Merge branch 'markduplicates' into 'master'

Modification for duplicate search and visualisation ok

See merge request !33

ui/nG6/pi1/analyzes/AlignmentStats.tpl

@@ -41,7 +41,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 				{elseif $split_param[0] == "READ_NAME_REGEX"}
 					<li class="parameter">Regular expression that can be used to extract three variables : tile/region, x coordinate and y coordinate ({$split_param[0]}={$split_param[1]}). These values are used to estimate the rate of optical duplication.</li>
 				{elseif $split_param[0] == "OPTICAL_DUPLICATE_PIXEL_DISTANCE"}
-					<li class="parameter">The maximum offset between two duplicte clusters in order to consider them optical duplicates is {$split_param[1]} ({$split_param[0]}={$split_param[1]}).</li>
+					<li class="parameter">The maximum offset between two duplicate clusters in order to consider them optical duplicates is {$split_param[1]} ({$split_param[0]}={$split_param[1]}).</li>
 				{/if}
 			{/if}
 		{/foreach}	
@@ -71,7 +71,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 				<th class="numeric-sort" style="vertical-align:Middle"><center>Singletons</center></th>
 	  			<th class="numeric-sort" style="vertical-align:Middle"><center>Mate mapped on a different chr</center></th>
 	  			<th class="numeric-sort" style="vertical-align:Middle"><center>Supplementary</center></th>
-				<th class="numeric-sort" style="vertical-align:Middle"><center>Duplicated</center></th>
+				<th class="numeric-sort" style="vertical-align:Middle"><center>Nb read duplicated</center></th>
 				<th class="numeric-sort" style="vertical-align:Middle"><center>Read pair duplicates</center></th>
 				<th class="numeric-sort" style="vertical-align:Middle"><center>Read pair optical duplicates</center></th>
 				
@@ -122,7 +122,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 						<td>-</td>
 						<td>-</td>
 						{else}
-						<td>{($sample_results["default"].pairDuplicates*2 + $sample_results["default"].unpairDuplicates)|number_format:0:' ':' '}</td>
+						<td>{($sample_results["default"].pairDuplicates*2 + $sample_results["default"].unpairDuplicates)|number_format:0:' ':' '} ({$sample_results["default"].percentDuplication}*100%)</td>
 						<td>{$sample_results["default"].pairDuplicates|number_format:0:' ':' '}</td>
 						<td>{$sample_results["default"].pairOpticalDuplicates|number_format:0:' ':' '}</td>
 						{/if}

workflows/components/alignmentstats.py

@@ -43,7 +43,7 @@ class AlignmentStats (Analysis):
         self.add_parameter("assume_sorted", "assume_sorted", default=assume_sorted, type=bool)
         self.add_parameter("validation_stringency", "validation_stringency", default=validation_stringency)
         self.add_parameter("max_file_handles", "max_file_handles", default=max_file_handles, type=int)
-        self.add_parameter("sorting_collection_size_ratio", "sorting_collection_size_ratio", default=max_file_handles, type=float)
+        self.add_parameter("sorting_collection_size_ratio", "sorting_collection_size_ratio", default=sorting_collection_size_ratio, type=float)
         self.add_parameter("archive_name", "archive_name", default=archive_name)
         self.memory = '4G'
         if self.get_memory() != None :
@@ -136,6 +136,7 @@ class AlignmentStats (Analysis):
                 self._add_result_element(sample, "pairDuplicates", dupl_info["Unknown Library"]["READ_PAIR_DUPLICATES"])
                 self._add_result_element(sample, "unpairDuplicates", dupl_info["Unknown Library"]["UNPAIRED_READ_DUPLICATES"])
                 self._add_result_element(sample, "pairOpticalDuplicates", dupl_info["Unknown Library"]["READ_PAIR_OPTICAL_DUPLICATES"])
+                self._add_result_element(sample, "percentDuplication", dupl_info["Unknown Library"]["PERCENT_DUPLICATION"])
             
             
         # Finaly create and add the archive to the analyse
@@ -156,7 +157,7 @@ class AlignmentStats (Analysis):
         xmx="-Xmx"+self.memory.lower()
         if self.search_dupl:
             self.tmp_bam = self.get_outputs('{basename_woext}_noDupl.bam', self.bam_files)
-            self.add_shell_execution(self.get_exec_path("javaPICARD")+ " "+ xmx +"-jar " + self.get_exec_path("Picard") + " MarkDuplicates INPUT=$1 METRICS_FILE=$2 OUTPUT=$3" + self.duplication_options + " 2> $4", 
+            self.add_shell_execution(self.get_exec_path("javaPICARD")+ " "+ xmx +" -jar " + self.get_exec_path("Picard") + " MarkDuplicates INPUT=$1 METRICS_FILE=$2 OUTPUT=$3" + self.duplication_options + " 2> $4", 
                                      cmd_format='{EXE} {IN} {OUT}', map=True,
                                      inputs=self.bam_files, outputs=[self.duplication_files, self.tmp_bam, self.dupl_stderrs])
         

workflows/illumina_qc/__init__.py

@@ -64,7 +64,7 @@ class IlluminaQualityCheck (CasavaNG6Workflow):
                 bwa = self.add_component("BWA", [indexed_ref, filtered_read1_files, filtered_read2_files, sample_lane_prefixes, "mem", not self.delete_bam], parent = fastqilluminafilter)
             
             # make some statistic on the alignement
-            alignmentstats = self.add_component("AlignmentStats", [bwa.bam_files, self.is_paired_end(), False], parent = bwa)
+            alignmentstats = self.add_component("AlignmentStats", [bwa.bam_files, self.is_paired_end(), True], parent = bwa)
             
             if self.is_paired_end():
                 # process insert sizes