add some parameters to the miseq workflow

workflows/miseq_diversity/__init__.py

@@ -85,7 +85,8 @@ class MiSeqDiversity (NG6Workflow):
 		addrawfiles = self.add_component("AddRawFiles", [self.runobj, saved_files, self.args["compression"]])
  		
 		# make some statistics on raw file
-		fastqc = self.add_component("FastQC", [filtered_read1_files+filtered_read2_files, (group_prefix is not None), True, run_name+"_fastqc.tar.gz"], parent = fastqilluminafilter)
+		fastqc = self.add_component("FastQC", [filtered_read1_files+filtered_read2_files, (group_prefix is not None), 
+											True, run_name+"_fastqc.tar.gz"], parent = fastqilluminafilter)
  
 		# list concatenated files
 		if is_paired_end and (group_prefix is not None):
@@ -105,34 +106,81 @@ class MiSeqDiversity (NG6Workflow):
  		fileExtension = os.path.splitext(concat_read1_files[0])[1]
  		if fileExtension == fileFormat:
 	 		gunzip = self.add_component("GunZipFiles",[concat_read1_files,concat_read2_files])
- 			makecontigs = self.add_component("MothurMakeContigs", kwargs={'read1_files':gunzip.fastq_R1,'read2_files':gunzip.fastq_R2,\
- 					'sample_name': self.args["sample_name"],'maxambig':'0','maxlength':self.args["max_contigs_length"]}, component_prefix="with_gz", parent=fastqilluminafilter)
+ 			makecontigs = self.add_component("MothurMakeContigs", 
+											kwargs={'read1_files':gunzip.fastq_R1,
+												'read2_files':gunzip.fastq_R2,
+												'sample_name': self.args["sample_name"],
+												'maxambig':self.args["max_ambiguous"],
+												'maxlength':self.args["max_contigs_length"],
+												'processors':self.args["processors"]}, 
+											component_prefix="with_gz", 
+											parent=fastqilluminafilter)
 	 	else:
-	 		makecontigs = self.add_component("MothurMakeContigs", kwargs={'read1_files':concat_read1_files,'read2_files':concat_read2_files,\
- 							'sample_name': self.args["sample_name"],'maxambig':'0','maxlength':self.args["max_contigs_length"]}, component_prefix="without_gz", parent=fastqilluminafilter)
+	 		makecontigs = self.add_component("MothurMakeContigs", 
+											kwargs={'read1_files':concat_read1_files,
+												'read2_files':concat_read2_files,
+												'sample_name': self.args["sample_name"],
+												'maxambig':self.args["max_ambiguous"],
+												'maxlength':self.args["max_contigs_length"],
+												'processors':self.args["processors"]}, 
+											component_prefix="without_gz", 
+											parent=fastqilluminafilter)
+  		
   		uniqueseqs = self.add_component("MothurUniqueSeqs", [makecontigs.good_fasta_files])
   		countseqs = self.add_component("MothurCountSeqs", [uniqueseqs.unique_names_files,makecontigs.good_groups_files])
-  		pcrseqs = self.add_component("MothurPcrSeqs", kwargs={'fasta_files':self.args["reference_alignment"], 'forward_primer':self.args["forward_primer"],\
-       															'reverse_primer':self.args["reverse_primer"]})
-  		alignseqs = self.add_component("MothurAlign", kwargs={'fasta_files':uniqueseqs.unique_fasta_files,'reference_alignment_files':pcrseqs.pcr_fasta_files,\
-  										'count_table_files':countseqs.count_table_files, 'maxhomop':8}, parent=makecontigs)
-  		filterseqs = self.add_component("MothurFilterSeqs",[alignseqs.good_fasta_files])
-   		uniqueseqs_filter = self.add_component("MothurUniqueSeqs", kwargs={'fasta_files':filterseqs.filtered_fasta_files, \
-   																		'count_table_files':alignseqs.good_count_table_files},component_prefix="after_filter")
-   		precluster = self.add_component("MothurPreCluster",kwargs={'fasta_files':uniqueseqs_filter.unique_fasta_files,\
-   																'count_table_files':uniqueseqs_filter.unique_count_table_files})
-   		chimerauchime = self.add_component("MothurChimeraUchime",kwargs={'fasta_files':precluster.precluster_fasta_files,\
-   																		'count_table_files':precluster.precluster_count_table_files},parent=alignseqs)
+  		
+  		pcrseqs = self.add_component("MothurPcrSeqs", 
+									kwargs={'fasta_files':self.args["reference_alignment"], 
+										'forward_primer':self.args["forward_primer"],
+										'reverse_primer':self.args["reverse_primer"]})
+  		
+  		alignseqs = self.add_component("MothurAlign", 
+										kwargs={'fasta_files':uniqueseqs.unique_fasta_files,
+											'reference_alignment_files':pcrseqs.pcr_fasta_files,
+											'count_table_files':countseqs.count_table_files, 
+											'maxhomop':self.args["max_homopolymers"],
+											'processors':self.args["processors"]}, 
+										parent=makecontigs)
+  		
+  		filterseqs = self.add_component("MothurFilterSeqs",
+										kwargs={'align_files':alignseqs.good_fasta_files,
+											'processors':self.args["processors"]})
+   		uniqueseqs_filter = self.add_component("MothurUniqueSeqs", 
+												kwargs={'fasta_files':filterseqs.filtered_fasta_files,
+													'count_table_files':alignseqs.good_count_table_files},
+												component_prefix="after_filter")
+   		precluster = self.add_component("MothurPreCluster",
+										kwargs={'fasta_files':uniqueseqs_filter.unique_fasta_files,
+											'count_table_files':uniqueseqs_filter.unique_count_table_files,
+											'processors':self.args["processors"]})
+   		chimerauchime = self.add_component("MothurChimeraUchime",
+											kwargs={'fasta_files':precluster.precluster_fasta_files,
+												'count_table_files':precluster.precluster_count_table_files,
+												'processors':self.args["processors"]},
+											parent=alignseqs)
+   		
     	# classify reads with the provided taxonomy
- 		classifyseqs = self.add_component("MothurClassifySeqs",kwargs={'fasta_files':chimerauchime.pick_fasta_files,'template_files':self.args["classify_template"],
- 																	'taxonomy_files':self.args["classify_taxonomy"],'count_table_files':chimerauchime.good_count_table_files, 
- 																	'without_krona':self.args["without_krona"]}, parent=chimerauchime)
+ 		classifyseqs = self.add_component("MothurClassifySeqs",
+										kwargs={'fasta_files':chimerauchime.pick_fasta_files,
+											'template_files':self.args["classify_template"],
+											'taxonomy_files':self.args["classify_taxonomy"],
+											'count_table_files':chimerauchime.good_count_table_files, 
+											'without_krona':self.args["without_krona"],
+											'processors':self.args["processors"]}, 
+										parent=chimerauchime)
   		# OTUs approach
-		distseqs = self.add_component("MothurDistSeqs", [chimerauchime.pick_fasta_files])
-		cluster = self.add_component("MothurCluster", kwargs={'dist_files':distseqs.dist_files,'count_table_files':chimerauchime.good_count_table_files})
+		distseqs = self.add_component("MothurDistSeqs", 
+									kwargs={'fasta_files':chimerauchime.pick_fasta_files,
+										'processors':self.args["processors"]})
+		cluster = self.add_component("MothurCluster", 
+									kwargs={'dist_files':distseqs.dist_files,
+										'count_table_files':chimerauchime.good_count_table_files})
 		
-		
-		otuanalysis = self.add_component("MothurOTUAnalysis", kwargs={'an_list_files':cluster.an_list_files,'count_table_files':chimerauchime.good_count_table_files,\
-    									'taxonomy_files':classifyseqs.taxonomy_files,'label':self.args["labels"],'tree_label':self.args["labels"],
-    									'without_krona':self.args["without_krona"]},parent=chimerauchime)
-		
\ No newline at end of file
+		otuanalysis = self.add_component("MothurOTUAnalysis", 
+										kwargs={'an_list_files':cluster.an_list_files,
+											'count_table_files':chimerauchime.good_count_table_files,
+											'taxonomy_files':classifyseqs.taxonomy_files,
+											'label':self.args["labels"],
+											'tree_label':self.args["labels"],
+											'without_krona':self.args["without_krona"]},
+										parent=chimerauchime)

workflows/miseq_diversity/workflow.properties

@@ -74,6 +74,21 @@ max_contigs_length.name = max_contigs_length
 max_contigs_length.flag = --max-contigs-length
 max_contigs_length.help = Maximum length sequences after make contigs
 
+max_ambiguous.flag = --max-ambiguous
+max_ambiguous.help = How many N allowed in a sequence
+max_ambiguous.default = 0
+max_ambiguous.type = int
+
+max_homopolymers.flag = --max-homopolymers
+max_ambiguous.help = Which is the maximum size of homopolymers to allow
+max_ambiguous.default = 8
+max_ambiguous.type = int
+
+processors.flag = --processors
+processors.help = How many cpus can be use during the process
+processors.default = 1
+processors.type = int
+
 reference_alignment.name = reference_alignment
 reference_alignment.flag = --reference-alignment
 reference_alignment.help = Where is stored the reference alignment