diff --git a/Snakefile b/Snakefile
old mode 100644
new mode 100755
index 49ffd6737bd0750936cd9c9a833517d18cb5044d..07bdd53c372eb3375f49569c482f295be4de58c8
--- a/Snakefile
+++ b/Snakefile
@@ -99,7 +99,7 @@ include: os.path.join(RULES, "fastqc.rules")
if config["adapters"]["remove"] :
## TODO add AlienTrimmer
- adapter_tool = "adapters"
+ adapter_tool = "cutadapt"
adapters_input_fastq = input_data
adapters_wkdir = "01-Trimming"
adapters_output = ["01-Trimming/{SAMPLE}_R1_trim.fastq.gz"]
@@ -114,7 +114,7 @@ if config["adapters"]["remove"] :
adapters_qual = config["adapters"]["quality"]
adapters_log = "01-Trimming/logs/{SAMPLE}_trim.txt"
final_output.extend(expand(adapters_output, SAMPLE=samples))
- include: os.path.join(RULES, "adapters.rules")
+ include: os.path.join(RULES, "cutadapt.rules")
else:
adapters_output = input_data
@@ -206,6 +206,7 @@ if config["star_mapping"]["do"]:
#first pass mapping
star_mapping_pass1_input = adapters_output
+ 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_"
@@ -217,6 +218,7 @@ if config["star_mapping"]["do"]:
#Second pass mapping
star_mapping_pass2_input = adapters_output
+ star_mapping_pass2_done = star_index_output_done
star_mapping_pass2_index = star_index_output_dir
star_mapping_pass2_logs = "02-Mapping/STAR/logs/{SAMPLE}_{REF}.out"
star_mapping_pass2_output_prefix = "02-Mapping/STAR/{REF}/{SAMPLE}_{REF}_"
diff --git a/config/config.yaml b/config/config.yaml
index ed14f4850a30c8bd54e1a78bf696ac7bdba3b9bf..41dc78196b513b83c2b170043c6ee914fcba91e5 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -55,7 +55,7 @@ tmpdir: "/pasteur/sonic/scratch/public/"
genome:
index: true
- genome_directory: /path/to/genome/
+ #genome_directory: /path/to/genome/
name: saccer3
fasta_file: /path/to/genome/saccer3.fa
gff_file: /path/to/genome/saccer3.gff
diff --git a/workflow/rules/alienTrimmer.rules b/workflow/rules/alienTrimmer.rules
new file mode 100755
index 0000000000000000000000000000000000000000..ea142092494fb5cfc544e8c16b9ea9b08f99b4ff
--- /dev/null
+++ b/workflow/rules/alienTrimmer.rules
@@ -0,0 +1,68 @@
+#########################################################################
+# 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:
+ "AlienTrimmer/2.0"
+ shell:
+ """
+ set +o pipefail
+
+ tmp="{input}"
+ infiles=($tmp)
+
+ tmp="{output}"
+ outfiles=($tmp)
+
+ # add mode and adapter sequences
+ cmd+="AlienTrimmer -c {params.adapters} -l {params.min} -q {params.qual} {params.options} -z"
+ # paired end or single end
+ if [[ ${{#infiles[@]}} -eq 2 ]];
+ then
+ cmd+=" -o ${{outfiles[0]}} -p ${{outfiles[1]}} -1 ${{infiles[0]}} -2 ${{infiles[1]}} "
+ else
+ cmd+=" -o ${{outfiles[0]}} -i ${{infiles[0]}}"
+ fi
+ #run command
+ eval "${{cmd}} > {log}"
+
+ """
diff --git a/workflow/rules/adapters.rules b/workflow/rules/cutadapt.rules
similarity index 100%
rename from workflow/rules/adapters.rules
rename to workflow/rules/cutadapt.rules
diff --git a/workflow/rules/kallisto_index.rules b/workflow/rules/kallisto_index.rules
new file mode 100644
index 0000000000000000000000000000000000000000..879418d56953836e660239488e48c948a7e9d80c
--- /dev/null
+++ b/workflow/rules/kallisto_index.rules
@@ -0,0 +1,46 @@
+#########################################################################
+# 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 kallisto_index:
+ input:
+ fasta = kallisto_index_fasta
+ output:
+ kallisto_index_output
+ params:
+ kmer = kallisto_index_kmer
+ singularity:
+ "rnaflow.img"
+ log:
+ kallisto_index_log
+ threads:
+ config['kallisto']['threads']
+ envmodules:
+ "kallisto/0.46.2"
+ shell:
+ """
+
+ kallisto index -i {output} --kmer-size={params.kmer} {input.fasta}
+
+ """
diff --git a/workflow/rules/kallisto_quant.rules b/workflow/rules/kallisto_quant.rules
new file mode 100644
index 0000000000000000000000000000000000000000..41275412c0ae955a896ff27a153fb39ee47934da
--- /dev/null
+++ b/workflow/rules/kallisto_quant.rules
@@ -0,0 +1,47 @@
+#########################################################################
+# 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 kallisto_quant:
+ input:
+ index = kallisto_quant_index,
+ fastq = kallisto_quant_fastq
+ output:
+ directory(kallisto_quant_output_dir)
+ params:
+ options = kallisto_quant_options
+ singularity:
+ "rnaflow.img"
+ log:
+ kallisto_pseudo_log
+ threads:
+ config['kallisto']['threads']
+ envmodules:
+ "kallisto/0.46.2"
+ shell:
+ """
+
+ kallisto quant -t {threads} {params.options} -o {output} -i {input.index} {input.fastq}
+
+ """
diff --git a/workflow/rules/star_mapping_pass1.rules b/workflow/rules/star_mapping_pass1.rules
old mode 100644
new mode 100755
index 6e6b09fc7658909f8af722f1e58edea4b2f3a100..c1df88d488673dc96b8e8394b12e5046af22d5dc
--- a/workflow/rules/star_mapping_pass1.rules
+++ b/workflow/rules/star_mapping_pass1.rules
@@ -25,11 +25,12 @@
rule star_mapping_pass1:
input:
fastq = star_mapping_pass1_input,
- index = star_mapping_pass1_index
+ done = star_mapping_pass1_done
output:
jontion = temp(star_mapping_pass1_junctions),
bam = temp(star_mapping_pass1_bam)
params:
+ index = star_mapping_pass1_index,
prefix = temp(star_mapping_pass1_output_prefix),
#read_groups = star_mapping_pass1_read_groups,
kwargs = config['star_mapping']['options']
@@ -44,7 +45,7 @@ rule star_mapping_pass1:
star_mapping_pass1_logs
shell:
"""
- STAR --genomeDir {input.index} \
+ STAR --genomeDir {params.index} \
--readFilesIn {input.fastq} \
--runThreadN {threads} \
--genomeLoad NoSharedMemory \
diff --git a/workflow/rules/star_mapping_pass2.rules b/workflow/rules/star_mapping_pass2.rules
old mode 100644
new mode 100755
index 1c4d677d3f5873084c5d7ec1e401715d8bc87ce3..a792f700945a73d6ff649f98ba4a4e4885884a20
--- a/workflow/rules/star_mapping_pass2.rules
+++ b/workflow/rules/star_mapping_pass2.rules
@@ -25,12 +25,13 @@
rule star_mapping_pass2:
input:
fastq = star_mapping_pass2_input,
- index = star_mapping_pass2_index,
+ done = star_mapping_pass2_done,
sjdb = star_mapping_pass2_junctions,
bam = star_mapping_pass2_bam
output:
star_mapping_pass2_sort
params:
+ index = star_mapping_pass2_index,
prefix = temp(star_mapping_pass2_output_prefix),
RG = star_mapping_pass2_read_groups,
kwargs = config['star_mapping']['options']
@@ -45,7 +46,7 @@ rule star_mapping_pass2:
star_mapping_pass2_logs
shell:
"""
- STAR --genomeDir {input.index} \
+ STAR --genomeDir {params.index} \
--readFilesIn {input.fastq} \
--runThreadN {threads} \
--genomeLoad NoSharedMemory \