Mercurial > repos > peterjc > tmhmm_and_signalp

changeset 3:f3b373a41f81

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Migrated tool version 0.0.6 from old tool shed archive to new tool shed repository
author peterjc
date Tue, 07 Jun 2011 18:05:13 -0400
parents 6901298ac16c
children 81caef04ce8b
files tools/protein_analysis/README tools/protein_analysis/seq_analysis_utils.py tools/protein_analysis/signalp3.xml tools/protein_analysis/suite_config.xml tools/protein_analysis/tmhmm2.xml
diffstat 5 files changed, 20 insertions(+), 12 deletions(-) [+]
line wrap: on
line diff
--- a/tools/protein_analysis/README	Tue Jun 07 18:04:39 2011 -0400
+++ b/tools/protein_analysis/README	Tue Jun 07 18:05:13 2011 -0400
@@ -72,11 +72,15 @@
        - Additional unit tests
 v0.0.4 - Ignore comment lines in tmhmm2 output.
 v0.0.5 - Explicitly request tmhmm short output (may not be the default)
+v0.0.6 - Improvement to how sub-jobs are run (should be faster)
 
 Developers
 ==========
 
-These wrappers are currently being developed on the following hg branch:
+This script and other tools are being developed on the following hg branch:
+http://bitbucket.org/peterjc/galaxy-central/src/tools
+
+This incorporates the previously used hg branch:
 http://bitbucket.org/peterjc/galaxy-central/src/seq_analysis
 
 For making the "Galaxy Tool Shed" http://community.g2.bx.psu.edu/ tarball use
--- a/tools/protein_analysis/seq_analysis_utils.py	Tue Jun 07 18:04:39 2011 -0400
+++ b/tools/protein_analysis/seq_analysis_utils.py	Tue Jun 07 18:05:13 2011 -0400
@@ -102,28 +102,32 @@
         raise err
     return files
 
-def run_jobs(jobs, threads):
+def run_jobs(jobs, threads, verbose=False):
     """Takes list of cmd strings, returns dict with error levels."""
     pending = jobs[:]
     running = []
     results = {}
     while pending or running:
-        #print "%i jobs pending, %i running, %i completed" \
-        #      % (len(jobs), len(running), len(results))
         #See if any have finished
         for (cmd, process) in running:
-            return_code = process.wait()
+            return_code = process.poll() #non-blocking
             if return_code is not None:
                 results[cmd] = return_code
         running = [(cmd, process) for (cmd, process) in running \
                    if cmd not in results]
+        if verbose:
+            print "%i jobs pending, %i running, %i completed" \
+                  % (len(pending), len(running), len(results))
         #See if we can start any new threads
         while pending and len(running) < threads:
             cmd = pending.pop(0)
+            if verbose:
+                print cmd
             process = subprocess.Popen(cmd, shell=True)
             running.append((cmd, process))
         #Loop...
-        sleep(1)
-    #print "%i jobs completed" % len(results)
+        sleep(10)
+    if verbose:
+        print "%i jobs completed" % len(results)
     assert set(jobs) == set(results)
     return results
--- a/tools/protein_analysis/signalp3.xml	Tue Jun 07 18:04:39 2011 -0400
+++ b/tools/protein_analysis/signalp3.xml	Tue Jun 07 18:05:13 2011 -0400
@@ -1,4 +1,4 @@
-<tool id="signalp3" name="SignalP 3.0" version="0.0.3">
+<tool id="signalp3" name="SignalP 3.0" version="0.0.6">
     <description>Find signal peptides in protein sequences</description>
     <command interpreter="python">
       signalp3.py $organism $truncate 8 $fasta_file $tabular_file
--- a/tools/protein_analysis/suite_config.xml	Tue Jun 07 18:04:39 2011 -0400
+++ b/tools/protein_analysis/suite_config.xml	Tue Jun 07 18:05:13 2011 -0400
@@ -1,9 +1,9 @@
-    <suite id="tmhmm_and_signalp" name="TMHMM and SignalP" version="0.0.5">
+    <suite id="tmhmm_and_signalp" name="TMHMM and SignalP" version="0.0.6">
         <description>Wrappers for TMHMM and SignalP</description>
-        <tool id="tmhmm2" name="TMHMM 2.0" version="0.0.5">
+        <tool id="tmhmm2" name="TMHMM 2.0" version="0.0.6">
             <description>Find transmembrane domains in protein sequences</description>
         </tool>
-        <tool id="signalp3" name="SignalP 3.0" version="0.0.3">
+        <tool id="signalp3" name="SignalP 3.0" version="0.0.6">
             <description>Find signal peptides in protein sequences</description>
         </tool>
     </suite>
--- a/tools/protein_analysis/tmhmm2.xml	Tue Jun 07 18:04:39 2011 -0400
+++ b/tools/protein_analysis/tmhmm2.xml	Tue Jun 07 18:05:13 2011 -0400
@@ -1,4 +1,4 @@
-<tool id="tmhmm2" name="TMHMM 2.0" version="0.0.5">
+<tool id="tmhmm2" name="TMHMM 2.0" version="0.0.6">
     <description>Find transmembrane domains in protein sequences</description>
     <command interpreter="python">
       tmhmm2.py 8 $fasta_file $tabular_file