protk 1.4.4.beta2 → 1.4.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f278e7fe8e3a0955907a13952ced4fa0d772c204
-  data.tar.gz: 513fb214683486b9d3596a9b9f0956107d611170
+  metadata.gz: 1b59cd3751adc7a13c6dce81a90c2a4d739e1efe
+  data.tar.gz: 3ac1aba71a95b729101a6c64699cebaf1929fe34
 SHA512:
-  metadata.gz: e59fcb0724cbf42b8f63e65ca6d88fd91c7d45d3981964358c82e040f9235e2ce6768251d088966044827cadf5c9ce46f189345d3c27293d0b10b44daf018c10
-  data.tar.gz: 36329dca4cf416fc2b9bd6f0d395895ee2fd32fdba2f6ebd75c5d26ed21b497dc890cfc6bcf36b1f08bc7f3954bae76adea64450a431d6ac365a2930191997cc
+  metadata.gz: 6ab966131e53b6e379ba1df7717cc71e0a7ead11b603d16d474f4fdce487623546ca472c8624421d62af1e238f7e2917f8ed1e66c52a82d0fc4798cd7b1fdf6b
+  data.tar.gz: 05b98a731eb99063f17942fed42dce0e450488e61b11452b918269bd27788a300d7d2ebf4c2a67930c14bc5291dfab7bf8b13b992300356e96b0d274e68c6d96

data/README.md

@@ -16,10 +16,16 @@ Protk is a suite of tools for proteomics. It aims to present a simple and consis
  
 Protk is a ruby gem and requires ruby 2.0 or higher with support for libxml2. To avoid installation problems we recommend using [rvm](https://rvm.io) to install ruby.
 
-``` shell
+```shell
     gem install protk
 ```
 
+On macOS you may need to do
+
+```bash
+	brew install coreutils
+```
+
 ## Ruby Compatibility
 
 In general Protk requires ruby with a version >=2.0.

data/bin/maker_to_proteindb.rb

@@ -0,0 +1,148 @@
+#!/usr/bin/env ruby
+#
+# This file is part of protk
+# Created by Ira Cooke 4/9/2013
+#
+# 
+
+require 'protk/constants'
+require 'protk/tool'
+require 'protk/gff_to_proteindb_tool'
+require 'bio'
+
+tool=GffToProteinDBTool.new([:explicit_output,:debug,:add_transcript_info])
+tool.option_parser.banner = "Create a protein database from Maker gene prediction \
+output that is suitable for later processing by proteogenomics tools.\
+\n\nUsage: maker_to_proteindb.rb [options] maker.gff3"
+
+tool.add_value_option(:proteins_file,nil,['-p', '--prot-fasta proteins', 'A fasta file \
+	containing protein sequences for each transcript'])
+
+# tool.add_value_option(:explicit_output,nil,['-o', '--output out', 'An explicitly named output file. \
+#   The default is to write to standard output'])
+
+exit unless tool.check_options(true)
+
+inname=ARGV.shift
+
+$protk = Constants.instance
+log_level = tool.debug ? :debug : :fatal
+$protk.info_level= log_level
+
+tool.print_progress=true
+
+outfile=nil
+if ( tool.explicit_output != nil)
+  outfile=File.open(tool.explicit_output,'w')
+else
+  outfile=$stdout
+  tool.print_progress=false
+end
+
+gene_lines=[]
+
+def get_protein_sequence(transcript_id,proteins_file)
+	%x[samtools faidx #{proteins_file} #{transcript_id} | tail -n +2]
+end
+
+def cds_to_header_text(coding_sequence,transcript_id)
+#  require 'debugger';debugger
+  imatch=coding_sequence.match(/CDS\t(\d+)\t(\d+).*?([-\+]{1}.*?Parent=#{transcript_id})$/)
+  if imatch==nil
+    return ""
+  end
+  istart=imatch[1]
+  iend=imatch[2]
+  "#{istart}|#{iend}"
+end
+
+def sequence_fasta_header(tool,transcript_line,coding_sequences)
+
+  tmatch=transcript_line.match(/mRNA\t(\d+)\t(\d+).*?([-\+]{1}).*?ID=(.*?);/)
+#  require 'debugger'; debugger
+  tstart,tend,tstrand = transcript_line.match(/mRNA\t(\d+)\t(\d+).*?([-\+]{1})/).captures
+
+  # tstart=tmatch[1]
+  # tend=tmatch[2]
+#  tsidfield = transcript_line.split("\t")[8]
+
+  tid = transcript_line.match(/ID=([^;]+)/).captures[0]
