# HG changeset patch
# User pjbriggs
# Date 1421856457 18000
# Node ID fdad0c8c09577574093a4298c2c54764fda1b031
Uploaded initial version to test toolshed.
diff -r 000000000000 -r fdad0c8c0957 macs21_wrapper.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macs21_wrapper.py Wed Jan 21 11:07:37 2015 -0500
@@ -0,0 +1,208 @@
+#purpose: macs2 python wrapper
+#author: Ziru Zhou
+#date: November, 2012
+
+import sys, subprocess, tempfile, shutil, glob, os, os.path, gzip
+from galaxy import eggs
+import pkg_resources
+pkg_resources.require( "simplejson" )
+import simplejson
+
+CHUNK_SIZE = 1024
+
+#==========================================================================================
+#functions
+#==========================================================================================
+def gunzip_cat_glob_path( glob_path, target_filename, delete = False ):
+ out = open( target_filename, 'wb' )
+ for filename in glob.glob( glob_path ):
+ fh = gzip.open( filename, 'rb' )
+ while True:
+ data = fh.read( CHUNK_SIZE )
+ if data:
+ out.write( data )
+ else:
+ break
+ fh.close()
+ if delete:
+ os.unlink( filename )
+ out.close()
+
+def xls_to_interval( xls_file, interval_file, header = None ):
+ out = open( interval_file, 'wb' )
+ if header:
+ out.write( '#%s\n' % header )
+ wrote_header = False
+ #From macs readme: Coordinates in XLS is 1-based which is different with BED format.
+ #PJB: updated to keep original 'start' coordinate i.e. do not convert to BED
+ for line in open( xls_file ):
+ #keep all existing comment lines
+ if line.startswith( '#' ):
+ out.write( line )
+ #added for macs2 since there is an extra newline
+ ##elif line.startswith( '\n' ):
+ ## out.write( line )
+ elif not wrote_header:
+ out.write( '#%s' % line )
+ print line
+ wrote_header = True
+ else:
+ fields = line.split( '\t' )
+ if len( fields ) > 1:
+ try:
+ # Try to convert 'start' to int and shift
+ ##fields[1] = str( int( fields[1] ) - 1 )
+ # PJB don't correct, just test to see if it's an integer
+ int( fields[1] )
+ except ValueError:
+ # Integer conversion failed so comment out
+ # "bad" line instead
+ fields[0] = "#%s" % fields[0]
+ out.write( '\t'.join( fields ) )
+ out.close()
+
+#==========================================================================================
+#main
+#==========================================================================================
+def main():
+ #take in options file and output file names
+ options = simplejson.load( open( sys.argv[1] ) )
+ outputs = simplejson.load( open( sys.argv[2] ) )
+
+ #=================================================================================
+ #parse options and execute macs2
+ #=================================================================================
+ #default inputs that are in every major command
+ experiment_name = '_'.join( options['experiment_name'].split() ) #save experiment name here, it will be used by macs for some file names
+ cmdline = "macs2 %s -t %s" % ( options['command'], ",".join( options['input_chipseq'] ) )
+ if options['input_control']:
+ cmdline = "%s -c %s" % ( cmdline, ",".join( options['input_control'] ) )
+
+ #=================================================================================
+ if (options['command'] == "callpeak"):
+ output_summits_bed = outputs['output_summits_bed_file']
+ output_extra_html = outputs['output_extra_file']
+ output_extra_path = outputs['output_extra_file_path']
+ output_peaks = outputs['output_peaks_file']
+ output_narrowpeaks = outputs['output_narrowpeaks_file']
+ output_broadpeaks = outputs['output_broadpeaks_file']
+ output_gappedpeaks = outputs['output_gappedpeaks_file']
+ output_xls_to_interval_peaks_file = outputs['output_xls_to_interval_peaks_file']
+ output_treat_pileup = outputs['output_treat_pileup_file']
