Skip to content
Snippets Groups Projects
Commit 0998f945 authored by Celine Noirot's avatar Celine Noirot
Browse files

Change orde of renameRules component to pass on cluster env.

parent 707723dd
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
workflows/rnaseqdenovo/__init__.py
+ 16
− 19
View file @ 0998f945
......@@ -110,7 +110,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
# Parameters for process workflow
elif function == "process":
# Parameter rename
self.add_parameter("split", "Nb contig to put per split files.", display_name="Nb contig to split", type="int",
self.add_parameter("split", "Nb contig to put per split files.", display_name="Nb contig to split", type="int", add_to="assembly",
default=4000, group="ASSEMBLY section")
self.add_parameter("rename", "With this option the contigs are renamed with the name of their best hit.", display_name="Rename contigs", type="bool",
default=False, group="ASSEMBLY section")
......@@ -169,9 +169,8 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
raise ValueError( "The sequencer '" + lib_arg["sequencer"] + "' is not valid. Sequencer must be in : MiSeq, HiSeqXX00, ILLUMINA, SLX, SOLEXA, SOLID, 454, COMPLETE, PACBIO, IONTORRENT, CAPILLARY, HELICOS, UNKNOWN." )
# Contigs split
split = self.add_component( "SplitSeq", [self.assembly["file"], self.split] )
split = self.add_component( "SplitSeq", [self.assembly["file"], self.assembly["split"]] )
contigs = split.output_files
# Contigs annotation
# ##############################
# Blast annotation of contigs
......@@ -234,7 +233,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
all_annotations = rename_all_annotations.output_files
# Rename best annotations
rename_best_annotations = self.add_component( "RenameTab", [best_annotations, rename_rules.output_file], component_prefix="bestAnnot" )
best_annotations = rename_best_annotations.output_files
best_annotations = rename_best_annotations.output_files
# If user provide GO
if self.ontology != None:
rename_GO = self.add_component( "RenameTab", [self.ontology, rename_rules.output_file], component_prefix="userGO" )
......@@ -243,7 +242,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
rename_vcf = self.add_component( "RenameVCF", [self.variant["file"], rename_rules.output_file], component_prefix="userVCF" )
# Loads contigs
merge_contigs = self.add_component( "ConcatenateFiles", [contigs, "contigs.fa", True], component_prefix="contigs" )
merge_contigs = self.add_component( "ConcatenateFiles", [contigs, "contigs.fa", True], component_prefix="contigs" )
merge_best_annot = self.add_component( "ConcatenateFiles", [best_annotations, "best_annotations.gff", True], component_prefix="bestAnnot" )
contig_files = [merge_contigs.output_file, rename_rules.output_file] if rename_rules is not None else [merge_contigs.output_file]
contig = self.add_biomart_load( Contig,
......@@ -308,8 +307,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
trna.get_version(),
"Predicts tRNA with tRNAscan-SE.",
[merge_trna_predict.output_file] )
if not self.skip_rnammer:
if not self.skip_rnammer:
rnammer = self.add_component( "RNAmmer", [contigs, "eukaryota"] )
merge_rnammer_predict = self.add_component( "ConcatenateFiles", [rnammer.output_files, "rnammer_predictions.gff", True], component_prefix="rnammerPredict" )
self.add_biomart_load( Prediction,
......@@ -322,8 +320,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
rnammer.get_version(),
"Predicts rRNA with RNAmmer.",
[merge_rnammer_predict.output_file] )
if not self.skip_interpro:
if not self.skip_interpro:
get_orf = self.add_component( "GetORF", [contigs, self.max_orf_nb] )
# Process
interpro = self.add_component( "InterProScan", [get_orf.output_files, "p"] )
......@@ -379,7 +376,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
# Alignment
# ##############################
all_bams = []
all_bams = []
all_bais = []
single_fastq, pair1_fastq, pair2_fastq = [], [], []
single_librairies_names, pair_librairies_names = [], []
......@@ -402,10 +399,10 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
single_fastq.append(lib_arg["files"][0])
# Index contigs
index_fai_dict = self.add_component( "IndexFaiDict", [merge_contigs.output_file, self.split] )
index_fai_dict = self.add_component( "IndexFaiDict", [merge_contigs.output_file, self.assembly["split"]] )
index_bwa = self.add_component( "BWAIndex", [merge_contigs.output_file] )
# Align paired-end reads
if len(pair2_fastq)>0 and len(pair1_fastq)>0 :
if len(pair2_fastq)>0 and len(pair1_fastq)>0 :
align_paired = self.add_component( "BWA", [index_bwa.databank, pair1_fastq, pair2_fastq, pair_librairies_names, "mem"], component_prefix="paired" )
index_bam_paired = self.add_component( "SamtoolsIndex", [align_paired.bam_files, 2, 2], component_prefix="paired" )
all_bams = all_bams + index_bam_paired.sorted_bams
