diff macs2_wrapper.py @ 1:c05f607d116c draft default tip

Replace simplejson with json. Add option to call broad peaks.

--- a/macs2_wrapper.py	Thu Oct 17 12:47:49 2013 -0400
+++ b/macs2_wrapper.py	Tue May 20 12:10:38 2014 -0400
@@ -1,12 +1,9 @@
-#purpose: macs2 python wrapper
-#author: Ziru Zhou
-#date: November, 2012
+# macs2 python wrapper
+# based on http://toolshed.g2.bx.psu.edu/view/modencode-dcc/macs2
 
 import sys, subprocess, tempfile, shutil, glob, os, os.path, gzip
 from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "simplejson" )
-import simplejson
+import json
 
 CHUNK_SIZE = 1024
 
@@ -38,12 +35,12 @@
         #keep all existing comment lines
         if line.startswith( '#' ):
             out.write( line )
-	#added for macs2 since there is an extra newline 
+    #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
+            print line
             wrote_header = True
         else:
             fields = line.split( '\t' )
@@ -57,8 +54,8 @@
 #==========================================================================================
 def main():
     #take in options file and output file names
-    options = simplejson.load( open( sys.argv[1] ) )
-    outputs = simplejson.load( open( sys.argv[2] ) )
+    options = json.load( open( sys.argv[1] ) )
+    outputs = json.load( open( sys.argv[2] ) )
 
     #=================================================================================
     #parse options and execute macs2
@@ -71,26 +68,29 @@
 
     #=================================================================================
     if (options['command'] == "callpeak"):
-    	output_bed = outputs['output_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_xls_to_interval_peaks_file = outputs['output_xls_to_interval_peaks_file']
-	output_xls_to_interval_negative_peaks_file = outputs['output_xls_to_interval_negative_peaks_file']
+        output_bed = outputs['output_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_xls_to_interval_peaks_file = outputs['output_xls_to_interval_peaks_file']
+    output_xls_to_interval_negative_peaks_file = outputs['output_xls_to_interval_negative_peaks_file']
 
-	if 'pvalue' in options:
-    		cmdline = "%s --format='%s' --name='%s' --gsize='%s' --bw='%s' --pvalue='%s' --mfold %s %s %s %s" % ( cmdline, options['format'], experiment_name, options['gsize'], options['bw'], options['pvalue'], options['mfoldlo'], options['mfoldhi'], options['nolambda'], options['bdg'] )
-	elif 'qvalue' in options:
-    		cmdline = "%s --format='%s' --name='%s' --gsize='%s' --bw='%s' --qvalue='%s' --mfold %s %s %s %s" % ( cmdline, options['format'], experiment_name, options['gsize'], options['bw'], options['qvalue'], options['mfoldlo'], options['mfoldhi'], options['nolambda'], options['bdg'] )
-		
-	if 'nomodel' in options:
-        	cmdline = "%s --nomodel --shiftsize='%s'" % ( cmdline, options['nomodel'] )
+    if 'pvalue' in options:
+        cmdline = "%s --format='%s' --name='%s' --gsize='%s' --bw='%s' --pvalue='%s' --mfold %s %s %s %s" % ( cmdline, options['format'], experiment_name, options['gsize'], options['bw'], options['pvalue'], options['mfoldlo'], options['mfoldhi'], options['nolambda'], options['bdg'] )
+    elif 'qvalue' in options:
+        cmdline = "%s --format='%s' --name='%s' --gsize='%s' --bw='%s' --qvalue='%s' --mfold %s %s %s %s" % ( cmdline, options['format'], experiment_name, options['gsize'], options['bw'], options['qvalue'], options['mfoldlo'], options['mfoldhi'], options['nolambda'], options['bdg'] )
+
+    if 'broad_cutoff' in options:
+        cmdline += " --broad --broad-cutoff=%s" % (options['broad_cutoff'])
+
+    if 'nomodel' in options:
+        cmdline = "%s --nomodel --shiftsize='%s'" % ( cmdline, options['nomodel'] )
     #=================================================================================
     if (options['command'] == "bdgcmp"):
-	output_bdgcmp = outputs['output_bdgcmp_file']
+        output_bdgcmp = outputs['output_bdgcmp_file']
 
-	cmdline = "%s -m %s -p %s -o bdgcmp_out.bdg" % ( cmdline, options['m'], options['pseudocount'] )
+        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
@@ -115,59 +115,59 @@
     #=================================================================================
     #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()
+        #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_peaks.bed" % experiment_name )
-    	if os.path.exists( created_bed_name ):
-        	shutil.move( created_bed_name, output_bed )
+        #move bed out to proper output file
+        created_bed_name =  os.path.join( tmp_dir, "%s_peaks.bed" % experiment_name )
+        if os.path.exists( created_bed_name ):
+            shutil.move( created_bed_name, output_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 )   
+        #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.encodePeak" % experiment_name )
-    	if os.path.exists( created_narrowpeak_file ):
-		shutil.move (created_narrowpeak_file, output_narrowpeaks )
+        #peaks.encodepeaks (narrowpeaks) file
+        created_narrowpeak_file = os.path.join (tmp_dir, "%s_peaks.encodePeak" % experiment_name )
+        if os.path.exists( created_narrowpeak_file ):
+            shutil.move (created_narrowpeak_file, output_narrowpeaks )
 
- 	#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' )
-        	create_peak_xls_file = os.path.join( tmp_dir, '%s_negative_peaks.xls' % experiment_name )
-        	if os.path.exists( create_peak_xls_file ):
-			print "negative file exists"
-            		xls_to_interval( create_peak_xls_file, output_xls_to_interval_negative_peaks_file, header = 'negative peaks file' )
+    #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' )
+            create_peak_xls_file = os.path.join( tmp_dir, '%s_negative_peaks.xls' % experiment_name )
+            if os.path.exists( create_peak_xls_file ):
+                print "negative file exists"
+                xls_to_interval( create_peak_xls_file, output_xls_to_interval_negative_peaks_file, header = 'negative peaks file' )
 
-    	#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( '<html><head><title>Additional output created by MACS (%s)</title></head><body><h3>Additional Files:</h3><p><ul>\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( '<li><a href="%s">%s</a></li>\n' % ( filename, filename ) )
-		#out_html.write( '<li><a href="%s">%s</a>peakxls %s SomethingDifferent tmp_dir %s path %s exp_name %s</li>\n' % ( created_peak_xls_file, filename, filename, tmp_dir, output_extra_path, experiment_name ) )
-    	out_html.write( '</ul></p>\n' )
-    	out_html.write( '<h3>Messages from MACS:</h3>\n<p><pre>%s</pre></p>\n' % open( stderr_name, 'rb' ).read() )
-    	out_html.write( '</body></html>\n' )
-    	out_html.close()
+        #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( '<html><head><title>Additional output created by MACS (%s)</title></head><body><h3>Additional Files:</h3><p><ul>\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( '<li><a href="%s">%s</a></li>\n' % ( filename, filename ) )
+            #out_html.write( '<li><a href="%s">%s</a>peakxls %s SomethingDifferent tmp_dir %s path %s exp_name %s</li>\n' % ( created_peak_xls_file, filename, filename, tmp_dir, output_extra_path, experiment_name ) )
+        out_html.write( '</ul></p>\n' )
+        out_html.write( '<h3>Messages from MACS:</h3>\n<p><pre>%s</pre></p>\n' % open( stderr_name, 'rb' ).read() )
+        out_html.write( '</body></html>\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 )
-     
+        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
     #=================================================================================