+ output_lambda_bedgraph = outputs['output_lambda_bedgraph_file']
+
+ cmdline = "%s --format='%s' --name='%s' --gsize='%s' --bw='%s'" % ( cmdline, options['format'], experiment_name, options['gsize'], options['bw'] )
+ if (options['broad'] == 'broad'):
+ cmdline = "%s --broad --broad-cutoff='%s'" % ( cmdline, options['broad_cutoff'] )
+ if 'pvalue' in options:
+ cmdline = "%s --pvalue='%s'" % ( cmdline, options['pvalue'] )
+ elif 'qvalue' in options:
+ cmdline = "%s --qvalue='%s'" % ( cmdline, options['qvalue'] )
+ cmdline = "%s --mfold %s %s %s %s %s %s --keep-dup %s" % (cmdline, options['mfoldlo'], options['mfoldhi'], options['nolambda'], options['bdg'], options['spmr'], options['call_summits'], options['keep_dup'] )
+
+ if 'nomodel' in options:
+ cmdline = "%s --nomodel --extsize='%s'" % ( cmdline, options['nomodel'] )
+ #=================================================================================
+ if (options['command'] == "bdgcmp"):
+ output_bdgcmp = outputs['output_bdgcmp_file']
+
+ cmdline = "%s -m %s -p %s -o bdgcmp_out.bdg" % ( cmdline, options['m'], options['pseudocount'] )
+ #=================================================================================
+
+ tmp_dir = tempfile.mkdtemp() #macs makes very messy output, need to contain it into a temp dir, then provide to user
+ stderr_name = tempfile.NamedTemporaryFile().name # redirect stderr here, macs provides lots of info via stderr, make it into a report
+ proc = subprocess.Popen( args=cmdline, shell=True, cwd=tmp_dir, stderr=open( stderr_name, 'wb' ) )
+ proc.wait()
+ #We don't want to set tool run to error state if only warnings or info, e.g. mfold could be decreased to improve model, but let user view macs log
+ #Do not terminate if error code, allow dataset (e.g. log) creation and cleanup
+ if proc.returncode:
+ stderr_f = open( stderr_name )
+ while True:
+ chunk = stderr_f.read( CHUNK_SIZE )
+ if not chunk:
+ stderr_f.close()
+ break
+ sys.stderr.write( chunk )
+
+ #=================================================================================
+ #copy files created by macs2 to appripriate directory with the provided names
+ #=================================================================================
+
+ #=================================================================================
+ #move files generated by callpeak command
+ if (options['command'] == "callpeak"):
+ #run R to create pdf from model script
+ if os.path.exists( os.path.join( tmp_dir, "%s_model.r" % experiment_name ) ):
+ cmdline = 'R --vanilla --slave < "%s_model.r" > "%s_model.r.log"' % ( experiment_name, experiment_name )
+ proc = subprocess.Popen( args=cmdline, shell=True, cwd=tmp_dir )
+ proc.wait()
+
+ #move bed out to proper output file
+ created_bed_name = os.path.join( tmp_dir, "%s_summits.bed" % experiment_name )
+ if os.path.exists( created_bed_name ):
+ shutil.move( created_bed_name, output_summits_bed )
+
+ #OICR peak_xls file
+ created_peak_xls_file = os.path.join( tmp_dir, "%s_peaks.xls" % experiment_name )
+ if os.path.exists( created_peak_xls_file ):
+ # shutil.copy( created_peak_xls_file, os.path.join ( "/mnt/galaxyData/tmp/", "%s_peaks.xls" % ( os.path.basename(output_extra_path) )))
+ shutil.copyfile( created_peak_xls_file, output_peaks )
+
+ #peaks.encodepeaks (narrowpeaks) file
+ created_narrowpeak_file = os.path.join (tmp_dir, "%s_peaks.narrowPeak" % experiment_name )
+ if os.path.exists( created_narrowpeak_file ):
+ shutil.move (created_narrowpeak_file, output_narrowpeaks )
+
+ #peaks.broadpeaks file
+ created_broadpeak_file = os.path.join (tmp_dir, "%s_peaks.broadPeak" % experiment_name )
+ if os.path.exists( created_broadpeak_file ):
+ shutil.move (created_broadpeak_file, output_broadpeaks )
+
+ #peaks.gappedpeaks file
+ created_gappedpeak_file = os.path.join (tmp_dir, "%s_peaks.gappedPeak" % experiment_name )
+ if os.path.exists( created_gappedpeak_file ):
+ shutil.move (created_gappedpeak_file, output_gappedpeaks )
+
+ #parse xls files to interval files as needed
+ #if 'xls_to_interval' in options:
+ if (options['xls_to_interval'] == "True"):
+ create_peak_xls_file = os.path.join( tmp_dir, '%s_peaks.xls' % experiment_name )
+ if os.path.exists( create_peak_xls_file ):
+ xls_to_interval( create_peak_xls_file, output_xls_to_interval_peaks_file, header = 'peaks file' )
+
+ #bedgraph bedgraph files
+ if (options['bdg']):
+ created_treat_pileup_file = os.path.join (tmp_dir, "%s_treat_pileup.bdg" % experiment_name )
+ if os.path.exists( created_treat_pileup_file ):
+ shutil.move (created_treat_pileup_file, output_treat_pileup )
+ created_lambda_bedgraph_file = os.path.join (tmp_dir, "%s_control_lambda.bdg" % experiment_name )
+ if os.path.exists( created_lambda_bedgraph_file ):
+ shutil.move (created_lambda_bedgraph_file, output_lambda_bedgraph )
+
+ #move all remaining files to extra files path of html file output to allow user download
+ out_html = open( output_extra_html, 'wb' )
+ out_html.write( '
Additional output created by MACS (%s)Additional Files:
\n' % experiment_name )
+ os.mkdir( output_extra_path )
+ for filename in sorted( os.listdir( tmp_dir ) ):
+ shutil.move( os.path.join( tmp_dir, filename ), os.path.join( output_extra_path, filename ) )
+ out_html.write( '- %s
\n' % ( filename, filename ) )
+ #out_html.write( '- %speakxls %s SomethingDifferent tmp_dir %s path %s exp_name %s
\n' % ( created_peak_xls_file, filename, filename, tmp_dir, output_extra_path, experiment_name ) )
+ out_html.write( '
\n' )
+ out_html.write( 'Messages from MACS:
\n%s
\n' % open( stderr_name, 'rb' ).read() )
+ out_html.write( '\n' )
+ out_html.close()
+
+ #=================================================================================
+ #move files generated by bdgcmp command
+ if (options['command'] == "bdgcmp"):
+ created_bdgcmp_file = os.path.join (tmp_dir, "bdgcmp_out.bdg" )
+ if os.path.exists( created_bdgcmp_file ):
+ shutil.move (created_bdgcmp_file, output_bdgcmp )
+
+ #=================================================================================
+ #cleanup
+ #=================================================================================
+ os.unlink( stderr_name )
+ os.rmdir( tmp_dir )
+
+if __name__ == "__main__": main()
diff -r 000000000000 -r fdad0c8c0957 macs21_wrapper.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macs21_wrapper.xml Wed Jan 21 11:07:37 2015 -0500
@@ -0,0 +1,387 @@
+
+
+ python
+ numpy
+ macs2
+
+ Model-based Analysis of ChIP-Seq [golem]
+ macs21_wrapper.py $options_file $outputs_file
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ major_command['major_command_selector'] == 'callpeak'
+
+
+ major_command['major_command_selector'] == 'callpeak'
+
+
+ major_command['major_command_selector'] == 'callpeak'
+ major_command['xls_to_interval'] is False
+
+
+ major_command['major_command_selector'] == 'callpeak'
+ major_command['broad_options']['broad_regions'] == ''
+
+
+ major_command['major_command_selector'] == 'callpeak'
+ major_command['broad_options']['broad_regions'] == 'broad'
+
+
+ major_command['major_command_selector'] == 'callpeak'
+ major_command['broad_options']['broad_regions'] == 'broad'
+
+
+ major_command['xls_to_interval'] is True
+ major_command['major_command_selector'] == 'callpeak'
+
+
+ major_command['bdg_options']['bdg'] is True
+ major_command['major_command_selector'] == 'callpeak'
+
+
+ major_command['bdg_options']['bdg'] is True
+ major_command['major_command_selector'] == 'callpeak'
+
+
+
+ major_command['major_command_selector'] == 'bdgcmp'
+
+
+
+ <%
+import simplejson
+%>
+##=======================================================================================
+#set $__outputs = { 'command':str( $major_command.major_command_selector ) }
+#if str( $major_command.major_command_selector ) == 'callpeak':
+ #set $__outputs['output_summits_bed_file'] = str( $output_summits_bed_file )
+ #set $__outputs['output_extra_file'] = str( $output_extra_files )
+ #set $__outputs['output_extra_file_path'] = str( $output_extra_files.files_path )
+ #set $__outputs['output_peaks_file'] = str( $output_peaks_file )
+ #set $__outputs['output_narrowpeaks_file'] = str( $output_narrowpeaks_file )
+ #set $__outputs['output_broadpeaks_file'] = str( $output_broadpeaks_file )
+ #set $__outputs['output_gappedpeaks_file'] = str( $output_gappedpeaks_file )
+ #set $__outputs['output_xls_to_interval_peaks_file'] = str( $output_xls_to_interval_peaks_file )
+ #set $__outputs['output_treat_pileup_file'] = str( $output_treat_pileup_file )
+ #set $__outputs['output_lambda_bedgraph_file'] = str( $output_lambda_bedgraph_file )
+#end if
+##=======================================================================================
+#if str( $major_command.major_command_selector ) == 'bdgcmp':
+ #set $__outputs['output_bdgcmp_file'] = str( $output_bdgcmp_file )
+#end if
+
+${ simplejson.dumps( __outputs ) }
+
+ <%
+import simplejson
+%>
+##=======================================================================================
+#set $__options = { 'experiment_name':str( $experiment_name ) }
+##treatment/tag input files and format
+#set $__options['input_chipseq'] = [ str( $major_command.input_chipseq_file1 ) ]
+#set $__options['format'] = $major_command.input_chipseq_file1.extension.upper()
+
+##control/input files
+#set $__options['input_control'] = []
+#if str( $major_command.input_control_file1 ) != 'None':
+ #set $_hole = __options['input_control'].append( str( $major_command.input_control_file1 ) )
+#end if
+
+#if str( $major_command.major_command_selector ) == 'callpeak':
+ #set $__options['command'] = str( "callpeak" )
+ #set $__options['bw'] = str( $major_command.bw )
+ #set $__options['xls_to_interval'] = str( $major_command.xls_to_interval )
+
+ ##bdg options
+ #if $major_command.bdg_options.bdg == True:
+ #set $__options['bdg'] = str( "-B" )
+ #set $__options['spmr'] = str( $major_command.bdg_options.spmr )
+ #else:
+ #set $__options['bdg'] = str( "" )
+ #set $__options['spmr'] = str( "" )
+ #end if
+
+ ##broad_options
+ #if str( $major_command.broad_options.broad_regions ) == 'broad':
+ #set $__options['broad'] = str( $major_command.broad_options.broad_regions )
+ #set $__options['broad_cutoff'] = str( $major_command.broad_options.broad_cutoff )
+ #else:
+ #set $__options['broad'] = str( "" )
+ #set $__options['broad_cutoff'] = str( "" )
+ #end if
+
+ ##genome sizes
+ #if str( $major_command.genome_size.gsize ) == '':
+ #set $__options['gsize'] = int( $major_command.genome_size.user_defined_gsize )
+ #else:
+ #set $__options['gsize'] = str( $major_command.genome_size.gsize )
+ #end if
+
+ ##advanced options
+ #if str( $major_command.advanced_options.advanced_options_selector ) == 'on':
+ #set $__options['mfoldlo'] = int( $major_command.advanced_options.mfoldlo )
+ #set $__options['mfoldhi'] = int( $major_command.advanced_options.mfoldhi )
+ #set $__options['nolambda'] = str( $major_command.advanced_options.nolambda )
+ #set $__options['call_summits'] = str( $major_command.advanced_options.call_summits )
+ #if str( $major_command.advanced_options.keep_duplicates.keep_dup ) == '':
+ #set $__options['keep_dup'] = int( $major_command.advanced_options.keep_duplicates.maximum_tags )
+ #else:
+ #set $__options['keep_dup'] = str( $major_command.advanced_options.keep_duplicates.keep_dup )
+ #end if
+ #else:
+ #set $__options['mfoldlo'] = int( "5" )
+ #set $__options['mfoldhi'] = int( "50" )
+ #set $__options['nolambda'] = str( "" )
+ #set $__options['call_summits'] = str( "" )
+ #set $__options['keep_dup'] = int( "1" )
+ #end if
+
+ ##enable xls file options
+ ##if str( $major_command.xls_to_interval ) == 'create':
+ ##set $__options['xls_to_interval'] = { 'peaks_file': str( $output_xls_to_interval_peaks_file ), 'negative_peaks_file': str( $output_xls_to_interval_negative_peaks_file ) }
+ ##end if
+
+ ##pq value select options
+ #if str( $major_command.pq_options.pq_options_selector ) == 'qvalue':
+ #set $__options['qvalue'] = str( $major_command.pq_options.qvalue )
+ #else:
+ #set $__options['pvalue'] = str( $major_command.pq_options.pvalue )
+ #end if
+
+ ##model options
+ #if str( $major_command.nomodel_type.nomodel_type_selector ) == 'nomodel':
+ #set $__options['nomodel'] = str( $major_command.nomodel_type.extsize )
+ #end if
+#end if
+##=======================================================================================
+#if str( $major_command.major_command_selector ) == 'bdgcmp':
+ #set $__options['command'] = str( "bdgcmp" )
+ #set $__options['pseudocount'] = float( str( $major_command.pseudocount ) )
+ #set $__options['m'] = str( $major_command.bdgcmp_options.bdgcmp_options_selector )
+#end if
+##=======================================================================================
+
+${ simplejson.dumps( __options ) }
+
+
+
+
+
+
+
+.. class:: warningmark
+
+**This is a modified version of the standard Galaxy toolshed "MACS2" tool,
+which has been customised for users at the University of Manchester to work
+with MACS 2.1.0.**
+
+It is based on the 16:14f378e35191 revision of the tool at
+
+ * http://toolshed.g2.bx.psu.edu/view/modencode-dcc/macs2
+
+------
+
+**What it does**
+
+With the improvement of sequencing techniques, chromatin immunoprecipitation
+followed by high throughput sequencing (ChIP-Seq) is getting popular to study
+genome-wide protein-DNA interactions. To address the lack of powerful ChIP-Seq
+analysis method, we present a novel algorithm, named Model-based Analysis of
+ChIP-Seq (MACS), for identifying transcript factor binding sites. MACS captures
+the influence of genome complexity to evaluate the significance of enriched
+ChIP regions, and MACS improves the spatial resolution of binding sites through
+combining the information of both sequencing tag position and orientation. MACS
+can be easily used for ChIP-Seq data alone, or with control sample with the
+increase of specificity.
+
+View the original MACS2 documentation:
+https://github.com/taoliu/MACS/blob/master/README.rst
+
+------
+
+**Usage**
+
+**Peak Calling**: Main MACS2 Function to Call peaks from alignment results.
+
+**Compare .bdg files**: Deduct noise by comparing two signal tracks in bedGraph.
+
+
+------
+
+**Citation**
+
+For the underlying tool, please cite Zhang Y, Liu T, Meyer CA, Eeckhoute J, Johnson DS, Bernstein BE, Nusbaum C, Myers RM, Brown M, Li W, Liu XS. Model-based analysis of ChIP-Seq (MACS). Genome Biol. 2008;9(9):R137.
+
+Integration of MACS2 with Galaxy performed by Ziru Zhou ( ziruzhou@gmail.com ). Please send your comments/questions to modENCODE DCC at help@modencode.org.
+
+
diff -r 000000000000 -r fdad0c8c0957 tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Wed Jan 21 11:07:37 2015 -0500
@@ -0,0 +1,34 @@
+
+
+
+
+
+
+
+
+
+
+
+ https://pypi.python.org/packages/source/M/MACS2/MACS2-2.1.0.20140616.tar.gz
+
+
+
+
+
+
+
+
+ $INSTALL_DIR/lib/python
+
+ export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python &&
+ python setup.py install --install-lib $INSTALL_DIR/lib/python --install-scripts $INSTALL_DIR/bin
+
+
+ $INSTALL_DIR/lib/python
+ $INSTALL_DIR/bin
+
+
+
+ Macs2.1 depends on having python2.7 and numpy 1.8 installed on all nodes of the work cluster
+
+