......@@ -425,7 +422,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
files=index_bam_paired.sorted_bams+index_bam_paired.output_files )
# Align single reads
if len(single_fastq)>0 :
if len(single_fastq)>0 :
align_single = self.add_component( "BWA", [index_bwa.databank, single_fastq, None, single_librairies_names, "mem"], component_prefix="single" )
index_bam_single = self.add_component( "SamtoolsIndex", [align_single.bam_files, 2, 2], component_prefix="single" )
all_bams = all_bams + index_bam_single.sorted_bams
......@@ -445,12 +442,12 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
files=index_bam_single.sorted_bams+index_bam_single.output_files )
# Count and coverage on non filtered bam
count_compute = self.add_component( "CountReads", [all_bams] )
count_compute = self.add_component( "CountReads", [all_bams] )
max_lib_size = self.project.get_max_library_size()
step = max_lib_size/30
rarefaction_curve = self.add_component( "RarefactionCurves", [all_bams,step] )
coverage = self.add_component( "Coverage", [all_bams, all_bais, self._nb_seq(self.assembly["file"]), self.split] )
coverage = self.add_component( "Coverage", [all_bams, all_bais, self._nb_seq(self.assembly["file"]), self.assembly["split"]] )
expression = self.add_biomart_load( Expression, [count_compute.matrix, self.project.libraries, coverage.output_files,rarefaction_curve.stdouts] )
#Add venn application in web page
self.add_venn()
......@@ -461,7 +458,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
# Variant calling and annotation
##############################
vcf_file = None
vcf_file = None
gatk_indel_filter_options=""
gatk_snp_filter_options=""
if self.variant and self.variant["file"] != None: # If user provide variant file
......@@ -595,7 +592,6 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
else:
sys.stderr.write("Please provide a best annotation file or at least the best annotation source!\n")
sys.exit(1)
contig = self.add_biomart_load(Contig,
contig_parameters,
"Assembly",
......@@ -603,7 +599,7 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
"0",
self.assembly["software_name"],
self.assembly["software_parameters"],
self.assembly["software_version"],
self.assembly["software_version"],
self.assembly["comments"], [self.assembly["file"]]+fastq_files)
self.add_blast_search( Contig, self.assembly["file"] )
......@@ -682,7 +678,6 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
variant_annotation_arg["software_parameters"],
variant_annotation_arg["software_version"],
variant_annotation_arg["comments"], [variant_annotation_arg["file"]])
variant_count = self.add_biomart_load(CountAlleleLib, [self.variant["file"], self.project.libraries])
contig_variant = self.add_biomart_load(Variant, [self.variant["file"], variant.new_table])
......@@ -948,6 +943,8 @@ class RNAseqDenovo (ApplicationWithoutReferenceGenome):
arguments.append('--assembly')
if config.has_option(section, 'file'):
arguments.append( 'file=' + config.get(section, 'file') )
if config.has_option(section, 'split'):
arguments.append( 'split=' + config.get(section, 'split') )
for option in add_analysis_options:
if config.has_option(section, option):
arguments.append( option.replace('_', '-') + '=' + config.get(section, option) )
......
workflows/rnaseqdenovo/components/renamerules.py
+ 4
− 4
View file @ 0998f945
......@@ -22,7 +22,7 @@ from jflow.component import Component
from weaver.function import PythonFunction
def renames_with_annot( prefix, inputs, rename_file):
def renames_with_annot( inputs, rename_file, prefix):
"""
@summary : Writes the new name of each annotation (the new name is built from the subject name).
For each sequence with same subject name, an unique number is added to the new name :
......@@ -78,7 +78,7 @@ def renames_with_annot( prefix, inputs, rename_file):
out_fh.close()
def names_with_prefix( prefix, inputs, rename_file ):
def names_with_prefix( inputs, rename_file , prefix ):
"""
@summary : Writes the new name of each sequence (the new name is built from the old name and a prefix).
@param prefix : the prefix used.
......@@ -126,12 +126,12 @@ class RenameRules (Component):
print self.rename_with_annot
if self.rename_with_annot == True:
self.add_python_execution(renames_with_annot,
cmd_format='{EXE} "' + self.prefix + '" {IN} {OUT}',
cmd_format='{EXE} {IN} {OUT} "' + self.prefix + '"',
inputs=self.inputs, outputs=self.output_file, includes=self.best_annotations)
# Only add prefix
elif self.prefix != None:
# Process prefix
self.add_python_execution(names_with_prefix,
cmd_format='{EXE} "' + self.prefix + '" {IN} {OUT}',
cmd_format='{EXE} {IN} {OUT} "' + self.prefix + '"',
inputs=self.inputs, outputs=self.output_file, includes=self.best_annotations)
\ No newline at end of file
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment