From 100e648eb028cd41589f575da7e1b574eaa644e2 Mon Sep 17 00:00:00 2001
From: BIOPZ-Gypas Foivos <foivos.gypas@unibas.ch>
Date: Thu, 10 Jan 2019 10:59:24 +0100
Subject: [PATCH] Removed cluster_log from rules in prepare_annotation
Snakefile. Removed create directories rule in prepare_annotation Snakefile.
Altered cluster.json in prepare_annotation Snakefile. Removed unecessary info
from config.yaml in prepare_annotation Snakefile.
---
snakemake/prepare_annotation/Snakefile | 33 +--------------
snakemake/prepare_annotation/cluster.json | 42 +++++++++----------
snakemake/prepare_annotation/config.yaml | 12 +-----
snakemake/prepare_annotation/run_snakefile.sh | 5 ++-
4 files changed, 28 insertions(+), 64 deletions(-)
diff --git a/snakemake/prepare_annotation/Snakefile b/snakemake/prepare_annotation/Snakefile
index 5320edf..ff32216 100644
--- a/snakemake/prepare_annotation/Snakefile
+++ b/snakemake/prepare_annotation/Snakefile
@@ -1,6 +1,6 @@
configfile: "config.yaml"
-localrules: create_output_and_log_directories, create_tab_delimited_CDS_file, create_bed_CDS_file, finish
+localrules: create_tab_delimited_CDS_file, create_bed_CDS_file, finish
#################################################################################
### Finish rule
@@ -12,36 +12,16 @@ rule finish:
idx_transcripts = os.path.join(config["output_dir"], "longest_pc_transcript_per_gene.idx"),
bed = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.bed")
-#################################################################################
-### Create output and log directories
-#################################################################################
-
-rule create_output_and_log_directories:
- output:
- output_dir = config["output_dir"],
- cluster_log = config["cluster_log"],
- local_log = config["local_log"],
- flag = config["dir_created"]
- threads: 1
- shell:
- "mkdir -p {output.output_dir}; \
- mkdir -p {output.cluster_log}; \
- mkdir -p {output.local_log}; \
- touch {output.flag};"
-
#################################################################################
### Select longest protein coding transcripts
#################################################################################
rule select_longest_coding_transcripts:
input:
- flag = config["dir_created"],
gtf = config["gtf"],
script = os.path.join(config["scripts"], "find_longest_coding_transcripts.py")
output:
gtf = os.path.join(config["output_dir"], "longest_pc_transcript_per_gene.gtf")
- params:
- cluster_log = os.path.join(config["cluster_log"], "select_longest_coding_transcript.log")
log:
os.path.join(config["local_log"], "select_longest_coding_transcript.log")
singularity:
@@ -58,12 +38,9 @@ rule select_longest_coding_transcripts:
rule generate_segemehl_index_other_RNAs:
input:
- flag = config["dir_created"],
sequence = config["other_RNAs_sequence"]
output:
idx = os.path.join(config["output_dir"], "other_RNAs_sequence.idx")
- params:
- cluster_log = os.path.join(config["cluster_log"], "generate_segemehl_index_other_RNAs.log")
log:
os.path.join(config["local_log"], "generate_segemehl_index_other_RNAs.log")
singularity:
@@ -81,8 +58,6 @@ rule extract_transcript_sequences:
genome = config["genome"]
output:
transcripts = os.path.join(config["output_dir"], "longest_pc_transcript_per_gene.fa")
- params:
- cluster_log = os.path.join(config["cluster_log"], "extract_transcript_sequences.log")
log:
os.path.join(config["local_log"], "extract_transcript_sequences.log")
singularity:
@@ -103,8 +78,6 @@ rule create_tab_delimited_CDS_file:
script = os.path.join(config["scripts"], "create_tab_delimited_CDS_file.py")
output:
tsv = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.tsv")
- params:
- cluster_log = os.path.join(config["cluster_log"], "create_tab_delimited_CDS_file.log")
log:
os.path.join(config["local_log"], "create_tab_delimited_CDS_file.log")
singularity:
@@ -124,8 +97,6 @@ rule create_bed_CDS_file:
tsv = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.tsv")
output:
bed = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.bed")
- params:
- cluster_log = os.path.join(config["cluster_log"], "create_bed_CDS_file.log")
log:
os.path.join(config["local_log"], "create_bed_CDS_file.log")
# singularity:
@@ -142,8 +113,6 @@ rule generate_segemehl_index_transcripts:
sequence = os.path.join(config["output_dir"], "longest_pc_transcript_per_gene.fa")
output:
idx = os.path.join(config["output_dir"], "longest_pc_transcript_per_gene.idx")
- params:
- cluster_log = os.path.join(config["cluster_log"], "generate_segemehl_index_transcripts.log")
log:
os.path.join(config["local_log"], "generate_segemehl_index_transcripts.log")
singularity:
diff --git a/snakemake/prepare_annotation/cluster.json b/snakemake/prepare_annotation/cluster.json
index 7845df8..504c3fd 100644
--- a/snakemake/prepare_annotation/cluster.json
+++ b/snakemake/prepare_annotation/cluster.json
@@ -1,23 +1,23 @@
{
-"__default__":
-{
-"queue":"6hours",
-"time": "05:00:00",
-"threads":"1",
-"mem":"4G"
-},
-"generate_segemehl_index_other_RNAs":
-{
-"queue":"6hours",
-"time": "06:00:00",
-"threads":"8",
-"mem":"50G"
-},
-"generate_segemehl_index_transcripts":
-{
-"queue":"6hours",
-"time": "06:00:00",
-"threads":"8",
-"mem":"50G"
-}
+ "__default__" :
+ {
+ "queue": "6hours",
+ "time": "05:00:00",
+ "threads": "1",
+ "mem": "4G",
+ "name": "{rule}.{wildcards}",
+ "out": "$PWD/logs/cluster_log/{rule}.{wildcards}-%j-%N.out"
+ },
+ "generate_segemehl_index_other_RNAs":
+ {
+ "time": "06:00:00",
+ "threads":"8",
+ "mem":"50G"
+ },
+ "generate_segemehl_index_transcripts":
+ {
+ "time": "06:00:00",
+ "threads":"8",
+ "mem":"50G"
+ }
}
diff --git a/snakemake/prepare_annotation/config.yaml b/snakemake/prepare_annotation/config.yaml
index 2f104b8..02a2810 100644
--- a/snakemake/prepare_annotation/config.yaml
+++ b/snakemake/prepare_annotation/config.yaml
@@ -9,15 +9,7 @@
### Output and log directory
##############################################################################
output_dir: "results"
- local_log: "results/local_log"
- cluster_log: "results/cluster_log"
- dir_created: "results/dir_created"
+ local_log: "logs/local_log"
+ cluster_log: "logs/cluster_log"
scripts: "scripts"
- ##############################################################################
- ### sample info
- ##############################################################################
- input_dir: "samples"
- input_reads_pattern: ".fastq.gz"
- sample: ["example"]
- example: {adapter: GATCGGAAGAGCACA}
...
diff --git a/snakemake/prepare_annotation/run_snakefile.sh b/snakemake/prepare_annotation/run_snakefile.sh
index 6791403..7a004f2 100755
--- a/snakemake/prepare_annotation/run_snakefile.sh
+++ b/snakemake/prepare_annotation/run_snakefile.sh
@@ -1,5 +1,8 @@
# set -e
+mkdir -p logs/cluster_log
+mkdir -p logs/local_log
+
snakemake \
--cluster-config cluster.json \
--cluster "sbatch --cpus-per-task={cluster.threads} --mem={cluster.mem} --qos={cluster.queue} --time={cluster.time} --output={params.cluster_log}-%j-%N -p scicore" \
@@ -7,4 +10,4 @@ snakemake \
-p \
--rerun-incomplete \
--use-singularity \
---singularity-args "--bind ${PWD}"
\ No newline at end of file
+--singularity-args "--bind ${PWD}"
--
GitLab