Add option to delete bams.

workflows/casava_qc/__init__.py

@@ -107,7 +107,7 @@ class CasavaQualityCheck (NG6Workflow):
             sample_lane_prefixes = None
             if group_prefix is not None :
                 sample_lane_prefixes = (Utils.get_group_basenames(filtered_read1_files+filtered_read2_files, "lane")).keys()
-            bwa = self.add_component("BWA", [indexed_ref, filtered_read1_files, filtered_read2_files, sample_lane_prefixes], parent = fastqilluminafilter)
+            bwa = self.add_component("BWA", [indexed_ref, filtered_read1_files, filtered_read2_files, sample_lane_prefixes, "aln", not self.args["delete_bam"]], parent = fastqilluminafilter)
             
             # make some statistic on the alignement
             alignmentstats = self.add_component("AlignmentStats", [bwa.bam_files, is_paired_end, False], parent = bwa)

workflows/casava_qc/workflow.properties

@@ -72,6 +72,11 @@ keep_reads.help = Keep reads which pass the Illumina filters or keep reads which
 keep_reads.default = pass_illumina_filters
 keep_reads.choices = pass_illumina_filters|not_pass_illumina_filters|all
 
+delete_bam = delete_bam
+delete_bam.flag = --delete-bam
+delete_bam.help = The BAM are not stored.
+delete_bam.default = False
+
 histogram_width.name = histogram_width
 histogram_width.flag = --histogram_width
 histogram_width.help = Explicitly sets the histogram width, overriding automatic truncation of histogram tail. 

workflows/components/bwa.py

@@ -31,7 +31,7 @@ from weaver.abstraction import Map
 
 class BWA (Analysis):
     
-    def define_parameters(self, reference_genome, read1, read2=None, group_prefix=None, algorithm="aln"):
+    def define_parameters(self, reference_genome, read1, read2=None, group_prefix=None, algorithm="aln", keep_bam=True):
         self.read1 = InputFileList(read1, Formats.FASTQ)
         self.read2=None
         if algorithm=="aln":
@@ -55,6 +55,7 @@ class BWA (Analysis):
 
         self.group_prefix = group_prefix
         self.algorithm = algorithm
+        self.keep_bam = keep_bam
         self.reference_genome = InputFile(reference_genome)
         #################################PATCH############################################
         self.source_file = reference_genome + "_source"
@@ -75,8 +76,9 @@ class BWA (Analysis):
         ##################################################################################
 
     def post_process(self):
-        # Finally create and add the archive to the analysis
-        self._save_files(self.bam_files)
+        if self.keep_bam:
+            # Finally create and add the archive to the analysis
+            self._save_files(self.bam_files)
         
     def get_version(self):
         cmd = [self.get_exec_path("bwa")]

workflows/illumina_qc/__init__.py

@@ -107,7 +107,7 @@ class IlluminaQualityCheck (NG6Workflow):
             sample_lane_prefixes = None
             if group_prefix is not None :
                 sample_lane_prefixes = (Utils.get_group_basenames(filtered_read1_files+filtered_read2_files, "lane")).keys()
-            bwa = self.add_component("BWA", [indexed_ref, filtered_read1_files, filtered_read2_files, sample_lane_prefixes], parent = fastqilluminafilter)
+            bwa = self.add_component("BWA", [indexed_ref, filtered_read1_files, filtered_read2_files, sample_lane_prefixes, "aln", not self.args["delete_bam"]], parent = fastqilluminafilter)
             
             # make some statistic on the alignement
             alignmentstats = self.add_component("AlignmentStats", [bwa.bam_files, is_paired_end, True], parent = bwa)

workflows/illumina_qc/workflow.properties

@@ -72,6 +72,11 @@ keep_reads.help = Keep reads which pass the Illumina filters or keep reads which
 keep_reads.default = pass_illumina_filters
 keep_reads.choices = pass_illumina_filters|not_pass_illumina_filters|all
 
