Changeset 2556

Timestamp:

Aug 5, 2014, 3:58:08 PM (9 years ago)

Author:

Nicklas Nordborg

Message:

References #614: Improve error handling when executing jobs on the cluster

Running samtools index ... which was the last part from the tophat script. Created a new statistics script, alignment_statistics.sh which replaces the statistics_tophat.sh. The new scripts works on a single folder given as an argument to the script instead of using a file with paths to BAM files.

Since this script only uses 'samtools' no redirection wrapper is not needed.

File:

• extensions/net.sf.basedb.reggie/trunk/src/net/sf/basedb/reggie/servlet/MaskAlignServlet.java (modified) (6 diffs)

extensions/net.sf.basedb.reggie/trunk/src/net/sf/basedb/reggie/servlet/MaskAlignServlet.java

@@ -380 +380 @@
           script.cmd("cp ${ScriptDir}/stdwrap.sh .");
           script.cmd("cp ${ScriptDir}/picard .");
-          script.cmd("cp ${ScriptDir}/statistics_tophat.sh .");
+          script.cmd("cp ${ScriptDir}/alignment_statistics.sh .");
           script.cmd("cp ${ScriptDir}/sync_resultfiles.sh .");
           script.newLine();
@@ -432 +432 @@
           script.newLine();
 
-          script.progress(60, "Running picard MarkDuplicates");
+          script.progress(70, "Running picard MarkDuplicates");
           String picardCmd = "./picard MarkDuplicates";
           picardCmd += " INPUT=fastq.masked.tophat/accepted_hits.bam";
@@ -441 +441 @@
           script.cmd(picardCmd);
           script.cmd("mv fastq.masked.tophat/accepted_hits.bam.tmp_picard fastq.masked.tophat/accepted_hits.bam");
-
-          // TODO - other scripts from tophat_single.sh script
-
-          script.comment("Run alignment analysis");
-          script.progress(80, "Running alignment analysis");
-          script.cmd("find fastq.masked.tophat -name \"accepted_hits.bam\" > accepted.list");
-          // TODO duplicate.sh and other scripts have hardocded paths to other scripts and folders
-          script.comment("./duplicate.sh < accepted.list >& duplicate.out");
-          script.bkgr("./statistics_tophat.sh < accepted.list >& statistics_tophat.out");
+          script.newLine();
+          
+          script.progress(80, "Creating BAM index");
+          script.cmd("samtools index fastq.masked.tophat/accepted_hits.bam");
+          script.newLine();
+
+          script.progress(90, "Culculating alignment statistics");
+          script.cmd("./alignment_statistics.sh fastq.masked.tophat > " + jobFolder + "/alignment_statistics.out");
           script.newLine();
           
@@ -456 +455 @@
           script.newLine();
           
-          script.progress(90, "Copying result files");
-          script.comment("Copy filter information back to job folder for importing into BASE");
-          script.cmd("cp fastq.masked.tophat/*_tophatstats.out " + jobFolder + "/tophatstats.out");
-          script.newLine();
+          script.progress(90, "Copying result files to project archive");
           script.comment("Sync result files to project archive");
           script.cmd("echo " + merged.getName() + " > sync.list");
@@ -630 +626 @@
     {
       CmdResult masked = cluster.executeCmd(ssh, "cat " + cluster.getJobFolder() + "/" + jobStatus.getJobName() + "/masked.out", 2);
-      CmdResult tophat = cluster.executeCmd("cat " + cluster.getJobFolder() + "/" + jobStatus.getJobName() + "/tophatstats.out" , 2);
-      if (masked.getExitStatus() == 0 && tophat.getExitStatus() == 0)
-      {
-        long[] reads = parseMaskedAndAlignedOut(sc, job, masked.getStdout(), tophat.getStdout());
+      CmdResult statistics = cluster.executeCmd("cat " + cluster.getJobFolder() + "/" + jobStatus.getJobName() + "/alignment_statistics.out" , 2);
+      if (masked.getExitStatus() == 0 && statistics.getExitStatus() == 0)
+      {
+        long[] reads = parseMaskedAndAlignedOut(sc, job, masked.getStdout(), statistics.getStdout());
         // 0 = number of reads after filter, 1 = number of reads after align
         return Values.formatNumber(reads[0]/1000000f, 1) + "M reads after mask; "  + Values.formatNumber(reads[1]/1000000f, 1) + "M reads after alignment";
@@ -639 +635 @@
       else
       {
-        job.setDescription(masked.getStderr() + "\n" + tophat.getStderr());
+        job.setDescription(masked.getStderr() + "\n" + statistics.getStderr());
       }
       return null;