diff --git a/Snakefile b/Snakefile
index 07bdd53c372eb3375f49569c482f295be4de58c8..b47b16332a090701d09d27d4a00a19468c815aaf 100755
--- a/Snakefile
+++ b/Snakefile
@@ -133,21 +133,20 @@ elif config["genome"]["rRNA_mapping"]:
def mapping_index(wildcards):
if (wildcards.REF == config["genome"]["name"]):
- input = config["genome"]["fasta_file"]
+ return {"fasta": config["genome"]["fasta_file"]}
elif (wildcards.REF == config["genome"]["host_name"]):
- input = config["genome"]["host_fasta_file"]
+ return {"fasta": config["genome"]["host_fasta_file"]}
elif (wildcards.REF == "Ribo" ):
- input = config["genome"]["ribo_fasta_file"]
- return(input)
+ return {"fasta": config["genome"]["ribo_fasta_file"]}
def annot_index(wildcards):
if (wildcards.REF == config["genome"]["name"]):
- input = config["genome"]["gff_file"]
+ return {"gff_file": config["genome"]["gff_file"]}
elif (wildcards.REF == config["genome"]["host_name"]):
- input = config["genome"]["host_gff_file"]
+ return {"gff_file": config["genome"]["host_gff_file"]}
elif (wildcards.REF == "Ribo" ):
- input = ""
- return(input)
+ return {"gff_file": ""}
+
@@ -161,7 +160,7 @@ if config["bowtie2_mapping"]["do"]:
mapper += ["bowtie2"]
if config["genome"]["index"]:
# indexing for bowtie2
- bowtie2_index_fasta = mapping_index
+ bowtie2_index_fasta = unpack(mapping_index)
bowtie2_index_output_done = os.path.join(os.path.dirname(config["genome"]["fasta_file"]), "{REF}.1.bt2")
bowtie2_index_output_prefix = os.path.join(config["genome"]["genome_directory"],"{REF}")
bowtie2_index_log = "02-Mapping/bowtie2/logs/bowtie2_{REF}_indexing.log"
@@ -193,10 +192,10 @@ if config["bowtie2_mapping"]["do"]:
if config["star_mapping"]["do"]:
mapper += ["STAR"]
if config["genome"]["index"]:
- star_index_fasta = mapping_index
+ star_index_fasta = unpack(mapping_index)
star_index_output_done = os.path.join(config["genome"]["genome_directory"],"{REF}/SAindex")
star_index_output_dir = os.path.join(config["genome"]["genome_directory"],"{REF}")
- star_mapping_splice_file = annot_index
+ star_mapping_splice_file = unpack(annot_index)
star_index_log = "02-Mapping/STAR/logs/STAR_{REF}_indexing.log"
include: os.path.join(RULES, "star_index.rules")
diff --git a/workflow/.gitkeep b/workflow/.gitkeep
old mode 100644
new mode 100755
diff --git a/workflow/rules/.gitkeep b/workflow/rules/.gitkeep
old mode 100644
new mode 100755
diff --git a/workflow/rules/adapters.rules b/workflow/rules/adapters.rules
new file mode 100755
index 0000000000000000000000000000000000000000..76f05ceab17f45b584effbea38073632919909fe
--- /dev/null
+++ b/workflow/rules/adapters.rules
@@ -0,0 +1,69 @@
+#########################################################################
+# RNAflow: an automated pipeline to analyse transcriptomic data #
+# #
+# Authors: Rachel Legendre #
+# Copyright (c) 2021-2022 Institut Pasteur (Paris). #
+# #
+# This file is part of RNAflow workflow. #
+# #
+# RNAflow is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# RNAflow is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
+# GNU General Public License for more details . #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with RNAflow (LICENSE). #
+# If not, see <https://www.gnu.org/licenses/>. #
+#########################################################################
+
+
+
+
+rule adapters:
+ input:
+ fastq = adapters_input_fastq
+ output:
+ adapters_output
+ params:
+ wkdir = adapters_wkdir,
+ options = adapters_options,
+ adapters = adapters_adapt_list,
+ mode = adapters_mode,
+ min = adapters_min,
+ qual = adapters_qual
+ singularity:
+ "rnaflow.img"
+ threads: config['adapters']['threads']
+ log:
+ adapters_log
+ envmodules:
+ "cutadapt",
+ "cutadapt-devel"
+ shell:
+ """
+ set +o pipefail
+
+ tmp="{input}"
+ infiles=($tmp)
+
+ tmp="{output}"
+ outfiles=($tmp)
+
+ # add mode and adapter sequences
+ cmd+=" cutadapt -{params.mode} {params.adapters} -m {params.min} -q {params.qual} {params.options} "
+ # paired end or single end
+ if [[ ${{#infiles[@]}} -eq 2 ]];
+ then
+ cmd+=" -o ${{outfiles[0]}} -p ${{outfiles[1]}} ${{infiles[0]}} ${{infiles[1]}} "
+ else
+ cmd+=" -o ${{outfiles[0]}} ${{infiles[0]}}"
+ fi
+ #run command
+ eval "${{cmd}} > {log}"
+
+ """
diff --git a/workflow/rules/basicCoverage.rules b/workflow/rules/basicCoverage.rules
new file mode 100755
index 0000000000000000000000000000000000000000..6da03abc5d0728af68cbe31fadde599be90d62f4
--- /dev/null
+++ b/workflow/rules/basicCoverage.rules
@@ -0,0 +1,48 @@
+#########################################################################