+delete_bam = delete_bam
+delete_bam.flag = --delete-bam
+delete_bam.help = The BAM are not stored.
+delete_bam.default = False
+
 histogram_width.name = histogram_width
 histogram_width.flag = --histogram_width
 histogram_width.help = Explicitly sets the histogram width, overriding automatic truncation of histogram tail. 

workflows/illumina_rnaseq/__init__.py

@@ -105,7 +105,7 @@ class RnaSeqQualityCheck (NG6Workflow):
             sample_lane_prefixes = None
             if group_prefix is not None :
                 sample_lane_prefixes = (Utils.get_group_basenames(filtered_read1_files+filtered_read2_files, "lane")).keys()
-            bwa = self.add_component("BWA", [indexed_ref, filtered_read1_files, filtered_read2_files, sample_lane_prefixes], parent = fastqilluminafilter)
+            bwa = self.add_component("BWA", [indexed_ref, filtered_read1_files, filtered_read2_files, sample_lane_prefixes, "aln", not self.args["delete_bam"]], parent = fastqilluminafilter)
       
             # make some statistic on the alignement
             alignmentstats = self.add_component("AlignmentStats", [bwa.bam_files, is_paired_end], parent = bwa, component_prefix="bwa")
@@ -129,7 +129,7 @@ class RnaSeqQualityCheck (NG6Workflow):
                 concat_read2_files = filtered_read2_files
             concat_read1_files = sorted(concat_read1_files)
             concat_read2_files = sorted(concat_read2_files)
-            tophat = self.add_component("TopHat", [indexed_ref, concat_read1_files, concat_read2_files], parent = fastqilluminafilter)
+            tophat = self.add_component("TopHat", [indexed_ref, concat_read1_files, concat_read2_files, "25000", "6", not self.args["delete_bam"]], parent = fastqilluminafilter)
             
             # make some statistic on the alignement
             alignmentstats = self.add_component("AlignmentStats", [tophat.bam_files, is_paired_end], parent = tophat, component_prefix="tophat")

workflows/illumina_rnaseq/components/tophat.py

@@ -32,7 +32,7 @@ from ng6.utils import Utils
 
 class TopHat (Analysis):
     
-    def define_parameters(self, index_ref_genome, read1, read2, max_intron_length="25000", nb_threads="6", archive_name=None):   
+    def define_parameters(self, index_ref_genome, read1, read2, max_intron_length="25000", nb_threads="6", keep_bam=True, archive_name=None):   
         self.read1 = InputFileList(read1, Formats.FASTQ)
         self.read2 = None
        
@@ -55,6 +55,7 @@ class TopHat (Analysis):
 
         self.max_intron_length = max_intron_length
         self.nb_threads = nb_threads
+        self.keep_bam = keep_bam
 
     def define_analysis(self):
         self.name = "TopHat Alignment"
@@ -63,8 +64,9 @@ class TopHat (Analysis):
         self.options = self.max_intron_length + " " + self.nb_threads
 
     def post_process(self):
-        # Finally create and add the archive to the analysis
-        self._save_files(self.bam_files)
+        if self.keep_bam:
+            # Finally create and add the archive to the analysis
+            self._save_files(self.bam_files)
         
     def get_version(self):
         cmd = [self.get_exec_path("tophat2"), "-v"]

workflows/illumina_rnaseq/workflow.properties

@@ -55,6 +55,11 @@ keep_reads.help = Keep reads which pass the Illumina filters or keep reads which
 keep_reads.default = pass_illumina_filters
 keep_reads.choices = pass_illumina_filters|not_pass_illumina_filters|all
 
+delete_bam = delete_bam
+delete_bam.flag = --delete-bam
+delete_bam.help = The BAM are not stored.
+delete_bam.default = False
+
 compression.name = compression
 compression.flag = --compression
 compression.help = How should data be compressed once archived (none|gz|bz2)