+  # if tsidfield =~ /ID=/
+  #   tid = tsidfield.match(/ID=(.*?);/).captures[0]
+  # else
+  #   tid = tsidfield.gsub(" ","_").gsub(";","_")
+  # end
+
+   # require 'byebug';byebug
+
+  tstrandfr="fwd"
+  tstrandfr = "rev" if tstrand=="-"
+
+  scaffold=transcript_line.split("\t")[0]
+
+  # tid=tmatch[4]
+  header=">lcl|#{scaffold}_#{tstrandfr}_#{tid} #{tstart}|#{tend}"
+  if tool.add_transcript_info
+    coding_sequences.each { |coding_sequence| header << " #{cds_to_header_text(coding_sequence,tid)}" }
+  end
+  header
+end
+
+def protein_sequence(protein_lines)
+  seq=""
+  protein_lines.each_with_index do |line, i|  
+      seq << line.match(/(\w+)\]?$/)[1]
+ end
+
+  seq
+end
+
+
+def parse_gene(tool,gene_lines)
+
+	# require 'byebug';byebug
+	geneid=gene_lines[0].match(/ID=([^;]+)/).captures[0]
+
+	scaffold_id = gene_lines[1].split("\t")[0]
+
+	transcripts=tool.get_lines_matching(/mRNA/,gene_lines)
+
+	coding_sequences=tool.get_lines_matching(/CDS/,gene_lines)
+
+	fasta_string=""
+	
+	transcripts.each_with_index do |ts, i|
+
+  		prot_id=ts.match(/ID=([^;]+)/).captures[0]
+
+		begin
+	  		fh=sequence_fasta_header(tool,ts,coding_sequences)
+  			fasta_string << "#{fh}\n"
+  			ps=get_protein_sequence(prot_id,tool.proteins_file)  
+  			fasta_string << "#{ps}"
+  		rescue => e
+  			$protk.log "Unable to retrieve protein for #{prot_id} #{e}" , :debug
+  		end
+	end
+
+	fasta_string
+end
+
+
+
+File.open(inname).each_with_index do |line, line_i|  
+  line.chomp!
+
+  if tool.start_new_gene(line)
+  	if gene_lines.length > 0
+	    gene_string=parse_gene(tool,gene_lines)
+	    outfile.write gene_string
+	    gene_lines=[]
+	end
+  end
+
+  if line =~ /maker/
+    gene_lines << line
+  end
+
+end

data/bin/msgfplus_search.rb

@@ -93,11 +93,13 @@ if for_galaxy || Pathname.new(database_path).extname.to_s.downcase != ".fasta"
 #   database_path="#{database_path}.fasta"
 end
 
+db_noext = "#{Pathname.new(database_path).sub_ext('')}"
+
 # Database must be indexed
-unless FileTest.exists?("#{database_path}.canno")
-  # dbdir = Pathname.new(database_path).dirname.to_s
+unless FileTest.exists?("#{db_noext}.canno")
   tdavalue=search_tool.decoy_search ? 1 : 0;
-  make_msgfdb_cmd << "java -Xmx3500M -cp #{genv.msgfplusjar} edu.ucsd.msjava.msdbsearch.BuildSA -d #{database_path} -tda #{tdavalue}; "
+  genv.log "Database index not found at #{db_noext}. Building new index" , :info
+  make_msgfdb_cmd << "java -Xmx#{search_tool.java_mem} -cp #{genv.msgfplusjar} edu.ucsd.msjava.msdbsearch.BuildSA -d #{database_path} -tda #{tdavalue}; "
 end
 
 
@@ -262,4 +264,4 @@ ARGV.each do |filename|
   #
   make_msgfdb_cmd=""
 
-end
+end

data/bin/protein_prophet.rb

@@ -54,6 +54,19 @@ else
   output_file=Tool.default_output_path(inputs,".prot.xml",prophet_tool.output_prefix,@output_suffix)
 end
 
+genv.log("Checking input files ...",:info)
+inputs.each {|file_name| 
+
+  throw "Missing input file #{file_name}" unless File.exist?(file_name)
+
+  file_pepxml = PepXML.new(file_name)
+
+  db_path=file_pepxml.extract_db()
+  throw "Unable to find database #{db_path} used for searching. Fix paths in input files first" unless File.exist?(db_path)
+}
+
+
+
 if ( !Pathname.new(output_file).exist? || prophet_tool.over_write )
 
   cmd="ProteinProphet "

data/bin/protxml_to_gff.rb

@@ -38,7 +38,7 @@ end
 
 def protein_id_to_gffid(protein_id,gff_idregex)
 	return protein_id if gff_idregex.nil?
