From 23a2c768541a40ee6e47f25b12b1b458e372a135 Mon Sep 17 00:00:00 2001
From: rlegendr <rachel.legendre@pasteur.fr>
Date: Fri, 17 Sep 2021 10:36:25 +0200
Subject: [PATCH] gestion of gz
---
Snakefile | 10 +++----
workflow/rules/sortmerna.rules | 6 ++---
workflow/rules/star_mapping_pass1.rules | 30 ++++++++++++++-------
workflow/rules/star_mapping_pass2.rules | 36 +++++++++++++++++--------
4 files changed, 54 insertions(+), 28 deletions(-)
diff --git a/Snakefile b/Snakefile
index a7c3018..664c5cb 100755
--- a/Snakefile
+++ b/Snakefile
@@ -212,8 +212,8 @@ if config["star_mapping"]["do"]:
star_index_fasta = unpack(mapping_index)
star_mapping_splice_file = unpack(annot_index)
star_index_log = "02-Mapping/STAR/logs/STAR_{REF}_indexing.log"
- star_index_output_done = config["genome"]["genome_directory"]+"{REF}/STAR/SAindex"
- star_index_output_dir = config["genome"]["genome_directory"]+"{REF}/STAR/"
+ star_index_output_done = config["genome"]["genome_directory"]+"/{REF}/STAR/SAindex"
+ star_index_output_dir = config["genome"]["genome_directory"]+"/{REF}/STAR/"
include: os.path.join(RULES, "star_index.rules")
@@ -223,7 +223,7 @@ if config["star_mapping"]["do"]:
star_mapping_pass1_done = star_index_output_done
star_mapping_pass1_index = star_index_output_dir
star_mapping_pass1_logs = "02-Mapping/STAR/logs/{SAMPLE}_{REF}_init.out"
- star_mapping_pass1_output_prefix = "02-Mapping/STAR/{REF}/{SAMPLE}_{REF}_init_"
+ star_mapping_pass1_output_prefix = "02-Mapping/{REF}/STAR/{SAMPLE}_{REF}_init_"
star_mapping_pass1_junctions = "02-Mapping/{REF}/STAR/{SAMPLE}_{REF}_init_SJ.out.tab"
star_mapping_pass1_bam = "02-Mapping/{REF}/STAR/{SAMPLE}_{REF}_init_Aligned.sortedByCoord.out.bam"
star_mapping_pass1_read_groups = ""
@@ -291,8 +291,8 @@ if config["feature_counts"]["do"]:
#----------------------------------
flagstat_input = counting_index
-flagstat_logs = "02-Mapping/Flagstats/{REF}/{MAP}/logs/{SAMPLE}_{REF}.out"
-flagstat_output = "02-Mapping/Flagstats/{REF}/{MAP}/{SAMPLE}_{REF}_stats.out"
+flagstat_logs = "02-Mapping/{REF}/{MAP}/logs/{SAMPLE}_{REF}.out"
+flagstat_output = "02-Mapping/{REF}/{MAP}/{SAMPLE}_{REF}_stats.out"
final_output.extend(expand(flagstat_output, SAMPLE=samples, REF=ref, MAP=mapper))
include: os.path.join(RULES, "flagstat.rules")
diff --git a/workflow/rules/sortmerna.rules b/workflow/rules/sortmerna.rules
index c176c46..27795ce 100755
--- a/workflow/rules/sortmerna.rules
+++ b/workflow/rules/sortmerna.rules
@@ -44,8 +44,8 @@ rule sortmerna:
set +o pipefail
#tmp="{input.fastq}"
#infiles=($tmp)
- fasta={input.fasta}
- index=${{fasta%%.fa}}
+ fasta="{input.fasta}"
+ index=${{fasta%.fa}}
if [[ ! -s ${{index}}.stats ]]
then
@@ -53,7 +53,7 @@ rule sortmerna:
fi
- sortmerna --ref $${{fasta}},${{index}} -a {threads} --reads {input.fastq} --aligned outfile_rRNA --fastx --sam --num_alignments 1 --other outfile_noRNA --log -v > {log.out} 2> {log.err}
+ sortmerna --ref ${{fasta}},${{index}} -a {threads} --reads {input.fastq} --aligned outfile_rRNA --fastx --sam --num_alignments 1 --other outfile_noRNA --log -v > {log.out} 2> {log.err}
pigz -fc outfile_rRNA > {output.rRNA}
diff --git a/workflow/rules/star_mapping_pass1.rules b/workflow/rules/star_mapping_pass1.rules
index c1df88d..516ead4 100755
--- a/workflow/rules/star_mapping_pass1.rules
+++ b/workflow/rules/star_mapping_pass1.rules
@@ -45,15 +45,27 @@ rule star_mapping_pass1:
star_mapping_pass1_logs
shell:
"""
- STAR --genomeDir {params.index} \
- --readFilesIn {input.fastq} \
- --runThreadN {threads} \
- --genomeLoad NoSharedMemory \
- --outSAMtype BAM SortedByCoordinate \
- --readFilesCommand zcat \
- --seedSearchStartLmax 20 \
- --outFileNamePrefix {params.prefix} \
- {params.kwargs} 2> {log}
+ if [[ {input.fastq} == "*.gz" ]]
+ then
+ STAR --genomeDir {params.index} \
+ --readFilesIn {input.fastq} \
+ --runThreadN {threads} \
+ --genomeLoad NoSharedMemory \
+ --outSAMtype BAM SortedByCoordinate \
+ --readFilesCommand zcat \
+ --seedSearchStartLmax 20 \
+ --outFileNamePrefix {params.prefix} \
+ {params.kwargs} 2> {log}
+ else
+ STAR --genomeDir {params.index} \
+ --readFilesIn {input.fastq} \
+ --runThreadN {threads} \
+ --genomeLoad NoSharedMemory \
+ --outSAMtype BAM SortedByCoordinate \
+ --seedSearchStartLmax 20 \
+ --outFileNamePrefix {params.prefix} \
+ {params.kwargs} 2> {log}
+ fi
samtools index {params.prefix}Aligned.sortedByCoord.out.bam 2>> {log}
diff --git a/workflow/rules/star_mapping_pass2.rules b/workflow/rules/star_mapping_pass2.rules
index a792f70..daae75f 100755
--- a/workflow/rules/star_mapping_pass2.rules
+++ b/workflow/rules/star_mapping_pass2.rules
@@ -46,17 +46,31 @@ rule star_mapping_pass2:
star_mapping_pass2_logs
shell:
"""
- STAR --genomeDir {params.index} \
- --readFilesIn {input.fastq} \
- --runThreadN {threads} \
- --genomeLoad NoSharedMemory \
- --outSAMtype BAM SortedByCoordinate \
- --readFilesCommand zcat \
- --seedSearchStartLmax 20 \
- --outFileNamePrefix {params.prefix} \
- --outSAMattrRGline {params.RG} \
- --sjdbFileChrStartEnd {input.sjdb} \
- {params.kwargs} 2> {log}
+ if [[ {input.fastq} == "*.gz" ]]
+ then
+ STAR --genomeDir {params.index} \
+ --readFilesIn {input.fastq} \
+ --runThreadN {threads} \
+ --genomeLoad NoSharedMemory \
+ --outSAMtype BAM SortedByCoordinate \
+ --readFilesCommand zcat \
+ --seedSearchStartLmax 20 \
+ --outFileNamePrefix {params.prefix} \
+ --outSAMattrRGline {params.RG} \
+ --sjdbFileChrStartEnd {input.sjdb} \
+ {params.kwargs} 2> {log}
+ else
+ STAR --genomeDir {params.index} \
+ --readFilesIn {input.fastq} \
+ --runThreadN {threads} \
+ --genomeLoad NoSharedMemory \
+ --outSAMtype BAM SortedByCoordinate \
+ --seedSearchStartLmax 20 \
+ --outFileNamePrefix {params.prefix} \
+ --outSAMattrRGline {params.RG} \
+ --sjdbFileChrStartEnd {input.sjdb} \
+ {params.kwargs} 2> {log}
+ fi
samtools index {params.prefix}Aligned.sortedByCoord.out.bam 2>> {log}
--
GitLab