concatenate fastq for casava directory analyse

workflows/illumina_matepair/__init__.py

@@ -34,15 +34,23 @@ class IlluminaMatePair (NG6Workflow):
         # manage the sequences files
         group_prefix = None
         
-        print self.args['files_read']
+        print self.args['sample_description']['lane_number']    
+        print self.project.get_name()
+        print self.args['sample_description']['casava_directory']
         print "---------------------"
         if self.args['sample_description']['casava_directory'] is not None :
             if self.args['sample_description']['lane_number'] is None :
                 raise ValueError, "lane-number must be specified with casava-directory."
-            mids_desc_array, self.read1_files, self.read2_files = Utils.filesFromCasava( self.args['sample_description']['casava_directory'], self.project.get_name(), self.args['sample_description']['lane_number'] ) 
+            
+            mids_desc_array, self.read1_files, self.read2_files, undetermined_read1_files, undetermined_read2_files = Utils.filesFromCasava( self.args['sample_description']['casava_directory'], self.project.get_name(), self.args['sample_description']['lane_number'] ) 
+            #print mids_desc_array, self.read1_files, self.read2_files, undetermined_read1_files, undetermined_read2_files
             group_prefix = (Utils.get_group_basenames(self.read1_files+self.read2_files, "read")).keys()
             self.runobj.add_mids_description(mids_desc_array)
             
+            # statistics about demultiplexing
+            if len(undetermined_read1_files) > 0 :
+                demultiplex_stats = self.add_component("DemultiplexStats", [self.read1_files, undetermined_read1_files]) 
+                           
         elif (self.args['files_read'][0]['read_1'] is not None) and (len(self.args['files_read'][0]['read_1']) > 0) :
             print self.args['files_read'][0]
             self.read1_files = []
@@ -101,7 +109,10 @@ class IlluminaMatePair (NG6Workflow):
             contamination_search = self.add_component("ContaminationSearch", [filtered_read1_files+filtered_read2_files, self.args["databank"], reads_prefixes], parent = fastqilluminafilter)
         
         # mate_pair analyse 
-        cutadapt = self.add_component("CutAdapt",[filtered_read1_files,filtered_read2_files,{"g":["CTGTCTCTT","ATACACATCT","AGATCTAT","AAGAGACAG"]},{"g":["CTGTCTCTT","ATACACATCT","AGATCTAT","AAGAGACAG"]},is_paired_end,0.1,4,20 ],parent= fastqilluminafilter)
+        concatenate1 = self.add_component("ConcatenateFilesGroups", [filtered_read1_files, (Utils.get_group_basenames(self.read1_files, "read")).keys()],component_prefix="read1")
+        concatenate2 = self.add_component("ConcatenateFilesGroups", [filtered_read2_files, (Utils.get_group_basenames(self.read2_files, "read")).keys()],component_prefix="read2")
+        
+        cutadapt = self.add_component("CutAdapt",[concatenate1.concat_files, concatenate2.concat_files,{"g":["CTGTCTCTT","ATACACATCT","AGATCTAT","AAGAGACAG"]},{"g":["CTGTCTCTT","ATACACATCT","AGATCTAT","AAGAGACAG"]},is_paired_end,0.1,4,20 ],parent= fastqilluminafilter)
         
         #reverse_complement