-
+	# require 'byebug'; byebug
 	m = protein_id.match(/#{gff_idregex}/)
 	if m
 		return m.captures[0]		
@@ -77,7 +77,9 @@ def prepare_fasta(database_path,type)
   end
 
 
-  db_indexfilename = type=='prot' ? "#{db_filename}.pin" : "#{db_filename}.nhr"
+  db_indexfilename = type=='prot' ? "#{db_filename}.00.pin" : "#{db_filename}.nhr"
+
+#  require 'byebug';byebug
 
   if File.exist?(db_indexfilename)
     orf_lookup = FastaDB.new(db_filename)
@@ -101,6 +103,7 @@ tool.add_value_option(:protein_probability_threshold,0.99,['--prot-threshold pro
 tool.add_value_option(:gff_idregex,nil,['--gff-idregex pre','Regex with capture group for parsing gff ids from protein ids'])
 tool.add_value_option(:genome_idregex,nil,['--genome-idregex pre','Regex with capture group for parsing genomic ids from protein ids'])
 tool.add_value_option(:ignore_regex,nil,['--ignore-regex pre','Regex to match protein ids that we should ignore completely'])
+tool.add_value_option(:include_mods,false,['--include-mods','Output gff entries for peptide modification sites'])
 
 exit unless tool.check_options(true,[:database,:coords_file])
 
@@ -170,6 +173,12 @@ proteins.each do |protein|
 					peptide_entries.each do |peptide_entry|
 						output_fh.write peptide_entry.to_s
 					end
+					if tool.include_mods
+						mod_entries = peptide.mods_to_gff3_records(protein_entry.aaseq,gff_parent_entry,gff_cds_entries)
+						mod_entries.each do |mod_entry|
+							output_fh.write mod_entry.to_s
+						end
+					end
 				end
 			end
 

data/bin/sixframe.rb

@@ -64,7 +64,12 @@ file.each do |entry|
   length = entry.naseq.length
 
   (1...7).each do |frame|
-    translated_seq= entry.naseq.translate(frame)
+    begin
+      translated_seq= entry.naseq.translate(frame)
+    rescue => exception
+      puts "#{entry}"
+      exit 1
+    end
     orfs=translated_seq.split("*")
     orf_index = 0
     position = ((frame - 1) % 3) + 1    

data/bin/tandem_search.rb

@@ -22,8 +22,10 @@ exit unless search_tool.check_options(true)
 
 # Our environment should be setup so that tandem or tandem.exe is on the path
 #
-tandem_bin=%x[which tandem].chomp
-tandem_bin=%x[which tandem.exe].chomp unless tandem_bin && tandem_bin.length>0
+# tandem_bin=%x[which tandem].chomp
+# tandem_bin=%x[which tandem.exe].chomp unless tandem_bin && tandem_bin.length>0
+
+# tandem_bin
 
 @output_suffix="_tandem"
 
@@ -70,7 +72,7 @@ ARGV.each do |filename|
 
     # The basic command
     #
-    cmd= "#{tandem_bin} #{params_path}"
+    cmd= "#{genv.tandem_bin} #{params_path}"
 
     # Add a cleanup command unless the user wants to keep params files
     #

data/lib/protk/constants.rb

@@ -63,6 +63,18 @@ class Constants
     "#{@protk_dir}/tools/msgfplus"
   end
 
+  def get_path_for_executable(exec_name_list)
+    exec_name_list.each do |exec_name| 
+      exec_path=%x[which #{exec_name}].chomp
+      return exec_path unless !exec_path || exec_path.length==0
+    end
+    throw "Unable to locate #{exec_name_list}"
+  end
+
+  def tandem_bin
+    get_path_for_executable ["tandem","tandem.exe"]
+  end
+
   def msgfplusjar
     msgfplus_path=%x[which MSGFPlus.jar]
     msgfplus_path.chomp

data/lib/protk/gff_to_proteindb_tool.rb

@@ -0,0 +1,56 @@
+#
+# This file is part of protk
+# Created by Ira Cooke 9/3/2017
+#
+# Provides common functionality used by tools that convert gff to a protein database
+# 
+# These tools read a gff and then write out protein entries in the following format
+#
+# >lcl|<scaffold_id>_<orientation>_<transcript_id> gene_start|gene_end cds1_start|cds1_end cds2_start|cds2_end ...
+#
+
+require 'optparse'
+require 'pathname'
+require 'protk/tool'
+
+class GffToProteinDBTool < Tool
+
+  attr_accessor :print_progress
+
+  # Initializes commandline options common to all such tools.
+  # Individual search tools can add their own options, but should use Capital letters to avoid conflicts
+  #
+  def initialize(option_support=[])
+    super(option_support)
+
+    if ( option_support.include? :add_transcript_info )
+      add_boolean_option(:add_transcript_info,false,['--info','Include CDS Coordinates'])
+    end
+
+    @option_parser.summary_width=40
+
+    @capturing_gene=false
+    @current_gene=nil
+  end
+
+  def start_new_gene(line)
+    if (line =~ /maker\sgene/)
+        new_gene = line.match(/ID=([^;]+)/).captures[0]
+        if new_gene!=@current_gene
+          @current_gene=new_gene
+          return true
+        end
+      end
+  end
+
+  def get_lines_matching(pattern,gene_lines)
+    match_lines=[]
+    gene_lines.each do |line|  
+      if line =~ pattern
+        match_lines << line
+      end
+    end
+    match_lines
+  end
+
+end

data/lib/protk/peptide.rb

@@ -3,12 +3,15 @@ require 'bio'
 require 'protk/bio_gff3_extensions'
 require 'protk/mzidentml_doc'
 require 'protk/error'
+require 'protk/peptide_mod'
+# require 'protk/indistinguishable_peptide'
 
 include LibXML
 
 class PeptideNotInProteinError < ProtkError
 end
 
+
 class Peptide
 
 	# Stripped sequence (no modifications)
@@ -17,6 +20,9 @@ class Peptide
 	attr_accessor :charge
 	attr_accessor :probability
 	attr_accessor :theoretical_neutral_mass
+	attr_accessor :modifications
+	attr_accessor :modified_sequence
+	attr_accessor :indistinguishable_peptides
 
 	def as_protxml
 		node = XML::Node.new('peptide')
@@ -33,6 +39,27 @@ class Peptide
 			pep.sequence=xmlnode['peptide_sequence']
 			pep.probability=xmlnode['nsp_adjusted_probability'].to_f
 			pep.charge=xmlnode['charge'].to_i
+
+			# This deal with the case where mods are on the primary peptide
+			#
+			mod_info_node = xmlnode.find('protxml:modification_info','protxml:http://regis-web.systemsbiology.net/protXML')
+
+			# The pepXML spec says there can be multiple modification_info's but in practice there never is.
+			# We assume either 1 or 0
+			if ( mod_info_node.length > 0 )
+				throw "Encountered multiple modification_info nodes for a peptide" if mod_info_node.length > 1
+				pep.modified_sequence = mod_info_node[0]['modified_peptide']
+				mod_nodes = mod_info_node[0].find('protxml:mod_aminoacid_mass','protxml:http://regis-web.systemsbiology.net/protXML')
+				# require 'byebug';byebug
+				pep.modifications = mod_nodes.collect { |e| PeptideMod.from_protxml(e) }
+			end
+
+			# This deals with indistinguishable peptides
+			#
+			ips = xmlnode.find('protxml:indistinguishable_peptide','protxml:http://regis-web.systemsbiology.net/protXML')
+			# require 'byebug';byebug
+			pep.indistinguishable_peptides = ips.collect { |e| IndistinguishablePeptide.from_protxml(e) }
+
 			pep
 		end
 
@@ -55,17 +82,23 @@ class Peptide
 			pep.charge = best_psm.attributes['chargeState'].to_i
 			pep.protein_name = mzid_doc.get_dbsequence(xmlnode.parent,xmlnode.parent.attributes['dBSequence_ref']).attributes['accession']
 
-			# pep.charge = MzIdentMLDoc.get_charge_for_psm(best_psm)
 
 			pep
 		end
 
 		def from_sequence(seq,charge=nil)
 			pep=new()
-			pep.sequence=seq
+
+			pep.modifications = pep.modifications_from_sequence(seq)
+			pep.modified_sequence = seq
+
+			seq = seq.sub(/^n\[[0-9]+?\]/,"")
+			pep.sequence = seq.gsub(/[0-9\.\[\]]/,"")
 			pep.charge=charge
 			pep
 		end
+
+
 		private :new
 	end
 
@@ -73,6 +106,26 @@ class Peptide
 
 	end
 
+	def modifications_from_sequence(seq)
+
+		seq = seq.sub(/^n\[[0-9]+?\]/,"")
+		offset = 0
+		mods = seq.enum_for(:scan, /([A-Z])\[([0-9\.]+)\]/).map {
+			pm = PeptideMod.from_data(Regexp.last_match.begin(0)+1-offset,Regexp.last_match.captures[0],Regexp.last_match.captures[1].to_f)
+			offset += Regexp.last_match.captures[1].length+2
+			pm
+		}
+
+		# if ( seq == "N[115]VMN[115]LTPAETQ[129]QLHAALESQLSPGELAK" )
+		# 	require 'byebug';byebug
+		# 	puts "hi"
+		# end
+
+
+		mods
+	end
+
+
 	# Expects prot_seq not to contain explicit stop codon (ie * at end)
 	# AA coords are 0-based unlike genomic coords which are 1 based
 	#
@@ -112,23 +165,61 @@ class Peptide
 		throw "Expected GFF3 Record but got #{parent_record.class}" unless parent_record.class==Bio::GFF::GFF3::Record
 		throw "Expected Array but got #{cds_records.class}" unless cds_records.class==Array
 
-		on_reverse_strand = (parent_record.strand=="-") ? true : false
 		aa_coords = coords_in_protein(prot_seq,false) # Always use forward protein coordinates
 
+		gff_records_for_coords_in_protein(aa_coords,self.sequence.length,parent_record,cds_records)		
+	end
+
+	def mods_to_gff3_records(prot_seq,parent_record,cds_records)
+
+		throw "Expected GFF3 Record but got #{parent_record.class}" unless parent_record.class==Bio::GFF::GFF3::Record
+		throw "Expected Array but got #{cds_records.class}" unless cds_records.class==Array
+
+		pep_aa_coords = coords_in_protein(prot_seq,false)
+
+		mod_records = []
+		
+		unless ( self.modifications.nil? )
+			self.modifications.each { |mod|
+				prot_position = mod.position+pep_aa_coords[:start]
+				mod_aa_coords = {:start => prot_position, :end => prot_position+1}
+				mod_records << gff_records_for_coords_in_protein(mod_aa_coords,1,parent_record,cds_records, {:type => "modified_amino_acid_feature", :mod => mod, :modified_sequence => self.modified_sequence})	
+			}
+		end
+
+		unless ( self.indistinguishable_peptides.nil? )
+			self.indistinguishable_peptides.each { |ip|
+				unless ( ip.modifications.nil? )
+					ip.modifications.each { |mod|
+						prot_position = mod.position+pep_aa_coords[:start]-1
+						mod_aa_coords = {:start => prot_position, :end => prot_position+1}
+						mod_records << gff_records_for_coords_in_protein(mod_aa_coords,1,parent_record,cds_records, {:type => "modified_amino_acid_feature", :mod => mod, :modified_sequence => ip.modified_sequence})	
+					}
+				end
+			} 
+		end
+
+		mod_records.flatten
+	
+	end
+
+
+	def gff_records_for_coords_in_protein(aa_coords,seqlen,parent_record,cds_records,record_info ={:type => "polypeptide"})
+		on_reverse_strand = (parent_record.strand=="-") ? true : false
 		ordered_cds_records = on_reverse_strand ? cds_records.sort.reverse : cds_records.sort
 
 		# Initial position is the number of NA's from the start of translation
 		#
-		pep_nalen = self.sequence.length*3
+		pep_nalen = seqlen*3
 
 		i = 0; #Current protein position (in nucleic acids)
 
 		pep_start_i = aa_coords[:start]*3
-		pep_end_i = pep_start_i+self.sequence.length*3
-		fragments=[]
+		pep_end_i = pep_start_i+seqlen*3
+		gff_records=[]
 		ordered_cds_records.each do |cds_record|
 
-			fragment = nil
+			gff_record = nil
 			fragment_len = 0
 			if on_reverse_strand
 
@@ -139,16 +230,16 @@ class Peptide
 					fragment_end = cds_record.end
 					fragment_len = [cds_record.length,pep_end_i-i].min
 					fragment_start = fragment_end-fragment_len+1
-					fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
+					gff_record = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record,record_info)
 				elsif before_len>0
 					fragment_end = cds_record.end - before_len
 					fragment_len = [cds_record.length-before_len,pep_end_i-i-before_len].min
 					fragment_start = fragment_end - fragment_len + 1
 					if fragment_len>0
-						fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
+						gff_record = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record,record_info)
 					end
 				else
-					fragment=nil
+					gff_record=nil
 				end				
 			else
 				in_peptide = (i<pep_end_i) && (i>=pep_start_i)
@@ -157,33 +248,64 @@ class Peptide
 					fragment_start = cds_record.start
 					fragment_len = [cds_record.length,pep_end_i-i].min
 					fragment_end = fragment_start+fragment_len-1
-					fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
+					gff_record = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record,record_info)
 				elsif before_len>0
 					fragment_start = cds_record.start + before_len
 					fragment_len = [cds_record.length-before_len,pep_end_i-i-before_len].min
 					fragment_end = fragment_start + fragment_len-1
 					if fragment_len>0
-						fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
+						gff_record = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record,record_info)
 					end
 				else
-					fragment=nil
+					gff_record = nil
 				end
 
 			end
 			i+=cds_record.length
-			fragments << fragment unless fragment.nil?
+			gff_records << gff_record unless gff_record.nil?
 		end
-		fragments
+		gff_records
 	end
 
-	def gff_record_for_peptide_fragment(start_i,end_i,parent_record)
+	def gff_record_for_peptide_fragment(start_i,end_i,parent_record,record_info)
 		cds_id = parent_record.id
-		this_id = "#{cds_id}.#{self.sequence}"
+		mod_sequence = record_info[:modified_sequence]
+		this_id = mod_sequence ? "#{cds_id}.#{mod_sequence}" : "#{cds_id}.#{self.sequence}"
 		this_id << ".#{self.charge}" unless self.charge.nil?
+		mod = record_info[:mod]
+		this_id << ".#{mod.position}.#{mod.mass}" unless mod.nil?
 		score = self.probability.nil? ? "." : self.probability.to_s
-		gff_string = "#{parent_record.seqid}\tMSMS\tpolypeptide\t#{start_i}\t#{end_i}\t#{score}\t#{parent_record.strand}\t0\tID=#{this_id};Parent=#{cds_id}"
+		record_type = mod.nil? ? record_info[:type] : "#{record_info[:type]}_#{mod.amino_acid}"
+		gff_string = "#{parent_record.seqid}\tMSMS\t#{record_type}\t#{start_i}\t#{end_i}\t#{score}\t#{parent_record.strand}\t0\tID=#{this_id};Parent=#{cds_id}"
 		Bio::GFF::GFF3::Record.new(gff_string)
 	end
 
+end
+
 
-end
+#             <indistinguishable_peptide peptide_sequence="MEYENTLTAAMK" charge="2" calc_neutral_pep_mass="1416.63">
+#             <modification_info modified_peptide="M[147]EYENTLTAAMK"/>
+#             </indistinguishable_peptide>
+class IndistinguishablePeptide < Peptide
+	class << self
+		def from_protxml(xmlnode)
+			pep=new()
+			pep.sequence=xmlnode['peptide_sequence']
+			pep.charge=xmlnode['charge'].to_i
+
+			mod_info_node = xmlnode.find('protxml:modification_info','protxml:http://regis-web.systemsbiology.net/protXML')
+
+			if ( mod_info_node.length > 0 )
+				throw "Encountered multiple modification_info nodes for an indistinguishable peptide" if mod_info_node.length > 1
+				pep.modified_sequence = mod_info_node[0]['modified_peptide']
+				mod_nodes = mod_info_node[0].find('protxml:mod_aminoacid_mass','protxml:http://regis-web.systemsbiology.net/protXML')
+				if ( mod_nodes.length > 0 )
+					pep.modifications = mod_nodes.collect { |e| PeptideMod.from_protxml(e) }
+				else
+					pep.modifications = pep.modifications_from_sequence(pep.modified_sequence)
+				end
+			end
+			pep
+		end
+	end
+end

data/lib/protk/peptide_mod.rb

@@ -0,0 +1,42 @@
+require 'libxml'
+require 'bio'
+
+include LibXML
+
+class PeptideMod
+
+	# Fully Modified Sequence
+	attr_accessor :position
+	attr_accessor :amino_acid
+	attr_accessor :mass
+
+	class << self
+
+		# <modification_info modified_peptide="GFGFVTYSC[160]VEEVDAAMC[160]ARPHK">
+		# <mod_aminoacid_mass position="9" mass="160.030600"/>
+		# <mod_aminoacid_mass position="18" mass="160.030600"/>
+		# </modification_info>
+
+		def from_protxml(xmlnode)
+			pepmod = new()
+			pepmod.position=xmlnode['position'].to_i
+			pepmod.mass=xmlnode['mass'].to_f
+			pepmod
+		end
+
+		def from_data(position,amino_acid,mass)
+			pepmod = new()
+			pepmod.position = position
+			pepmod.amino_acid = amino_acid
+			pepmod.mass = mass
+			pepmod
+		end
+
+		private :new
+	end
+
+	def initialize()
+
+	end
+
+end

data/lib/protk/setup_rakefile.rake

@@ -153,6 +153,12 @@ file tpp_installed_file => [@build_dir,tpp_download_file] do
 
 	sh %{cd #{@build_dir};tar -xvzf TPP-#{tpp_version}.tgz}
 
+	sh %{cp ~/Desktop/singleton.hpp #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src/../extern/ProteoWizard/pwiz/libraries/boost_aux/boost/utility/singleton.hpp}
+
+	sh %{cp ~/Desktop/MascotScoreParser.h #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src/Validation/DiscriminateFunction/Mascot/MascotScoreParser.h}
+	sh %{cp ~/Desktop/PTMProphetParser.cxx #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src/Validation/PTMProphetParser/PTMProphetParser.cxx}
+	sh %{cp ~/Desktop/RespectFilter.h #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src/Validation/Respect/RespectFilter.h} 
+
 	File.open("#{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src/Makefile.config.incl","wb") do |f|
 		f.write "TPP_ROOT=#{env.tpp_root}/\nTPP_WEB=/tpp/\nXSLT_PROC=/usr/bin/xsltproc\nCGI_USERS_DIR=${TPP_ROOT}cgi-bin/"
 	end
@@ -173,13 +179,18 @@ file tpp_installed_file => [@build_dir,tpp_download_file] do
 		makefile_text = File.read("#{makefile_path}")
 
 		File.open("#{makefile_path}","w+") do |f|
-			subs_text = makefile_text.gsub("cp -rfu","cp -rf")
+			subs_text = makefile_text.gsub("cp -rfu","cp -rf").gsub("-Werror","")
+#			subs_text = subs_text.gsub("-Werror","")
 			f.write subs_text
 		end
+
+
+
 	end
 	sh %{cd #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src;echo '' > ../perl/tpp_models.pl;echo '' > ../perl/exporTPP.pl;echo '' > ../CGI/show_nspbin.pl;echo '' > ../CGI/tpp_gui/tpp_gui.pl}
 
-	build_cmd = "#{use_perl_locallib_cmd};cd #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src ; make -s"
+#	build_cmd = "#{use_perl_locallib_cmd};cd #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src ; make -s"
+	build_cmd = "#{use_perl_locallib_cmd};cd #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src ; make"
 	install_cmd = "#{use_perl_locallib_cmd};cd #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src ; make install"
 	env.log build_cmd, :info
 	sh %{#{build_cmd}}

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.4.4.beta2
+  version: 1.4.4
 platform: ruby
 authors:
 - Ira Cooke
@@ -14,170 +14,170 @@ dependencies:
   name: open4
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.3.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.3.0
 - !ruby/object:Gem::Dependency
   name: bio
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 1.4.3
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.4.3
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 1.4.3
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.4.3
 - !ruby/object:Gem::Dependency
   name: rest-client
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 1.6.7
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.6.7
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 1.6.7
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.6.7
 - !ruby/object:Gem::Dependency
   name: net-ftp-list
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 3.2.5
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 3.2.5
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: 3.2.5
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 3.2.5
 - !ruby/object:Gem::Dependency
   name: libxml-ruby
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
-    - - '>='
+        version: '2.9'
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.7.0
+        version: 2.9.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
-    - - '>='
+        version: '2.9'
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.7.0
+        version: 2.9.0
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
 - !ruby/object:Gem::Dependency
   name: rspec-mocks
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
 - !ruby/object:Gem::Dependency
   name: rake-compiler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: byebug
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3.5'
 - !ruby/object:Gem::Dependency
   name: sqlite3
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
 description: Commandline tools for proteomics
@@ -202,6 +202,7 @@ executables:
 - uniprot_mapper.rb
 - sixframe.rb
 - augustus_to_proteindb.rb
+- maker_to_proteindb.rb
 - protxml_to_gff.rb
 - protxml_to_table.rb
 - swissprot_to_table.rb
@@ -222,6 +223,7 @@ files:
 - bin/filter_psms.rb
 - bin/interprophet.rb
 - bin/make_decoy.rb
+- bin/maker_to_proteindb.rb
 - bin/manage_db.rb
 - bin/mascot_search.rb
 - bin/mascot_to_pepxml.rb
@@ -283,6 +285,7 @@ files:
 - lib/protk/fastadb.rb
 - lib/protk/galaxy_stager.rb
 - lib/protk/galaxy_util.rb
+- lib/protk/gff_to_proteindb_tool.rb
 - lib/protk/gffdb.rb
 - lib/protk/manage_db_rakefile.rake
 - lib/protk/manage_db_tool.rb
@@ -292,6 +295,7 @@ files:
 - lib/protk/omssa_util.rb
 - lib/protk/openms_defaults.rb
 - lib/protk/peptide.rb
+- lib/protk/peptide_mod.rb
 - lib/protk/pepxml.rb
 - lib/protk/pepxml_writer.rb
 - lib/protk/physical_constants.rb
@@ -324,19 +328,18 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>'
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.1
+rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
 summary: Proteomics Toolkit
 test_files: []
-has_rdoc: