Add Maximal Information-based Nonparametric Exploration (MINE) tool.

This commit is contained in:
Daniel Blankenberg
2011-12-16 12:54:21 -05:00
parent 695aa191ef
commit d59b7ec591
3 changed files with 168 additions and 0 deletions
+1
View File
@@ -149,6 +149,7 @@
<tool file="stats/plot_from_lda.xml" />
<tool file="regVariation/t_test_two_samples.xml" />
<tool file="regVariation/compute_q_values.xml" />
<tool file="stats/MINE.xml" />
<label text="GFF" id="gff" />
<tool file="stats/count_gff_features.xml" />
+82
View File
@@ -0,0 +1,82 @@
<tool id="maximal_information_based_nonparametric_exploration" name="MINE" version="0.0.1">
<description>- Maximal Information-based Nonparametric Exploration</description>
<requirements>
<requirement type="package" version="1.0">MINE</requirement>
</requirements>
<command interpreter="python">mine_wrapper.py
--jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/mine/MINE.jar"
--infile "${input_file}"
#if str( $master_variable_type.master_variable_type_selector ) in [ 'allPairs', 'adjacentPairs' ]:
--master_variable "${master_variable_type.master_variable_type_selector}"
#else:
--master_variable "${master_variable_type.master_variable}"
#end if
--cv "${cv}"
--exp "${exp}"
--c "${c}"
##--gc ##skip
#if str( $master_variable_type.master_variable_type_selector ) != 'allPairs' and $master_variable_type.permute:
--permute
#end if
--output_results "${output_results}"
--output_log "${output_log}"
</command>
<inputs>
<param name="input_file" type="data" format="csv" label="CSV file" />
<conditional name="master_variable_type">
<param name="master_variable_type_selector" type="select" label="Choose the master variable type">
<option value="allPairs">allPairs</option>
<option value="adjacentPairs">adjacentPairs</option>
<option value="compare_against_ith" selected="True">compare against i-th</option>
</param>
<when value="compare_against_ith">
<param type="integer" value="0" name="master_variable" />
<param type="boolean" truevalue="--permute" false_value="" name="permute" checked="False" />
</when>
<when value="adjacentPairs">
<param type="boolean" truevalue="--permute" false_value="" name="permute" checked="False" />
</when>
</conditional>
<param type="float" value="0" name="cv" />
<param type="float" value="0.6" name="exp" />
<param type="float" value="15" name="c" />
</inputs>
<outputs>
<data format="csv" name="output_results" label="${tool.name} on ${on_string} (Results)" />
<data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
</outputs>
<tests>
<!-- TODO -->
</tests>
<help>
**What it does**
Applies the Maximal Information-based Nonparametric Exploration strategy to an input dataset.
See http://www.exploredata.net/ for more information.
------
**Citation**
For the underlying tool, please cite `David N. Reshef, Yakir A. Reshef, Hilary K. Finucane5, Sharon R. Grossman, Gilean McVean, Peter J. Turnbaugh, Eric S. Lander, Michael Mitzenmacher, Pardis C. Sabeti Detecting Novel Associations in Large Data Sets. Science. 2011 Dec. &lt;http://www.sciencemag.org/content/334/6062/1518&gt;`_
If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
</help>
</tool>
+85
View File
@@ -0,0 +1,85 @@
#!/usr/bin/env python
#Dan Blankenberg
"""
A wrapper script for running the MINE.jar commands.
"""
import sys, optparse, os, tempfile, subprocess, shutil
CHUNK_SIZE = 2**20 #1mb
BASE_NAME = "galaxy_mime_file.txt"
JOB_ID = "galaxy_mine"
def cleanup_before_exit( tmp_dir ):
if tmp_dir and os.path.exists( tmp_dir ):
print os.listdir( tmp_dir )
shutil.rmtree( tmp_dir )
def open_file_from_option( filename, mode = 'rb' ):
if filename:
return open( filename, mode = mode )
return None
def __main__():
#Parse Command Line
parser = optparse.OptionParser()
parser.add_option( '-j', '--jar', dest='jar', action='store', type="string", help='Location of JAR file' )
parser.add_option( '-i', '--infile', dest='infile', action='store', type="string", help='infile' )
parser.add_option( '-m', '--master_variable', dest='master_variable', action='store', type="string", help='master_variable' )
parser.add_option( '-v', '--cv', dest='cv', action='store', type="string", help='cv' )
parser.add_option( '-e', '--exp', dest='exp', action='store', type="string", help='exp' )
parser.add_option( '-c', '--c', dest='c', action='store', type="string", help='c' )
parser.add_option( '-p', '--permute', dest='permute', action='store_true', default=False, help='permute' )
parser.add_option( '-o', '--output_results', dest='output_results', action='store', type="string", help='output_results' )
parser.add_option( '-l', '--output_log', dest='output_log', action='store', type="string", help='output_log' )
parser.add_option( '', '--stdout', dest='stdout', action='store', type="string", default=None, help='If specified, the output of stdout will be written to this file.' )
parser.add_option( '', '--stderr', dest='stderr', action='store', type="string", default=None, help='If specified, the output of stderr will be written to this file.' )
(options, args) = parser.parse_args()
tmp_dir = tempfile.mkdtemp( prefix='tmp-MINE-' )
tmp_input_name = os.path.join( tmp_dir, BASE_NAME )
if options.permute:
permute = "-permute"
else:
permute = ""
os.symlink( options.infile, tmp_input_name )
cmd = 'java -jar "%s" "%s" %s -cv%s -exp%s -c%s %s "%s"' % ( options.jar, tmp_input_name, options.master_variable, options.cv, options.exp, options.c, permute, JOB_ID )
print cmd
#set up stdout and stderr output options
stdout = open_file_from_option( options.stdout, mode = 'wb' )
stderr = open_file_from_option( options.stderr, mode = 'wb' )
#if no stderr file is specified, we'll use our own
if stderr is None:
stderr = tempfile.NamedTemporaryFile( prefix="MINE-stderr-", dir=tmp_dir )
proc = subprocess.Popen( args=cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir )
return_code = proc.wait()
if return_code:
stderr_target = sys.stderr
else:
stderr_target = sys.stdout
stderr.flush()
stderr.seek(0)
while True:
chunk = stderr.read( CHUNK_SIZE )
if chunk:
stderr_target.write( chunk )
else:
break
stderr.close()
print os.listdir( tmp_dir )
shutil.move( '%s,%s,Results.csv' % ( tmp_input_name, JOB_ID ), options.output_results )
shutil.move( '%s,%s,Status.csv' % ( tmp_input_name, JOB_ID ), options.output_log )
cleanup_before_exit( tmp_dir )
if __name__=="__main__": __main__()