protk 1.2.1 → 1.2.2

data/bin/mascot_to_pepxml.rb

@@ -15,10 +15,36 @@ require 'protk/mascot_util'
 #
 genv=Constants.new
 
-tool=SearchTool.new({:database=>true,:explicit_output=>true,:over_write=>true})
+tool=SearchTool.new([:database,:explicit_output,:over_write,:enzyme])
 tool.option_parser.banner = "Convert mascot dat files to pep.xml files.\n\nUsage: mascot_to_pepxml.rb [options] file1.dat file2.dat ... "
+
+tool.options.enzyme="trypsin"
+
+tool.options.shortid=false
+tool.option_parser.on( '--shortid', 'Use short protein id as per Mascot result (default uses full protein ids in fasta file)' ) do  
+    tool.options.shortid=true
+end
+
 tool.option_parser.parse!
 
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
+
+current_db=""
+
+case 
+when Pathname.new(tool.database).exist? # It's an explicitly named db
+  current_db=Pathname.new(tool.database).realpath.to_s
+else
+  current_db=tool.current_database :fasta
+end
+
+
 
 ARGV.each do |file_name| 
   name=file_name.chomp
@@ -28,12 +54,15 @@ ARGV.each do |file_name|
   if ( tool.explicit_output==nil )
     new_basename="#{this_dir}/#{MascotUtil.input_basename(name)}_mascot2xml"      
     cmd="cp #{name} #{new_basename}.dat"
-    cmd << "; #{genv.mascot2xml} #{new_basename}.dat -D#{tool.current_database :fasta}"
+    cmd << "; #{genv.mascot2xml} #{new_basename}.dat -D#{current_db} -E#{tool.enzyme}"
     
+    cmd << " -shortid" if tool.shortid
+
   else  #Mascot2XML doesn't support explicitly named output files so we move the file to an appropriate output filename after finishing
     new_basename="#{this_dir}/#{MascotUtil.input_basename(name)}_mascot2xml"
     cmd="cp #{name} #{new_basename}.dat"
-    cmd << "; #{genv.mascot2xml} #{new_basename}.dat -D#{tool.current_database :fasta}"
+    cmd << "; #{genv.mascot2xml} #{new_basename}.dat -D#{current_db} -E#{tool.enzyme}"
+    cmd << " -shortid" if tool.shortid
     cmd << "; mv #{new_basename}.pep.xml #{tool.explicit_output}; rm #{new_basename}.dat"
     repair_script="#{File.dirname(__FILE__)}/repair_run_summary.rb"     
     cmd << "; #{repair_script} #{tool.explicit_output}"

data/bin/msgfplus_search.rb

@@ -17,17 +17,32 @@ input_stager = nil
 
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
-search_tool=SearchTool.new({:msms_search=>true,:background=>false,:glyco=>false,:database=>true,:explicit_output=>true,:over_write=>true,:msms_search_detailed_options=>true})
+search_tool=SearchTool.new([:database,:explicit_output,:over_write,:enzyme,
+  :modifications,:instrument,:mass_tolerance_units,:mass_tolerance,:missed_cleavages])
+
 search_tool.option_parser.banner = "Run an MSGFPlus msms search on a set of msms spectrum input files.\n\nUsage: msgfplus_search.rb [options] file1.mzML file2.mzML ..."
 search_tool.options.output_suffix="_msgfplus"
 
+search_tool.options.enzyme=1
+search_tool.options.instrument=0
+
+search_tool.options.no_pepxml=false
+search_tool.option_parser.on(  '--no-pepxml', 'Dont convert results to pepxml. Keep native mzidentml format' ) do
+  search_tool.options.no_pepxml=true
+end
+
+search_tool.options.isotope_error_range="0,1"
+search_tool.option_parser.on(  '--isotope-error-range range', 'Takes into account of the error introduced by chooosing a non-monoisotopic peak for fragmentation.(Default 0,1)' ) do |range|
+  search_tool.options.isotope_error_range=range
+end
+
 search_tool.options.fragment_method=0
 search_tool.option_parser.on(  '--fragment-method method', 'Fragment method 0: As written in the spectrum or CID if no info (Default), 1: CID, 2: ETD, 3: HCD, 4: Merge spectra from the same precursor' ) do |method|
   search_tool.options.fragment_method=method
 end
 
 search_tool.options.protocol=0
-search_tool.option_parser.on(  '--protocol p', '0: NoProtocol (Default), 1: Phosphorylation' ) do |p|
+search_tool.option_parser.on(  '--protocol p', '0: NoProtocol (Default), 1: Phosphorylation, 2: iTRAQ, 3: iTRAQPhospho' ) do |p|
   search_tool.options.protocol=p
 end
 
@@ -61,12 +76,23 @@ search_tool.option_parser.on(  '--add-features', 'output additional features' )
   search_tool.options.add_features=true
 end
 
+search_tool.options.num_threads=nil
+search_tool.option_parser.on('--threads NumThreads','Number of processing threads to use') do |nt|
+  search_tool.options.num_threads=nt
+end
+
 search_tool.options.java_mem="3500M"
 search_tool.option_parser.on('--java-mem mem','Java memory limit when running the search (Default 3.5Gb)') do |mem|
   search_tool.options.java_mem=mem
 end
   
-search_tool.option_parser.parse!
+exit unless search_tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts search_tool.option_parser 
+    exit
+end
 
 # Environment with global constants
 #
@@ -149,17 +175,33 @@ ARGV.each do |filename|
     # Instrument type
     cmd << " -inst #{search_tool.instrument}"
     
-#    cmd << " -m 4"
+    cmd << " -m #{search_tool.fragment_method}"
 
     cmd << " -addFeatures 1"
 
+    cmd << " -protocol #{search_tool.protocol}"
+
+    cmd << " -minLength #{search_tool.min_pep_length}"
+
+    cmd << " -maxLength #{search_tool.max_pep_length}"
+
+    cmd << " -minCharge #{search_tool.min_pep_charge}"
+
+    cmd << " -maxCharge #{search_tool.max_pep_charge}"
+
+    cmd << " -ti #{search_tool.isotope_error_range}"
+
+    cmd << " -n #{search_tool.num_reported_matches}"
+
     # Enzyme
     #
-  #    if ( search_tool.enzyme!="Trypsin")
-  #      cmd << " -e #{search_tool.enzyme}"
-  #    end
+    cmd << " -e #{search_tool.enzyme}"
+
+    # Num Threads
+    #
+    cmd << " -thread #{search_tool.num_threads}" if search_tool.num_threads
 
-  mods_file_content = ""
+    mods_file_content = ""
 
     # Variable Modifications
     #
@@ -188,10 +230,14 @@ ARGV.each do |filename|
     end
     
     # As a final part of the command we convert to pepxml
-    cmd << "; #{genv.idconvert} #{mzid_output_path} --pepXML -o #{Pathname.new(mzid_output_path).dirname}"
-
-    #Then copy the pepxml to the final output path
-    cmd << "; cp #{mzid_output_path.chomp('.mzid')}.pepXML #{output_path}"
+    if search_tool.no_pepxml
+      cmd << "; #{genv.idconvert} #{mzid_output_path} --pepXML -o #{Pathname.new(mzid_output_path).dirname}" 
+      #Then copy the pepxml to the final output path
+      cmd << "; cp #{mzid_output_path.chomp('.mzid')}.pepXML #{output_path}"
+    elsif search_tool.explicit_output
+      cmd << "; cp #{mzid_output_path} #{output_path}"
+    end
+      
 
     # Up to here we've formulated the command. The rest is cleanup
     p "Running:#{cmd}"

data/bin/omssa_search.rb

@@ -16,7 +16,12 @@ for_galaxy = GalaxyUtil.for_galaxy?
 
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
-search_tool=SearchTool.new({:msms_search=>true,:background=>false,:glyco=>true,:database=>true,:explicit_output=>true,:over_write=>true,:msms_search_detailed_options=>true})
+search_tool=SearchTool.new([:database,:explicit_output,:over_write,:enzyme,
+  :modifications,:instrument,:mass_tolerance_units,:mass_tolerance,:missed_cleavages,
+  :precursor_search_type,:respect_precursor_charges,:num_peaks_for_multi_isotope_search,:searched_ions
+  ])
+
+
 search_tool.option_parser.banner = "Run an OMSSA msms search on a set of mgf input files.\n\nUsage: omssa_search.rb [options] file1.mgf file2.mgf ..."
 search_tool.options.output_suffix="_omssa"
 
@@ -54,7 +59,13 @@ search_tool.option_parser.on( '--nthreads num', 'Number of search threads to use
   search_tool.options.nthreads=num
 end
 
-search_tool.option_parser.parse!
+exit unless search_tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts search_tool.option_parser 
+    exit
+end
 
 # Environment with global constants
 #

data/bin/peptide_prophet.rb

@@ -13,7 +13,7 @@ require 'protk/prophet_tool'
 
 # Setup specific command-line options for this tool. Other options are inherited from ProphetTool
 #
-prophet_tool=ProphetTool.new({:glyco=>true,:explicit_output=>true,:maldi=>true})
+prophet_tool=ProphetTool.new([:glyco,:explicit_output,:maldi])
 prophet_tool.option_parser.banner = "Run PeptideProphet on a set of pep.xml input files.\n\nUsage: peptide_prophet.rb [options] file1.pep.xml file2.pep.xml ..."
 prophet_tool.options.output_suffix="_pproph"
 
@@ -92,7 +92,13 @@ prophet_tool.option_parser.on( '--override-database database', 'Manually specify
   prophet_tool.options.override_database = database
 end
 
-prophet_tool.option_parser.parse!
+exit unless prophet_tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts prophet_tool.option_parser 
+    exit
+end
 
 throw "When --output and -F options are set only one file at a time can be run" if  ( ARGV.length> 1 ) && ( prophet_tool.explicit_output!=nil ) && (prophet_tool.one_ata_time!=nil)
 

data/bin/pepxml_to_table.rb

@@ -16,10 +16,16 @@ include LibXML
 
 # Setup specific command-line options for this tool. Other options are inherited from ProphetTool
 #
-tool=Tool.new({:explicit_output=>true})
+tool=Tool.new([:explicit_output])
 tool.option_parser.banner = "Convert a pepXML file to a tab delimited table.\n\nUsage: pepxml_to_table.rb [options] file1.pep.xml"
 
-tool.option_parser.parse!
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
 
 # Obtain a global environment object
 #genv=Constants.new

data/bin/protein_prophet.rb

@@ -26,7 +26,7 @@ end
 
 # Setup specific command-line options for this tool. Other options are inherited from ProphetTool
 #
-prophet_tool=ProphetTool.new({:glyco=>true,:explicit_output=>true})
+prophet_tool=ProphetTool.new([:glyco,:explicit_output])
 prophet_tool.option_parser.banner = "Run ProteinProphet on a set of pep.xml input files.\n\nUsage: protein_prophet.rb [options] file1.pep.xml file2.pep.xml ..."
 prophet_tool.options.output_suffix="_protproph"
 
@@ -90,7 +90,13 @@ prophet_tool.option_parser.on( '--minindep mp',"Minimum percentage of independen
   prophet_tool.options.minindep = mp
 end
 
-prophet_tool.option_parser.parse!
+exit unless prophet_tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts prophet_tool.option_parser 
+    exit
+end
 
 
 # Obtain a global environment object

data/bin/protxml_to_table.rb

@@ -0,0 +1,82 @@
+#!/usr/bin/env ruby
+#
+# This file is part of protk
+# Created by Ira Cooke 18/1/2011
+#
+# Convert a pepXML file to a tab delimited table
+#
+#
+
+require 'libxml'
+require 'protk/constants'
+require 'protk/command_runner'
+require 'protk/tool'
+
+include LibXML
+
+# Setup specific command-line options for this tool. Other options are inherited from ProphetTool
+#
+tool=Tool.new([:explicit_output])
+tool.option_parser.banner = "Convert a protXML file to a tab delimited table.\n\nUsage: protxml_to_table.rb [options] file1.protXML"
+
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
+
+input_file=ARGV[0]
+
+output_file = tool.explicit_output!=nil ? tool.explicit_output : nil
+
+output_fh = output_file!=nil ? File.new("#{output_file}",'w') : $stdout
+
+
+XML::Error.set_handler(&XML::Error::QUIET_HANDLER)
+
+protxml_parser=XML::Parser.file("#{input_file}")
+
+protxml_ns_prefix="xmlns:"
+protxml_ns="xmlns:http://regis-web.systemsbiology.net/protXML"
+protxml_doc=protxml_parser.parse
+if not protxml_doc.root.namespaces.default
+  protxml_ns_prefix=""
+  protxml_ns=nil
+end
+
+
+column_headers=[
+	"group_number","group_probability","protein_name",
+	"protein_probability","coverage","peptides",
+	"num_peptides","confidence"
+]
+
+output_fh.write "#{column_headers.join("\t")}\n"
+
+
+protein_groups=protxml_doc.find("//#{protxml_ns_prefix}protein_group", protxml_ns)
+
+protein_groups.each do |protein_group| 
+
+	proteins=protein_group.find("./#{protxml_ns_prefix}protein", protxml_ns)
+
+	proteins.each do |protein|  
+		column_values=[]
+
+		column_values << protein_group.attributes['group_number']
+		column_values << protein_group.attributes['probability']
+
+		column_values << protein.attributes['protein_name']
+		column_values << protein.attributes['probability']
+		column_values << protein.attributes['percent_coverage']
+		column_values << protein.attributes['unique_stripped_peptides']
+		column_values << protein.attributes['total_number_peptides']
+		column_values << protein.attributes['confidence']
+		output_fh.write(column_values.join("\t"))
+		output_fh.write("\n")
+
+	end
+end
+

data/bin/repair_run_summary.rb

@@ -40,7 +40,13 @@ tool.option_parser.on('--omssa-itol fitol','Add a fragment ion tolerance paramet
   tool.options.omssa_ion_tolerance=fitol
 end
 
-tool.option_parser.parse!
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
 
 pepxml_file=ARGV[0]
 

data/bin/sixframe.rb

@@ -10,10 +10,34 @@ require 'protk/constants'
 require 'protk/tool'
 require 'bio'
 
-tool=Tool.new(:explicit_output=>true)
+def check_coords(naseq,aaseq,frame,pstart,pend)
+  orf_from_coords=""
+  if ( frame<=3)
+    orf_from_coords=naseq[pstart-1..pend-1].translate(1)
+  else
+    orf_from_coords=naseq[pstart-1..pend-1].reverse_complement.translate(1)
+    # current coords give
+    # naseq.reverse_complement[pstart-1..pend-1].translate(1)
+    # naseq[350368-pend..(350367-pstart+1)].reverse_complement.translate(1)
+#    orf_from_coords=naseq[naseq.length-pend..naseq.length-pstart].reverse_complement.translate(1)
+  end
+  if ( orf_from_coords!=aaseq)
+    require 'debugger'; debugger
+  end
+#  p "#{aaseq} #{frame}"
+end
+
+
+tool=Tool.new([:explicit_output])
 tool.option_parser.banner = "Create a sixframe translation of a genome.\n\nUsage: sixframe.rb [options] genome.fasta"
 
-tool.option_parser.parse!
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
 
 inname=ARGV.shift
 
@@ -26,7 +50,11 @@ end
 file = Bio::FastaFormat.open(inname)
 
 file.each do |entry|
+
+  puts entry.entry_id
+
   length = entry.naseq.length
+
   (1...7).each do |frame|
     translated_seq= entry.naseq.translate(frame)
     orfs=translated_seq.split("*")
@@ -37,15 +65,30 @@ file.each do |entry|
     orfs.each do |orf|
       oi+=1
       if ( orf.length > 20 )
+
         position_start = position
         position_end = position_start + orf.length*3 -1
 
+        if ( frame>3) #On reverse strand. Coordinates need translating to forward strand
+          forward_position_start=length-position_end+1
+          forward_position_end = length-position_start+1
+          position_start=forward_position_start
+          position_end=forward_position_end
+        end
+
+
+
+
         # Create accession compliant with NCBI naming standard
         # See http://www.ncbi.nlm.nih.gov/books/NBK7183/?rendertype=table&id=ch_demo.T5
         ncbi_scaffold_id = entry.entry_id.gsub('|','_').gsub(' ','_')
         ncbi_accession = "lcl|#{ncbi_scaffold_id}_frame_#{frame}_orf_#{oi}"
 
+#        check_coords(entry.naseq,orf,frame,position_start,position_end)
+
         # Output in fasta format
+        # start and end positions are always relative to the forward strand
+
         outfile.write(">#{ncbi_accession} #{position_start}|#{position_end}\n#{orf}\n")
 
       end
@@ -54,3 +97,6 @@ file.each do |entry|
 
   end
 end
+
+
+