protk 1.2.6.pre5 → 1.3.0.pre1

data/bin/blastxml_to_table.rb

@@ -1,119 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-#
-# 
-
-require 'protk/constants'
-require 'protk/tool'
-require 'bio'
-require 'protk/fastadb'
-require 'bio-blastxmlparser'
-
-tool=Tool.new([:explicit_output])
-tool.option_parser.banner = "Dump BLAST xml to tabular format.\n\nUsage: blastxml_to_table.rb blast.xml"
-
-tool.options.database=nil
-tool.option_parser.on( '-d filename','--database filename', 'Database used for BLAST search. If provided, hit sequences will be looked up in this database' ) do |file| 
-  tool.options.database=file
-end
-
-tool.options.gene2go=nil
-tool.option_parser.on('--gene2go pathtogene2go','Path to gene2go database. If provided GO terms will be looked up') do |gene2go|
-	tool.options.gene2go=gene2go
-end
-
-tool.options.gitogeneid=nil
-tool.option_parser.on('--gitogeneid gitogeneid.db','Path to GDBM formatted gi to geneid mapping database. If provided gene ids will be looked up') do |gitogeneid|
-	tool.options.gitogeneid=gitogeneid
-end
-
-exit unless tool.check_options 
-
-#require 'debugger';debugger
-
-exit unless ARGV.length == 1
-input_file=ARGV[0]
-
-out_file=$stdout
-if ( tool.explicit_output != nil)
-  out_file=File.open(tool.explicit_output, "w")
-end
-
-$fastadb = nil
-if tool.database
-	$fastadb=FastaDB.new(tool.database)
-end
-
-$gitogeneid = nil
-if (tool.gitogeneid!=nil) && (File.exist? tool.gitogeneid)
-	require 'gdbm'
-	$gitogeneid = GDBM.new(tool.gitogeneid,flags=GDBM::READER)
-end
-
-
-$gene2go = nil
-if (tool.gene2go!=nil) && (File.exist? tool.gene2go)
-	require 'gdbm'
-	$gene2go = GDBM.new(tool.gene2go,flags=GDBM::READER)
-end
-
-def gi_from_hit_id(hit_id)
-	gi_scan=hit_id.scan(/gi\|(\d+)/)
-	gi_scan.join("")
-end
-
-def generate_line(hsp,hit,query,hit_seq=nil)
-
-	line="#{query.query_id}\t#{query.query_def}\t#{hit.hit_id}\t#{hit.hit_num}\t#{hit.hit_def}\t#{hit.accession}\t#{hsp.hsp_num}\t#{hsp.bit_score}\t#{hsp.evalue}\t#{hsp.qseq}\t#{hsp.hseq}"
-	if hit_seq
-		line << "\t#{hit_seq}"
-	end
-	geneid=""
-	goterm=""
-	if $gitogeneid
-		geneid=$gitogeneid[gi_from_hit_id(hit.hit_id)]
-		goterm=$gene2go[geneid] if geneid!=nil	&& $gene2go
-	end
-
-
-	# throw "No geneid" if geneid==nil
-	line << "\t#{geneid}\t#{goterm}"
-#	require 'debugger';debugger
-#	puts gi_from_hit_id(hit.hit_id)
-#	puts $gene2go[gi_from_hit_id(hit.hit_id)]
-	line<<"\n"
-	line
-end
-
-def fetch_hit_seq(hit)
-	hit_seq=nil
-	if $fastadb
-		hit_seq=$fastadb.fetch(hit.hit_id).first.aaseq
-	end
-	hit_seq
-end
-
-blast = Bio::BlastXMLParser::XmlSplitterIterator.new(input_file).to_enum
-
-blast.each do |query|  
-	query.hits.each do |hit|
-#	hit=query.hits.first
-#	if hit
-		hit_seq=fetch_hit_seq(hit)
-		hit.hsps.each do |hsp|
-			out_line=generate_line(hsp,hit,query,hit_seq)
-
-			out_file.write out_line
-		end
-#	end
-	end
-end
-
-
-$gitogeneid.close if $gitogeneid!=nil
-$gene2go.close if $gene2go!=nil
-
-#require 'debugger';debugger
-
-#puts "Hi"

data/bin/correct_omssa_retention_times.rb

@@ -1,27 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Created by Ira Cooke 14/12/2010
-#
-# Corrects retention times in omssa output
-#
-
-$VERBOSE=nil
-
-require 'protk/constants'
-require 'protk/command_runner'
-require 'protk/tool'
-require 'protk/omssa_util'
-
-# Environment with global constants
-#
-genv=Constants.new
-
-tool=Tool.new([:over_write])
-tool.option_parser.banner = "Correct retention times on a pepxml file produced by omssa using information from an mgf file.\n\nUsage: correct_omssa_retention_times.rb [options] file1.pep.xml file2.mgf"
-tool.option_parser.parse!
-
-
-OMSSAUtil.add_retention_times(ARGV[1],ARGV[0],tool.over_write,true)
-
-

data/bin/feature_finder.rb

@@ -1,95 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Created by Ira Cooke 21/3/2012
-#
-# A wrapper for the OpenMS FeatureFinder tools (FeatureFinderCentroided and FeatureFinderIsotopeWavelet)
-
-require 'protk/constants'
-require 'protk/command_runner'
-require 'protk/tool'
-require 'protk/openms_defaults'
-require 'libxml'
-require 'tempfile'
-
-include LibXML
-
-tool=Tool.new([:explicit_output, :background,:over_write,:prefix_suffix])
-tool.option_parser.banner = "Find molecular features on a set of input files.\n\nUsage: feature_finder.rb [options] file1.mzML file2.mzML ..."
-
-tool.options.intensity_type = "ref"
-tool.option_parser.on( '--intensity-type type',"method used to calculate intensities (ref,trans,corrected). Default = ref. See OpenMS documentation for details" ) do |type|
-  tool.options.intensity_type = type
-end
-
-tool.options.intensity_threshold = "3"
-tool.option_parser.on( '--intensity-threshold thresh',"discard features below this intensity (Default=3). Set to -1 to retain all detected features" ) do |thresh|
-  tool.options.intensity_threshold = thresh
-end
-
-
-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
-
-def run_ff(genv,tool,cmd,output_path,jobid)
-  if ( !tool.over_write && Pathname.new(output_path).exist? )
-    genv.log("Skipping analysis on existing file #{output_path}",:warn)   
-  else
-    jobscript_path="#{output_path}.pbs.sh"
-    job_params={:jobid=>jobid, :vmem=>"14Gb", :queue => "sixteen"}
-    code=tool.run(cmd,genv,job_params,jobscript_path)
-    throw "Command failed with exit code #{code}" unless code==0
-  end
-end
-
-def generate_ini(tool,out_path)
-  base_ini_file=OpenMSDefaults.new.featurefinderisotopewavelet
-  parser = XML::Parser.file(base_ini_file)
-  doc = parser.parse
-  intensity_threshold_node = doc.find('//ITEM[@name="intensity_threshold"]')[0]
-  intensity_type_node = doc.find('//ITEM[@name="intensity_type"]')[0]
-  intensity_threshold_node['value']=tool.intensity_threshold
-  intensity_type_node['value']=tool.intensity_type
-  doc.save(out_path)
-end
-
-throw "Cannot use explicit output in combination with multiple input files" if ( tool.explicit_output && ARGV.length>1)
-
-input_basename=Pathname.new(ARGV[0]).basename.to_s
-ini_file_name="#{Pathname.new(Tempfile.new(input_basename).path).basename.to_s}_feature_finder.ini"
-ini_file="#{Pathname.new(ini_file_name).dirname.realpath.to_s}/#{ini_file_name}"
-
-generate_ini(tool,ini_file)
-
-ARGV.each do |filen|
-  input_file=filen.chomp
-  throw "Input must be an mzML file" unless input_file=~/\.mzML$/
-
-  input_basename=input_file.gsub(/\.mzML$/,'')  
-  output_dir=Pathname.new(input_basename).dirname.realpath.to_s
-  output_base=Pathname.new(input_basename).basename.to_s
-  output_file = "#{output_dir}/#{tool.output_prefix}#{output_base}#{tool.output_suffix}.featureXML"
-  if ( tool.explicit_output )
-    output_file = "#{output_dir}/#{tool.explicit_output}"
-  end
-
-  if ( tool.over_write || !Pathname.new(output_file).exist? )
-    output_base_filename=Pathname.new(output_file).basename.to_s
-    cmd=""
-    cmd<<"export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:#{genv.openms_root}/lib;
-#{genv.featurefinderisotopewavelet} -in #{Pathname.new(input_file).realpath.to_s} -out #{output_dir}/#{output_base_filename} -ini #{ini_file}"
-  
-    run_ff(genv,tool,cmd,output_file,tool.jobid_from_filename(input_basename))
-  
-  else
-    genv.log("Skipping search on existing file #{output_file}",:warn)    
-  end
-end

data/bin/file_convert.rb

@@ -1,164 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Created by Ira Cooke 14/12/2010
-#
-# Wrapper for msconvert
-#
-
-require 'protk/constants'
-require 'protk/command_runner'
-require 'protk/tool'
-require 'tempfile'
-require 'libxml'
-
-include LibXML
-
-# Regex for cleaning mgf sed -i.bak 's/\(PEPMASS=[0-9]*.[0-9]*\)[ \t]*[0-9]*/\1/g'
-
-# Read the input file and search for an instance of the charge state cvParam inside a precursor tag. Return true if one is found. False otherwise
-#
-def has_charge_information(input_filename)
-  #<precursorList count="1">
-  #        <precursor spectrumRef="controllerType=0 controllerNumber=1 scan=59">
-  #          <isolationWindow>
-  #            <cvParam cvRef="MS" accession="MS:1000827" name="isolation window target m/z" value="939.43" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
-  #            <cvParam cvRef="MS" accession="MS:1000828" name="isolation window lower offset" value="2.0" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
-  #            <cvParam cvRef="MS" accession="MS:1000829" name="isolation window upper offset" value="2.0" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
-  #          </isolationWindow>
-  #          <selectedIonList count="1">
-  #            <selectedIon>
-  #              <cvParam cvRef="MS" accession="MS:1000744" name="selected ion m/z" value="939.432189941406" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
-  #              <cvParam cvRef="MS" accession="MS:1000041" name="charge state" value="2"/>
-  #              <cvParam cvRef="MS" accession="MS:1000042" name="peak intensity" value="1321.692016601563" unitCvRef="MS" unitAccession="MS:1000131" unitName="number of counts"/>
-  #            </selectedIon>
-  #          </selectedIonList>
-  
-  reader=XML::Reader.file(input_filename)  
-  
-  while(reader.read)
-    
-    if ( reader.local_name=="precursor")
-      
-      subdoc=reader.read_inner_xml
-      
-      if ( subdoc =~ /MS:1000041/ )
-        return true
-      end
-      
-    end
-    
-  end
-  
-  return false
-  
-end
-
-
-
-# Setup specific command-line options for this tool. Other options are inherited from Tool
-#
-convert_tool=Tool.new([:explicit_output,:over_write,:maldi])
-convert_tool.option_parser.banner = "Convert files between different formats.\n\nUsage: file_convert.rb [options] input_file output_file"
-
-# Special case (usually tool specific options use capitals). Use lowercase l here to mimick maldi option in the search_tool class
-#
-convert_tool.options.maldi=false
-convert_tool.option_parser.on( '-l', '--maldi', 'Input Files are MALDI Spectra' ) do 
-  convert_tool.options.maldi=true
-end
-
-convert_tool.options.output_format="mgf"
-convert_tool.option_parser.on( '-F', '--format fmt', 'Convert to a specified format' ) do |fmt| 
-  convert_tool.options.output_format=fmt
-end
-
-#convert_tool.options.missing_charge_state="false"
-#convert_tool.option_parser.on( '-C', '--missing-charges', 'No attempt will be made to write charge states. Leads to better looking spectrum names' ) do |fmt| 
-#  convert_tool.options.output_format=fmt
-#end
-#end
-
-
-
-exit unless convert_tool.check_options 
-
-if ( ARGV[0].nil? )
-    puts "You must supply an input file"
-    puts convert_tool.option_parser 
-    exit
-end
-
-
-
-# Environment with global constants
-#
-genv=Constants.new
-
-filename=ARGV[0]
-
-
-input_ext=Pathname.new(filename).extname
-input_relative_filename=Pathname.new(filename).basename.to_s
-
-base_output_dir=Pathname.new(filename).dirname.realpath.to_s #Default output dir is input dir
-
-output_basename=input_relative_filename.gsub(/#{input_ext}$/,"").to_s
-
-if ( convert_tool.explicit_output )
-  output_filepath=Pathname.new(convert_tool.explicit_output)
-  base_output_dir=output_filepath.dirname.to_s
-
-  if ( convert_tool.explicit_output=~/^\//) # It's an absolute path so use absolute path as output dir
-    # Convert base_output_dir to realpath
-    #
-    base_output_dir=Pathname.new(base_output_dir).realpath.to_s
-  end
-
-  output_filename=output_filepath.basename.to_s
-  
-end
-
-# Create a uniquely named directory to hold the output. This is the only way to know the output of msconvert 
-#
-output_dir="#{base_output_dir}/#{Pathname.new(Tempfile.new("file_convert").path).basename.to_s}"
-Dir.mkdir(output_dir)
-
-
-throw "Input format is the same as output format" if ( input_ext==".#{convert_tool.output_format}" )
-  
-genv.log("Converting #{filename} to #{convert_tool.output_format}",:info)
-runner=CommandRunner.new(genv)
-basedir=Pathname.new(filename).dirname.to_s #Where we run the tool
-
-if ( convert_tool.maldi )
-  #For MALDI we know the charge is 1 so set it explicitly. Sometimes it is missing from the data
-  runner.run_local("cd #{basedir}; #{genv.msconvert} #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.1\" --#{convert_tool.output_format} -o #{output_dir}")
-else
-  if ( has_charge_information(filename) )
-    runner.run_local("cd #{basedir}; #{genv.msconvert} #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.<ChargeState>\" --#{convert_tool.output_format} -o #{output_dir}")
-  else
-    # If input file is missing charges the best we can do is just assign charge=1. Search engines can choose to ignore this value anyway.
-    #    
-    runner.run_local("cd #{basedir}; #{genv.msconvert} #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.1\" --#{convert_tool.output_format} -o #{output_dir}")
-  end
-end
-
-# Find out what the output name was
-#
-tmp_output_filename=""
-Dir.foreach(output_dir) { |entry_name| 
-  if ( entry_name=~/^\.$/ || entry_name=~/^\.\.$/ )
-  else
-    tmp_output_filename=entry_name
-  end
-}
-
-# Cleanup after converting
-cmd = "cd #{output_dir};pwd; mv #{tmp_output_filename}  #{base_output_dir}/#{output_filename}; cd ../; pwd;rm -r #{output_dir}"
-
-code =runner.run_local(cmd)
-
-throw "Command failed with exit code #{code}" unless code==0
-
-throw "Failed to create output file #{base_output_dir}/#{output_filename}" unless ( FileTest.exists?("#{base_output_dir}/#{output_filename}") )

data/bin/generate_omssa_loc.rb

@@ -1,42 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of MSLIMS
-# Created by Ira Cooke 12/4/2010
-#
-# Generates files required by the omssa galaxy wrapper
-#
-
-require 'protk/constants'
-# Environment with global constants
-#
-genv=Constants.new
-
-# Set search engine specific parameters on the SearchTool object
-#
-omssa_root="#{genv.omssa_root}/omssacl"
-# Get ommssa to print out a list of its acceptable modifications
-acceptable_mods=%x[#{omssa_root} -ml].split(/\n/).collect do |mod|  
-
-mod_vals=mod.split(":") 
-[mod_vals[0].lstrip.rstrip,mod_vals[1].lstrip.rstrip]
-
-end
-
-# Drop the header
-#
-acceptable_mods.shift
-
-loc_output=File.new("omssa_mods.loc",'w')
-
-loc_output << "#This file lists the names of chemical modifications accepted by OMMSA\n"
-loc_output << "#\n"
-loc_output << "#\n"
-
-acceptable_mods.each { |am| 
-  key = am[1].downcase.gsub(" ","").gsub("\(","\_").gsub("\)","\_").gsub("\:","\_").gsub("\-\>","\_")
-  loc_output << "#{am[1]}\t#{key}_\t#{am[0]}\t#{key}_\n"
-}
-
-loc_output.close
-
-

data/bin/gffmerge.rb

@@ -1,208 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Original python version created by Max Grant
-# Translated to ruby by Ira Cooke 29/1/2013
-#
-# 
-
-require 'protk/constants'
-require 'protk/tool'
-require 'protk/fastadb'
-require 'libxml'
-require 'bio'
-
-include LibXML
-
-tool=Tool.new([:explicit_output])
-tool.option_parser.banner = "Create a gff containing peptide observations.\n\nUsage: gffmerge.rb "
-
-
-tool.options.gff_predicted=nil
-tool.option_parser.on( '-g filename','--gff filename', 'Predicted Data (GFF3 Format)' ) do |file| 
-  tool.options.gff_predicted=file
-end
-
-tool.options.protxml=nil
-tool.option_parser.on( '-p filename','--protxml filename', 'Observed Data (ProtXML Format)' ) do |file| 
-  tool.options.protxml=file
-end
-
-tool.options.sixframe=nil
-tool.option_parser.on( '-t filename','--sixframe filename', 'Sixframe Translations (Fasta Format)' ) do |file| 
-  tool.options.sixframe=file
-end
-
-tool.options.skip_fasta_indexing=false
-tool.option_parser.on('--skip-index','Don\'t index sixframe translations (Index should already exist)') do 
-  tool.options.skip_fasta_indexing=true
-end
-
-tool.options.peptide_probability_threshold=0.95
-tool.option_parser.on('--threshold prob','Peptide Probability Threshold (Default 0.95)') do |thresh|
-  tool.options.peptide_probability_threshold=thresh.to_f
-end
-
-exit unless tool.check_options [:protxml,:sixframe]
-
-gff_out_file="merged.gff"
-if ( tool.explicit_output != nil)
-  gff_out_file=tool.explicit_output
-end
-
-gff_db = Bio::GFF.new()
-if ( tool.gff_predicted !=nil)
-  p "Reading source gff file"
-  gff_db = Bio::GFF::GFF3.new(File.open(tool.gff_predicted))
-  # p gff_db.records[1].attributes
-  # exit
-end
-
-f = open(gff_out_file,'w+')
-gff_db.records.each { |rec| 
-  f.write(rec.to_s)
-}
-
-p "Parsing proteins from protxml"
-protxml_parser=XML::Parser.file(tool.protxml)
-protxml_doc=protxml_parser.parse
-proteins = protxml_doc.find('.//protxml:protein','protxml:http://regis-web.systemsbiology.net/protXML')
-
-
-db_filename = nil
-case
-when Pathname.new(tool.sixframe).exist? # It's an explicitly named db  
-  db_filename = Pathname.new(tool.sixframe).realpath.to_s
-else
-  db_filename=Constants.new.current_database_for_name(tool.sixframe)
-end
-
-db_indexfilename = "#{db_filename}.pin"
-
-if File.exist?(db_indexfilename)
-  p "Using existing indexed translations"
-  orf_lookup = FastaDB.new(db_filename)
-else
-  p "Indexing sixframe translations"
-  orf_lookup = FastaDB.create(db_filename,db_filename,'prot')
-end
-
-p "Aligning peptides and writing GFF data..."
-low_prob = 0
-skipped = 0
-peptide_count = 0
-protein_count = 0
-total_peptides = 0
-for prot in proteins
-  prot_prob = prot['probability']
-  if ( prot_prob.to_f < tool.peptide_probability_threshold )
-    next
-  end
-  indis_proteins = prot.find('protxml:indistinguishable_protein','protxml:http://regis-web.systemsbiology.net/protXML')
-  prot_names = [prot['protein_name']]
-  for protein in indis_proteins
-    prot_names += [protein['protein_name']]
-  end
-
-  peptides = prot.find('protxml:peptide','protxml:http://regis-web.systemsbiology.net/protXML')
-
-  for protein_name in prot_names
-    protein_count += 1
-    prot_qualifiers = {"source" => "OBSERVATION", "score" => prot_prob, "ID" => 'pr' + protein_count.to_s}
-    begin
-      puts "Looking up #{protein_name}"
-      orf = orf_lookup.get_by_id protein_name
-      if ( orf == nil)
-        puts "Failed lookup for #{protein_name}"
-        raise KeyError
-      end
-
-
-      position = orf.identifiers.description.split('|').collect { |pos| pos.to_i }
-
-      if ( position.length != 2 )
-        puts "Badly formatted entry #{orf}"
-        raise EncodingError
-      end
-      orf_name = orf.entry_id.scan(/lcl\|(.*)/)[0][0]
-      frame=orf_name.scan(/frame_(\d)/)[0][0]
-      scaffold_name = orf_name.scan(/(scaffold_?\d+)_/)[0][0]
-
-      strand = (frame.to_i > 3) ? '-' : '+'
-#      strand = +1
-
-      prot_id = "pr#{protein_count.to_s}"
-      prot_attributes = [["ID",prot_id],["Name",orf_name]]
-      prot_gff_line = Bio::GFF::GFF3::Record.new(seqid = scaffold_name,source="OBSERVATION",feature_type="protein",
-        start_position=position[0]+1,end_position=position[1],score=prot_prob,strand=strand,frame=nil,attributes=prot_attributes)
-      gff_db.records += ["##gff-version 3\n","##sequence-region #{scaffold_name} 1 160\n",prot_gff_line]
-
-      prot_seq = orf.aaseq.to_s
-      throw "Not amino_acids" if prot_seq != orf.seq.to_s
-
-      if ( strand=='-' )
-        prot_seq.reverse!
-      end
-
-      for peptide in peptides
-        pprob = peptide['nsp_adjusted_probability'].to_f
-        if ( pprob >= tool.peptide_probability_threshold )
-          total_peptides += 1
-          pep_seq = peptide['peptide_sequence']
-
-          if ( strand=='-')
-            pep_seq.reverse!
-          end
-
-          start_indexes = [0]
-          prot_seq.scan /#{pep_seq}/  do |match| 
-              start_indexes << prot_seq.index(match,start_indexes.last)
-          end
-          start_indexes.delete_at(0)
-
-          # Now convert peptide coordinate to genome coordinates
-          # And create gff lines for each match
-          start_indexes.collect do |si|
-            pep_genomic_start = position[0] + 3*si
-            pep_genomic_end = pep_genomic_start + 3*pep_seq.length - 1
-            peptide_count+=1
-            pep_id = "p#{peptide_count.to_s}"
-            pep_attributes = [["ID",pep_id],["Parent",prot_id]]
-            pep_gff_line = Bio::GFF::GFF3::Record.new(seqid = scaffold_name,source="OBSERVATION",
-              feature_type="peptide",start_position=pep_genomic_start,end_position=pep_genomic_end,score=pprob,
-              strand=strand,frame=nil,attributes=pep_attributes)
-            fragment_gff_line = Bio::GFF::GFF3::Record.new(seqid = scaffold_name,source="OBSERVATION",
-              feature_type="fragment",start_position=pep_genomic_start,end_position=pep_genomic_end,score='',
-              strand=strand,frame=nil,attributes=[["Parent",pep_id],["ID",peptide['peptide_sequence']]])
-            gff_db.records += [pep_gff_line,fragment_gff_line]
-
-          end
-
-
-        end
-      end
-
-    rescue KeyError,EncodingError
-      skipped+=0
-    end
-
-    # p orf_name
-    # p prot_gff_line
-    # exit
-  end
-
-end
-
-f = open(gff_out_file,'w+')
-gff_db.records.each { |rec| 
-  f.write(rec.to_s)
-}
-f.close
-
-p "Finished."
-p "Proteins: #{protein_count}"
-p "Skipped Decoys: #{skipped}"
-p "Total Peptides: #{total_peptides}"
-p "Peptides Written: #{total_peptides - low_prob}"
-p "Peptides Culled: #{low_prob}"
-exit(0)