Mercurial > repos > peterjc > effectivet3

changeset 0:43436379876f

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
author peterjc
date Tue, 07 Jun 2011 17:21:30 -0400
parents
children e607c342312f
files tools/protein_analysis/effectiveT3.py tools/protein_analysis/effectiveT3.txt tools/protein_analysis/effectiveT3.xml
diffstat 3 files changed, 298 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/protein_analysis/effectiveT3.py	Tue Jun 07 17:21:30 2011 -0400
@@ -0,0 +1,140 @@
+#!/usr/bin/env python
+"""Wrapper for EffectiveT3 v1.0.1 for use in Galaxy.
+
+This script takes exactly five command line arguments:
+ * model name (e.g. TTSS_STD-1.0.1.jar)
+ * threshold (selective or sensitive)
+ * an input protein FASTA filename
+ * output tabular filename
+
+It then calls the standalone Effective T3 v1.0.1 program (not the
+webservice), and reformats the semi-colon separated output into
+tab separated output for use in Galaxy.
+"""
+import sys
+import os
+import subprocess
+
+#You may need to edit this to match your local setup,
+effectiveT3_jar = "/opt/EffectiveT3/TTSS_GUI-1.0.1.jar"
+
+
+def stop_err(msg, error_level=1):
+   """Print error message to stdout and quit with given error level."""
+   sys.stderr.write("%s\n" % msg)
+   sys.exit(error_level)
+
+if len(sys.argv) != 5:
+   stop_err("Require four arguments: model, threshold, input protein FASTA file & output tabular file")
+
+model, threshold, fasta_file, tabular_file = sys.argv[1:]
+
+if not os.path.isfile(fasta_file):
+   stop_err("Input FASTA file not found: %s" % fasta_file)
+
+if threshold not in ["selective", "sensitive"] \
+and not threshold.startswith("cutoff="):
+   stop_err("Threshold should be selective, sensitive, or cutoff=..., not %r" % threshold)
+
+def clean_tabular(raw_handle, out_handle):
+    """Clean up Effective T3 output to make it tabular."""
+    count = 0
+    positive = 0
+    errors = 0
+    for line in raw_handle:
+        if not line or line.startswith("#") \
+        or line.startswith("Id; Description; Score;"):
+            continue
+        assert line.count(";") >= 3, repr(line)
+        #Normally there will just be three semi-colons, however the
+        #original FASTA file's ID or description might have had
+        #semi-colons in it as well, hence the following hackery:
+        try:
+            id_descr, score, effective = line.rstrip("\r\n").rsplit(";",2)
+            #Cope when there was no FASTA description
+            if "; " not in id_descr and id_descr.endswith(";"):
+                id = id_descr[:-1]
+                descr = ""
+            else:
+                id, descr = id_descr.split("; ",1)
+        except ValueError:
+            stop_err("Problem parsing line:\n%s\n" % line)
+        parts = [s.strip() for s in [id, descr, score, effective]]
+        out_handle.write("\t".join(parts) + "\n")
+        count += 1
+        if float(score) < 0:
+           errors += 1
+        if effective.lower() == "true":
+           positive += 1
+    return count, positive, errors
+
+def run(cmd):
+    #Avoid using shell=True when we call subprocess to ensure if the Python
+    #script is killed, so too is the child process.
+    try:
+        child = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    except Exception, err:
+        stop_err("Error invoking command:\n%s\n\n%s\n" % (" ".join(cmd), err))
+    #Use .communicate as can get deadlocks with .wait(),
+    stdout, stderr = child.communicate()
+    return_code = child.returncode
+    if return_code:
+        if stderr and stdout:
+            stop_err("Return code %i from command:\n%s\n\n%s\n\n%s" % (return_code, err, stdout, stderr))
+        else:
+            stop_err("Return code %i from command:\n%s\n%s" % (return_code, err, stderr))
+
+if not os.path.isfile(effectiveT3_jar):
+   stop_err("Effective T3 JAR file not found: %s" % effectiveT3_jar)
+
+effectiveT3_dir = os.path.dirname(effectiveT3_jar)
+if not os.path.isdir(effectiveT3_dir):
+   stop_err("Effective T3 folder not found: %s" % effectiveT3_dir)
+
+effectiveT3_model = os.path.join(effectiveT3_dir, "module", model)
+if not os.path.isfile(effectiveT3_model):
+   stop_err("Effective T3 model JAR file not found: %s" % effectiveT3_model)
+
+#We will have write access whereever the output should be,
+temp_file = os.path.abspath(tabular_file + ".tmp")
+
+#Use absolute paths since will change current directory...
+tabular_file = os.path.abspath(tabular_file)
+fasta_file = os.path.abspath(fasta_file)
+
+cmd = ["java", "-jar", effectiveT3_jar,
+       "-f", fasta_file,
+       "-m", model,
+       "-t", threshold,
+       "-o", temp_file,
+       "-q"]
+
+try:
+    #Must run from directory above the module subfolder:
+    os.chdir(effectiveT3_dir)
+except:
+    stop_err("Could not change to Effective T3 folder: %s" % effectiveT3_dir)
+
+run(cmd)
+
+if not os.path.isfile(temp_file):
+   stop_err("ERROR - No output file from Effective T3")
+
+out_handle = open(tabular_file, "w")
+out_handle.write("#ID\tDescription\tScore\tEffective\n")
+data_handle = open(temp_file)
+count, positive, errors = clean_tabular(data_handle, out_handle)
+data_handle.close()
+out_handle.close()
+
+os.remove(temp_file)
+
+if errors:
+   print "%i sequences, %i positive, %i errors" \
+         % (count, positive, errors)
+else:
+   print "%i/%i sequences positive" % (positive, count)
+
+if count and count==errors:
+   #Galaxy will still  allow them to see the output file
+   stop_err("All your sequences gave an error code")
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/protein_analysis/effectiveT3.txt	Tue Jun 07 17:21:30 2011 -0400
@@ -0,0 +1,94 @@
+Galaxy wrapper for EffectiveT3 v1.0.1
+=====================================
+
+This wrapper is copyright 2011 by Peter Cock, The James Hutton Institute
+(formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved.
+See the licence text below.
+
+This is a wrapper for the command line Java tool EffectiveT3, v1.0.1,
+
+Jehl, Arnold and Rattei.
+Effective - a database of predicted secreted bacterial proteins
+Nucleic Acids Research, 39(Database issue), D591-5, 2011.
+http://dx.doi.org/10.1093/nar/gkq1154
+
+Arnold, Brandmaier, Kleine, Tischler, Heinz, Behrens, Niinikoski, Mewes, Horn and Rattei.
+Sequence-based prediction of type III secreted proteins.
+PLoS Pathog. 5(4):e1000376, 2009.
+http://dx.doi.org/10.1371/journal.ppat.1000376
+
+http://effectors.org/
+
+You can change the path by editing the definition near the start of the Python
+script effectiveT3.py, but by default it expects the following files to be
+installed at these locations:
+
+/opt/EffectiveT3/TTSS_GUI-1.0.1.jar
+/opt/EffectiveT3/module/TTSS_ANIMAL-1.0.1.jar
+/opt/EffectiveT3/module/TTSS_PLANT-1.0.1.jar
+/opt/EffectiveT3/module/TTSS_STD-1.0.1.jar
+
+To install the wrapper copy or move the following files under the Galaxy tools
+folder, e.g. in a tools/protein_analysis folder:
+
+* effectiveT3.xml (the Galaxy tool definition)
+* effectiveT3.py (the Python wrapper script)
+* effectiveT3.txt (this README file)
+
+You will also need to modify the tools_conf.xml file to tell Galaxy to offer the
+tool. If you are using other protein analysis tools like TMHMM or SignalP, put
+it next to them. Just add the line:
+
+<tool file="protein_analysis/effectiveT3.xml" />
+
+That's it.
+
+
+History
+=======
+
+v0.0.7 - Initial public release
+
+
+Developers
+==========
+
+This script and related tools are being developed on the following hg branch:
+http://bitbucket.org/peterjc/galaxy-central/src/tools
+
+For making the "Galaxy Tool Shed" http://community.g2.bx.psu.edu/ tarball use
+the following command from the Galaxy root folder:
+
+$ tar -czf effectiveT3.tar.gz tools/protein_analysis/effectiveT3.xml tools/protein_analysis/effectiveT3.py tools/protein_analysis/effectiveT3.txt
+
+Check this worked:
+
+$ tar -tzf effectiveT3.tar.gz
+tools/protein_analysis/effectiveT3.xml
+tools/protein_analysis/effectiveT3.py
+tools/protein_analysis/effectiveT3.txt
+
+
+Licence (MIT/BSD style)
+=======================
+
+Permission to use, copy, modify, and distribute this software and its
+documentation with or without modifications and for any purpose and
+without fee is hereby granted, provided that any copyright notices
+appear in all copies and that both those copyright notices and this
+permission notice appear in supporting documentation, and that the
+names of the contributors or copyright holders not be used in
+advertising or publicity pertaining to distribution of the software
+without specific prior permission.
+
+THE CONTRIBUTORS AND COPYRIGHT HOLDERS OF THIS SOFTWARE DISCLAIM ALL
+WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL THE
+CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT
+OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
+OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
+OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
+OR PERFORMANCE OF THIS SOFTWARE.
+
+NOTE: This is the licence for the Galaxy Wrapper only. NLStradamus
+is available and licenced separately.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/protein_analysis/effectiveT3.xml	Tue Jun 07 17:21:30 2011 -0400
@@ -0,0 +1,64 @@
+<tool id="effectiveT3" name="Effective T3" version="0.0.7">
+    <description>Find bacterial effectors in protein sequences</description>
+    <command interpreter="python">
+effectiveT3.py $module.fields.path
+#if $restrict.type=="cutoff":
+  cutoff=$restrict.cutoff
+#else:
+  $restrict.type
+#end if
+$fasta_file $tabular_file</command>
+    <inputs>
+        <param name="fasta_file" type="data" format="fasta" label="FASTA file of protein sequences"/> 
+        <param name="module" type="select" display="radio" label="Classification module">
+            <options from_file="effectiveT3.loc">
+                <column name="value" index="0"/>
+                <column name="name" index="1"/>
+                <column name="path" index="2"/>
+            </options>
+        </param>
+        <conditional name="restrict">
+            <param name="type" type="select" label="Cut-off setting">
+                <option value="selective">Selective (threshold set in module)</option>
+                <option value="sensitive">Sensitive (threshold set in module)</option>
+                <option value="cutoff">User defined cut-off</option>
+            </param>
+            <when value="selective" />
+            <when value="sensitive" />
+            <when value="cutoff" >
+                <param name="cutoff" type="float" min="0" max="1" label="Cut-off" value="" help="Threshold cut-off between 0 and 1"  />
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data name="tabular_file" format="tabular" label="$module.value_label results" />
+    </outputs>
+    <help>
+    
+**What it does**
+
+This calls the command line Effective T3 v1.0.1 tool for prediction of bacterial effector proteins.
+
+The input is a FASTA file of protein sequences, and the output is tabular with four columns (one row per protein):
+
+ * Sequence identifier
+ * Sequence description (from the FASTA file)
+ * Score (between 0 and 1, or negative for an error such as a very short peptide)
+ * Predicted effector (true/false)
+
+**References**
+
+Jehl, Arnold and Rattei.
+Effective - a database of predicted secreted bacterial proteins
+Nucleic Acids Research, 39(Database issue), D591-5, 2011.
+http://dx.doi.org/10.1093/nar/gkq1154
+
+Arnold, Brandmaier, Kleine, Tischler, Heinz, Behrens, Niinikoski, Mewes, Horn and Rattei.
+Sequence-based prediction of type III secreted proteins.
+PLoS Pathog. 5(4):e1000376, 2009.
+http://dx.doi.org/10.1371/journal.ppat.1000376
+
+http://effectors.org/
+
+    </help>
+</tool>