw"
params: cpu="20" , mem="50G" , sz=SZ
shell:"""
module unload rseqc
module unload ucsc-wigtobigwig
module load ucsc-wigtobigwig/377
module load rseqc/2.6.4
mkdir -p coverage
bam2wig.py -s {params.sz} \
-i {input} \
-o coverage/{wildcards.smp}
"""
rule feature_counts:
input: "star/{smp}.bam"
output: "featurecounts/{smp}.txt"
params: cpu="4" , mem="16G" , gtf=GTF
shell:"""
module unload subread
module load subread/2.0.6
featureCounts -p --countReadPairs -t exon -g gene_id -a {params.gtf} \
-o featurecounts/{wildcards.smp}.txt {input}
"""
\ No newline at end of file
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment