Adaptation des scripts pour PicardTools 2.14.1 SGE

ui/nG6/pi1/analysis_table.tpl

 {*
 Copyright (C) 2009 INRA 
  
-This program is free software: you can redistribute it and/or modify
+This program is a free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
 the Free Software Foundation, either version 3 of the License, or
 (at your option) any later version.

workflows/components/alignmentstats.py

@@ -152,7 +152,7 @@ class AlignmentStats (Analysis):
         # Duplication stats
         if self.search_dupl:
             self.tmp_bam = self.get_outputs('{basename_woext}_noDupl.bam', self.bam_files)
-            self.add_shell_execution("java -Xmx4g -jar " + self.get_exec_path("MarkDuplicates") + " INPUT=$1 METRICS_FILE=$2 OUTPUT=$3" + self.duplication_options + " 2> $4", 
+            self.add_shell_execution("/tools/java/jre1.8.0_45/bin/java -Xmx4g -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/components/insertssizes.py

@@ -20,7 +20,19 @@ from subprocess import Popen, PIPE
 
 from ng6.analysis import Analysis
 
-def inserts_metrics(bam_file, pairs_count_file, metrics_file, hist_file, log_file, samtools_path, collectinsertsizemetrics_path, options_dump_path, memory):
+# def inserts_metrics(bam_file, pairs_count_file, metrics_file, hist_file, log_file, samtools_path, collectinsertsizemetrics_path, options_dump_path, memory):
+#     """
+#       @param bam_file : path for bam
+#       @param pairs_count_file : path to the produced file with the number of reads pairs in bam
+#       @param metrics_file : path to the metrics file produced by collectinsertsizemetrics
+#       @param hist_file : path to the histogram produced by collectinsertsizemetrics
+#       @param log_file : path to the log produced by collectinsertsizemetrics
+#       @param samtools_path : path to the software samtools
+#       @param collectinsertsizemetrics_path : path to the software collectinsertsizemetrics
+#       @param picard_path : path to the software picard.jar
+#       @param options : options for the software collectinsertsizemetrics
+#     """
+def inserts_metrics(bam_file, pairs_count_file, metrics_file, hist_file, log_file, samtools_path, picard_path, options_dump_path, memory):
     """
       @param bam_file : path for bam
       @param pairs_count_file : path to the produced file with the number of reads pairs in bam
@@ -28,7 +40,7 @@ def inserts_metrics(bam_file, pairs_count_file, metrics_file, hist_file, log_fil
       @param hist_file : path to the histogram produced by collectinsertsizemetrics
       @param log_file : path to the log produced by collectinsertsizemetrics
       @param samtools_path : path to the software samtools
-      @param collectinsertsizemetrics_path : path to the software collectinsertsizemetrics
+      @param picard_path : path to the software picard.jar
       @param options : options for the software collectinsertsizemetrics
     """
     from subprocess import Popen, PIPE
@@ -45,7 +57,7 @@ def inserts_metrics(bam_file, pairs_count_file, metrics_file, hist_file, log_fil
     
     if properly_paired_nb > 0 :
         # Process inserts sizes metrics
-        command = Popen( ["-c", "java "+xmx+" -jar " + collectinsertsizemetrics_path + " " +options + " HISTOGRAM_FILE=" + hist_file + " INPUT=" + bam_file + " OUTPUT=" + metrics_file + " 2> " + log_file], shell=True, stdout=PIPE, stderr=PIPE )
+        command = Popen( ["-c", "/tools/java/jre1.8.0_45/bin/java "+xmx+" -jar " + picard_path + " CollectInsertSizeMetrics " +options + " HISTOGRAM_FILE=" + hist_file + " INPUT=" + bam_file + " OUTPUT=" + metrics_file + " 2> " + log_file], shell=True, stdout=PIPE, stderr=PIPE )
         stdout, stderr = command.communicate()
         # Count nb pairs in bam file
         command = Popen( ["-c", samtools_path + " view -F384 " + bam_file + " | wc -l"], shell=True, stdout=PIPE, stderr=PIPE) # First read in pair 
@@ -126,10 +138,14 @@ class InsertsSizes (Analysis):
         self._create_and_archive(self.info_files, self.archive_name)
         
     def get_version(self):
-        cmd = ["java", "-Xmx1g", "-jar", self.get_exec_path("CollectInsertSizeMetrics"),"--version"]
-        p = Popen(cmd, stdout=PIPE, stderr=PIPE)
+        cmd = "/tools/java/jre1.8.0_45/bin/java -Xmx1g -jar {} CollectInsertSizeMetrics --version".format(self.get_exec_path("Picard"))
+        p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True)
         stdout, stderr = p.communicate()
-        return stderr.split()[0]
+        return(stderr.decode("utf-8").rsplit()[0])
+#         cmd = ["/tools/java/jre1.8.0_45/bin/java", "-Xmx1g", "-jar", self.get_exec_path("Picard")," CollectInsertSizeMetrics --version"]
+#         p = Popen(cmd, stdout=PIPE, stderr=PIPE)
+#         stdout, stderr = p.communicate()
+#         return stderr.split()[0]
                      
     def process(self):
         options_dump_path = self.get_temporary_file(".dump")
@@ -140,11 +156,11 @@ class InsertsSizes (Analysis):
         for i in range(len(self.bam_files)):
             self.add_python_execution(inserts_metrics,cmd_format="{EXE} {IN} {OUT} {ARG}",
                                       inputs=self.bam_files[i], outputs=[self.pairs_count_files[i], self.info_files[i], self.hist_files[i], self.log_files[i]], 
-                                      arguments=[self.get_exec_path("samtools"), self.get_exec_path("CollectInsertSizeMetrics"), options_dump_path, self.memory])
+                                      arguments=[self.get_exec_path("samtools"), self.get_exec_path("Picard"), options_dump_path, self.memory])
             
     def parse_pairs_count_file(self, input_file):
         """
-          @param input_file  : the pairs count file path
+          @param input_file  : the pairs  count file path
           @return            : the number of properly paired
         """
         count_file_fh = open(input_file, "r")

workflows/illumina_rnaseq/components/starindex.py

@@ -12,7 +12,7 @@
 # GNU General Public License for more details.
 # 
 # You should have received a copy of the GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# along with this program.  If not, see <http://www.gnu.org/licenses/>. 
 #
 
 import os
@@ -35,7 +35,7 @@ class STARIndex (Component):
     def process(self):
         xmx="-Xmx" + self.memory.lower()
         # normalize fasta
-        self.add_shell_execution( "java " + xmx + " -jar " + self.get_exec_path("NormalizeFasta.jar") + " I=$1 O=$2  ", 
+        self.add_shell_execution( "/tools/java/jre1.8.0_45/bin/java " + xmx + " -jar " + self.get_exec_path("Picard") + " NormalizeFasta I=$1 O=$2  ", 
                                   cmd_format="{EXE} {IN} {OUT}", map=False,
                                   inputs = self.input_fasta, outputs = self.normalized_fasta_file)
         

[Gerald Salin]

link to issue #6 (closed)