diff --git a/assembly/README.md b/assembly/README.md
index e5a56cc070f00d9b491176b421958cdff23a9831..8c339e5721c86fa4741a2b0c236bea8d961d7190 100755
--- a/assembly/README.md
+++ b/assembly/README.md
@@ -13,6 +13,13 @@ The user needs to provide two things to run the workflow on her samples:
- a config file with some global options for the analysis
- a tab separate table, without header, that contains the sample names and the corresponding paths to the HiFi consensus reads.
+## Create conda environment containing snakemake and singularity
+```
+conda env create -f environment.yml
+
+```
+
+
## config.yml
In the file config/config.yaml some global parameters can be set:
diff --git a/assembly/config/cluster_config.yaml b/assembly/config/cluster_config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..a8eb21698259a77bfd2a075f95285bb9c955f5ad
--- /dev/null
+++ b/assembly/config/cluster_config.yaml
@@ -0,0 +1,29 @@
+cluster:
+ mkdir -p logs/{rule} &&
+ sbatch
+ --partition={resources.partition}
+ --qos={resources.qos}
+ --cpus-per-task={threads}
+ --mem={resources.mem_mb}
+ --job-name=assemblySMK-{rule}-{wildcards}
+ --output=logs/{rule}/{rule}-{wildcards}-%j.stdout
+ --error=logs/{rule}/{rule}-{wildcards}-%j.stderr
+default-resources:
+ - partition=scicore
+ - qos=1day
+ - time=12:00:00
+ - mem_mb=20000
+restart-times: 3
+max-jobs-per-second: 10
+max-status-checks-per-second: 1
+local-cores: 1
+latency-wait: 60
+jobs: 500
+keep-going: True
+rerun-incomplete: True
+printshellcmds: True
+scheduler: greedy
+use-conda: True
+
+
+# https://github.com/jdblischak/smk-simple-slurm
diff --git a/assembly/config/config.yaml b/assembly/config/config.yaml
index 171ee8f746989a4e8f72d3b20b4e37709e23748f..9af1c0c7665a69956f1adacc03fa354521e44d4d 100755
--- a/assembly/config/config.yaml
+++ b/assembly/config/config.yaml
@@ -4,14 +4,13 @@
samples: config/samples.tsv
outdir: ./results
-output_prefix: pb_bernese
ref:
genome_size: 4.4m
gbf: resources/H37Rv.gbf
-bakta_db: resources/bakta_db
-container: container/assemblySC.sif
+bakta_db: /scicore/home/gagneux/GROUP/PacbioSnake_resources/databases/bakta_db
+container: /scicore/home/gagneux/GROUP/PacbioSnake_resources/containers/assemblySC.sif
threads_per_job: 4
diff --git a/assembly/config/environment.yml b/assembly/config/environment.yml
new file mode 100644
index 0000000000000000000000000000000000000000..f5e4dfb68a298668efd08fbd932411e9cf7f2d77
--- /dev/null
+++ b/assembly/config/environment.yml
@@ -0,0 +1,9 @@
+name: assemblySMK
+channels:
+ - conda-forge
+ - bioconda
+ - defaults
+ - r
+dependencies:
+ - snakemake=7.32.4
+ - singularity=3.8.6
diff --git a/assembly/run_assembly_pipeline.py b/assembly/run_assembly_pipeline.py
old mode 100644
new mode 100755
index 0c4985ce6a8ee28c8c870553f88397e4cdecbd42..388c61689988a8ac2eeeb7f139005c6a9f74435e
--- a/assembly/run_assembly_pipeline.py
+++ b/assembly/run_assembly_pipeline.py
@@ -1,66 +1,70 @@
+#!/usr/bin/env python3
import argparse
import os
import yaml
+import sys
def get_args():
- parser = argparse.ArgumentParser(
- description='')
-
- parser.add_argument(
- '-c', '--configfile',
- dest='config',
- required=True,
- help='.'
- )
-
- parser.add_argument(
- '-j', '--njobs',
- dest="win_size",
- required=True, type=int,
- help='Window size.'
- )
-
- parser.add_argument(
- '-t',
- dest='threads',
- type=int, default=0,
- help='Threads per job.'
- )
+ parser = argparse.ArgumentParser(description='Run PacBio HiFi assembly pipeline on sciCORE')
+
+ # Parameter groups
+ parser_io = parser.add_argument_group('INPUT/OUTPUT')
+
+ parser_cluster = parser.add_argument_group('CLUSTER CONFIGURATION')
+
+ # INPUT/OUTPUT
+ parser_io.add_argument('-s', '--samples', required=True, help='Path to tab-separeted table, no header, with sample name and path to fastq with HiFi reads.')
+
+ parser_io.add_argument('-o', '--outdir', required=True, help='Output directory for the results.')
+
+
+ # CLUSTER CONFIG
+ parser_cluster.add_argument('-j', '--njobs', default='4', help='Number of jobs to run in parallel. [4]')
+
+ parser_cluster.add_argument('-t', '--threads', default='10', help='Threads per job. [10]' )
args=parser.parse_args()
+
return args
def main():
args = get_args()
-
- with open(args.config, 'r') as file:
- config = yaml.safe_load(file)
-
-
+
# Infer pipeline location from path of run_assembly_pipeline.py
-
-
+ pl_path = os.path.dirname(os.path.abspath(sys.argv[0]))
+ print(pl_path)
+ # Directories for which singularity needs to be given access
+ bind_dirs = [
+ "/scicore/home/gagneux/GROUP/tbresearch/genomes/IN_PROGRESS/PacBio_genomes/Gagneux",
+ "/scratch",
+ "/scicore/home/gagneux/GROUP/PacbioSnake_resources",
+ args.outdir,
+ pl_path
+ ]
+
+ singularity_args = "--bind " + " --bind ".join(bind_dirs)
cmd = [
"snakemake",
- "--profile", "",
- "--snakefile", "/scicore/home/gagneux/GROUP/PacbioSnake/assembly/workflow/Snakefile",
- "--directory", "/scicore/home/gagneux/GROUP/PacbioSnake/assembly",
- "--configfile", "/scicore/home/gagneux/stritt0001/TB/projects/pacbio_microscale/results/demo/config.yml",
- "--jobs", "4",
- "--latency-wait", "60",
+ "--snakefile", pl_path + "/workflow/Snakefile",
+ "--directory", pl_path,
+ "--configfile", pl_path + "/config/config.yaml",
+ "--profile", pl_path + "/config/cluster_config.yaml",
+ # Overwrite samples and outdir parameters
+ "--config", "samples=" + args.samples,
+ "--config", "outdir=" + args.outdir,
+ "--jobs", args.njobs,
"--cleanup-shadow",
- "--shadow-prefix",
- "--verbose",
- "--use-singularity", "--singularity-args", "--bind /scicore/home/gagneux/GROUP/tbresearch/genomes/IN_PROGRESS/PacBio_genomes/Gagneux --bind /scicore/home/gagneux/stritt0001 --bind /scratch",
- "--cluster", "sbatch --job-name=pbassembly --cpus-per-task=4 --mem-per-cpu=4G --time=06:00:00 --qos=6hours --output=/scicore/home/gagneux/stritt0001/TB/projects/pacbio_microscale/results/demo/pbassembly.o%j --error=/scicore/home/gagneux/stritt0001/TB/projects/pacbio_microscale/results/demo/pbassembly.e%j"
+ "--use-singularity",
+ "--singularity-args" + " \"" + singularity_args + "\""
]
+ #print(" ".join(cmd))
os.system(" ".join(cmd))
if __name__ == '__main__':