+# RNAflow: an automated pipeline to analyse transcriptomic data #
+# #
+# Authors: Rachel Legendre #
+# Copyright (c) 2021-2022 Institut Pasteur (Paris). #
+# #
+# This file is part of RNAflow workflow. #
+# #
+# RNAflow is free software: you can redistribute it and/or modify #
+# it under the terms of the GNU General Public License as published by #
+# the Free Software Foundation, either version 3 of the License, or #
+# (at your option) any later version. #
+# #
+# RNAflow is distributed in the hope that it will be useful, #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
+# GNU General Public License for more details . #
+# #
+# You should have received a copy of the GNU General Public License #
+# along with RNAflow (LICENSE). #
+# If not, see <https://www.gnu.org/licenses/>. #
+#########################################################################
+
+
+
+rule basicCoverage:
+ input:
+ basicCoverage_input
+ log:
+ basicCoverage_logs
+ output:
+ basicCoverage_output
+ singularity:
+ "rnaflow.img"
+ params:
+ options = basicCoverage_options
+ envmodules:
+ "samtools",
+ "bedtools"
+ shell:
+ """
+
+ samtools view -f 0x10 -b {input} | bedtools genomecov -ibam stdin -bg > $rev
+ samtools view -F 0x10 -b {input} | bedtools genomecov -ibam stdin -bg > $fwd
+ bamCoverage --bam {input} --outFileName {output} {params.options} 2> {log}
+ """
+
+
diff --git a/workflow/rules/bowtie2_index.rules b/workflow/rules/bowtie2_index.rules
index d7c70561a336abc0201caf845087227947944562..ea8aa99c931531dbded81ea10a4849108bef2e77 100755
--- a/workflow/rules/bowtie2_index.rules
+++ b/workflow/rules/bowtie2_index.rules
@@ -26,7 +26,7 @@
rule bowtie2_index:
input:
- fasta = bowtie2_index_fasta
+ bowtie2_index_fasta
output:
bowtie2_index_output_done
singularity:
@@ -40,7 +40,10 @@ rule bowtie2_index:
"samtools"
shell:
"""
- bowtie2-build {input.fasta} {params.prefix} 2> {log}
- samtools faidx {input.fasta} 2>> {log}
+ set +o pipefail
+
+ #compute index
+ bowtie2-build {input} {params.prefix} 2> {log}
+ samtools faidx {input} 2>> {log}
"""
diff --git a/workflow/rules/kallisto_index.rules b/workflow/rules/kallisto_index.rules
old mode 100644
new mode 100755
diff --git a/workflow/rules/kallisto_quant.rules b/workflow/rules/kallisto_quant.rules
old mode 100644
new mode 100755
diff --git a/workflow/rules/star_index.rules b/workflow/rules/star_index.rules
old mode 100644
new mode 100755
index 8cfc47d3e44832bcb1bbf8d9022491171b34286f..aedc51efbbc7790d310973e415f7e5e31993b874
--- a/workflow/rules/star_index.rules
+++ b/workflow/rules/star_index.rules
@@ -25,12 +25,12 @@
rule star_index:
input:
- fasta = star_index_fasta
+ star_index_fasta,
+ star_mapping_splice_file
output:
star_index_output_done
params:
- wkdir = star_index_output_dir,
- splice_file = star_mapping_splice_file
+ wkdir = star_index_output_dir
singularity:
"rnaflow.img"
log:
@@ -42,16 +42,17 @@ rule star_index:
"samtools"
shell:
"""
- GenomeLength=`grep -v ">" {star_index_fasta} | tr -d '\n' | wc -c`
- SAindex=$(echo $GenomeLength | awk '{{a=log($1)/2 - 1; if (a>14) a=14; printf("%d\n",a)}}')
+ set +o pipefail
+ GenomeLength=`grep -v ">" {input} | tr -d '\n' | wc -c`
+ SAindex=$(echo $GenomeLength | awk '{{a=log($1)/2 - 1; if (a>14) a=14; printf("%d\\n",a)}}')
- if [[ -s {params.splice_file} && {params.splice_file} == "*.gtf" ]]
+ if [[ -s {input.gff_file} && {input.gff_file} == "*.gtf" ]]
then
- STAR --runMode genomeGenerate --genomeFastaFiles {input.fasta} --genomeDir {params.wkdir} --runThreadN {threads} --sjdbGTFfile {params.splice_file} --genomeSAindexNbases $SAindex
- elif [[ -s {params.splice_file} && {params.splice_file} == "*.gff" ]]
+ STAR --runMode genomeGenerate --genomeFastaFiles {input.fasta} --genomeDir {params.wkdir} --runThreadN {threads} --sjdbGTFfile {input.gff_file} --genomeSAindexNbases $SAindex
+ elif [[ -s {input.gff_file} && {input.gff_file} == "*.gff" ]]
then
- STAR --runMode genomeGenerate --genomeFastaFiles {input.fasta} --genomeDir {params.wkdir} --runThreadN {threads} --sjdbGTFfile {params.splice_file} --sjdbGTFtagExonParentTranscript Parent --genomeSAindexNbases $SAindex
+ STAR --runMode genomeGenerate --genomeFastaFiles {input.fasta} --genomeDir {params.wkdir} --runThreadN {threads} --sjdbGTFfile {input.gff_file} --sjdbGTFtagExonParentTranscript Parent --genomeSAindexNbases $SAindex
else
STAR --runMode genomeGenerate --genomeFastaFiles {input.fasta} --genomeDir {params.wkdir} --runThreadN {threads} --genomeSAindexNbases $SAindex
fi