protk 1.4.3 → 1.4.4.beta1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 31df514a2203236ea9ac25f8d5cc9c282378e04d
-  data.tar.gz: f1bb438ef01003afc166eb5b0342dbd8f6ecd09b
+  metadata.gz: 6b769808b35e55e6f9c74b11704e57153e6276cc
+  data.tar.gz: ba8003573127b2912a64995a76e2204af3213851
 SHA512:
-  metadata.gz: 7f7f0fe81411f17b89037162ad7bf5374be69309888bda2f84b058d69773dd1790469d40dd5797e0306ce49ecc95426cfb80b65bfcb95ac0a052be90db40ea42
-  data.tar.gz: f2db6018ac90079e925f7c5c071be3fbedd77bc3787cfc58a91aa38048f43f60426020a3bff3a5a58c4bea6d71aaad7c0ab10437e050eaf1998792ca6ab2e1dd
+  metadata.gz: 7de51d2b7a77625abd3f0042057a7fc689f986e8fbf30b257b4d48930983445a26c6dac23fe8b1f7e3e96855fa47152f3731a2c29443c72cac84aaf56ae751c5
+  data.tar.gz: 9a4d1fd1644cbb2e6a067173fa59a8bb99570eb4b1d4878272267b36140a01c4893568ca12a0afef77db1b1c626745f162f183ba1cd9afcaef78a0802072f605

data/bin/mzid_to_protxml.rb

@@ -12,6 +12,7 @@ require 'protk/constants'
 require 'protk/command_runner'
 require 'protk/mzidentml_doc'
 require 'protk/protein_group'
+require 'protk/protein_summary'
 require 'protk/tool'
 
 include LibXML
@@ -45,6 +46,10 @@ prot_xml_writer = ProtXMLWriter.new
 $protk.log "Parsing MzIdentML input file" , :info
 mzid_doc = MzIdentMLDoc.new(input_file)
 
+header = ProteinSummary.from_mzid(mzid_doc)
+
+prot_xml_writer.append_header(header)
+
 protein_groups = mzid_doc.protein_groups
 
 n_prots = protein_groups.length
@@ -77,4 +82,6 @@ end
 
 $protk.log "Writing #{n_written} proteins to #{output_file_name}", :info
 
+prot_xml_writer.append_dataset_derivation
+
 prot_xml_writer.save(output_file_name)

data/lib/protk/data/template_prot.xml

@@ -1,39 +1,3 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <protein_summary xmlns="http://regis-web.systemsbiology.net/protXML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://sashimi.sourceforge.net/schema_revision/protXML/protXML_v6.xsd" summary_xml="">
-<protein_summary_header reference_database="FULLPATH_TO_REFERENCE_DB" residue_substitution_list="I -&gt; L" source_files="FULLPATH_TO_SOURCE_PEPXML" source_files_alt="FULLPATH_TO_SOURCE_PEPXML" min_peptide_probability="" min_peptide_weight="" num_predicted_correct_prots="" num_input_1_spectra="" num_input_2_spectra="" num_input_3_spectra="" num_input_4_spectra="" num_input_5_spectra="" initial_min_peptide_prob="" total_no_spectrum_ids="" sample_enzyme="trypsin">
-<program_details analysis="proteinprophet" time="2014-01-20T14:17:37" version=" Insilicos_LabKey_C++ (TPP v0.0 Development trunk rev 0, Build 201307090846 (linux))">
-<proteinprophet_details occam_flag="Y" groups_flag="Y" degen_flag="Y" nsp_flag="Y" initial_peptide_wt_iters="2" nsp_distribution_iters="2" final_peptide_wt_iters="3">
-      <nsp_information neighboring_bin_smoothing="Y">
-         <nsp_distribution bin_no="0" nsp_lower_bound_incl="0.00" nsp_upper_bound_incl="0.00" pos_freq="0.057" neg_freq="0.625" pos_to_neg_ratio="0.09"/>
-         <nsp_distribution bin_no="1" nsp_lower_bound_excl="0.00" nsp_upper_bound_incl="0.31" pos_freq="0.037" neg_freq="0.152" pos_to_neg_ratio="0.24"/>
-         <nsp_distribution bin_no="2" nsp_lower_bound_excl="0.31" nsp_upper_bound_incl="1.00" pos_freq="0.077" neg_freq="0.032" pos_to_neg_ratio="2.42"/>
-         <nsp_distribution bin_no="3" nsp_lower_bound_excl="1.00" nsp_upper_bound_incl="2.50" pos_freq="0.113" neg_freq="0.033" pos_to_neg_ratio="3.39"/>
-         <nsp_distribution bin_no="4" nsp_lower_bound_excl="2.50" nsp_upper_bound_incl="4.63" pos_freq="0.123" neg_freq="0.032" pos_to_neg_ratio="3.91"/>
-         <nsp_distribution bin_no="5" nsp_lower_bound_excl="4.63" nsp_upper_bound_incl="7.90" pos_freq="0.143" neg_freq="0.032" pos_to_neg_ratio="4.50"/>
-         <nsp_distribution bin_no="6" nsp_lower_bound_excl="7.90" nsp_upper_bound_incl="14.92" pos_freq="0.196" neg_freq="0.041" pos_to_neg_ratio="4.78"/>
-         <nsp_distribution bin_no="7" nsp_lower_bound_excl="14.92" nsp_upper_bound_excl="inf" pos_freq="0.254" neg_freq="0.054" pos_to_neg_ratio="4.72" alt_pos_to_neg_ratio="4.78"/>
-      </nsp_information>
-      <ni_information>
-      </ni_information>
-      <protein_summary_data_filter min_probability="0.00" sensitivity="1.000" false_positive_error_rate="0.835" predicted_num_correct="1787" predicted_num_incorrect="9044"/>
-      <protein_summary_data_filter min_probability="0.10" sensitivity="1.000" false_positive_error_rate="0.235" predicted_num_correct="1787" predicted_num_incorrect="548"/>
-      <protein_summary_data_filter min_probability="0.20" sensitivity="1.000" false_positive_error_rate="0.235" predicted_num_correct="1787" predicted_num_incorrect="548"/>
-      <protein_summary_data_filter min_probability="0.30" sensitivity="0.956" false_positive_error_rate="0.151" predicted_num_correct="1709" predicted_num_incorrect="305"/>
-      <protein_summary_data_filter min_probability="0.40" sensitivity="0.916" false_positive_error_rate="0.095" predicted_num_correct="1638" predicted_num_incorrect="171"/>
-      <protein_summary_data_filter min_probability="0.50" sensitivity="0.887" false_positive_error_rate="0.063" predicted_num_correct="1585" predicted_num_incorrect="106"/>
-      <protein_summary_data_filter min_probability="0.60" sensitivity="0.853" false_positive_error_rate="0.036" predicted_num_correct="1525" predicted_num_incorrect="58"/>
-      <protein_summary_data_filter min_probability="0.70" sensitivity="0.826" false_positive_error_rate="0.020" predicted_num_correct="1477" predicted_num_incorrect="31"/>
-      <protein_summary_data_filter min_probability="0.80" sensitivity="0.805" false_positive_error_rate="0.012" predicted_num_correct="1438" predicted_num_incorrect="18"/>
-      <protein_summary_data_filter min_probability="0.90" sensitivity="0.773" false_positive_error_rate="0.006" predicted_num_correct="1381" predicted_num_incorrect="8"/>
-      <protein_summary_data_filter min_probability="0.95" sensitivity="0.749" false_positive_error_rate="0.004" predicted_num_correct="1339" predicted_num_incorrect="5"/>
-      <protein_summary_data_filter min_probability="0.96" sensitivity="0.738" false_positive_error_rate="0.003" predicted_num_correct="1318" predicted_num_incorrect="4"/>
-      <protein_summary_data_filter min_probability="0.97" sensitivity="0.728" false_positive_error_rate="0.002" predicted_num_correct="1302" predicted_num_incorrect="3"/>
-      <protein_summary_data_filter min_probability="0.98" sensitivity="0.711" false_positive_error_rate="0.002" predicted_num_correct="1272" predicted_num_incorrect="2"/>
-      <protein_summary_data_filter min_probability="0.99" sensitivity="0.609" false_positive_error_rate="0.000" predicted_num_correct="1088" predicted_num_incorrect="0"/>
-      <protein_summary_data_filter min_probability="1.00" sensitivity="0.164" false_positive_error_rate="0.000" predicted_num_correct="294" predicted_num_incorrect="0"/>
-</proteinprophet_details>
-</program_details>
-</protein_summary_header>
-<dataset_derivation generation_no="0">
-</dataset_derivation>
 </protein_summary>

data/lib/protk/mzidentml_doc.rb

@@ -37,6 +37,21 @@ class MzIdentMLDoc < Object
 		@document=parser.parse
 	end
 
+	def source_files
+		@document.find("//#{MZID_NS_PREFIX}:SourceFile","#{MZID_NS_PREFIX}:#{MZID_NS}")
+	end
+
+	def search_databases
+		@document.find("//#{MZID_NS_PREFIX}:SearchDatabase","#{MZID_NS_PREFIX}:#{MZID_NS}")
+	end
+
+	def enzymes
+		@document.find("//#{MZID_NS_PREFIX}:Enzyme","#{MZID_NS_PREFIX}:#{MZID_NS}")
+	end
+
+	def analysis_software
+		@document.find("//#{MZID_NS_PREFIX}:AnalysisSoftware","#{MZID_NS_PREFIX}:#{MZID_NS}")
+	end
 
 	def spectrum_queries
 		@document.find("//#{MZID_NS_PREFIX}:SpectrumIdentificationResult","#{MZID_NS_PREFIX}:#{MZID_NS}")
@@ -130,10 +145,7 @@ class MzIdentMLDoc < Object
 	# 	<SpectrumIdentificationItemRef spectrumIdentificationItem_ref="SII_1_1"/>
 	# </PeptideHypothesis>
 	def get_best_psm_for_peptide(peptide_node)
-
-
-
-		best_score=-1
+		best_score=nil
 		best_psm=nil
 		spectrumidrefs = self.find(peptide_node,"SpectrumIdentificationItemRef")
 		Constants.instance.log "Searching from among #{spectrumidrefs.length} for best psm" , :debug
@@ -143,7 +155,7 @@ class MzIdentMLDoc < Object
 			# psm_node = self.find(peptide_node,"SpectrumIdentificationItem[@id=\'#{id_ref}\']",true)[0]
 			psm_node = self.psms_cache[id_ref]
 			score = self.get_cvParam(psm_node,"MS:1002466")['value'].to_f
-			if score>best_score
+			if ( best_score == nil ) || ( score > best_score )
 				best_psm=psm_node
 				best_score=score
 			end

data/lib/protk/peptide.rb

@@ -49,7 +49,7 @@ class Peptide
 			pep=new()
 			pep.sequence=mzid_doc.get_sequence_for_peptide(xmlnode)
 			best_psm = mzid_doc.get_best_psm_for_peptide(xmlnode)
-			# require 'byebug';byebug
+			# require 'byebug';byebug if !best_psm
 			pep.probability = mzid_doc.get_cvParam(best_psm,"MS:1002466")['value'].to_f
 			pep.theoretical_neutral_mass = mzid_doc.get_cvParam(best_psm,"MS:1001117")['value'].to_f
 			pep.charge = best_psm.attributes['chargeState'].to_i

data/lib/protk/protein_summary.rb

@@ -0,0 +1,113 @@
+
+require 'protk/mzidentml_doc'
+require 'protk/protxml_writer'
+
+include LibXML
+
+# Represents the protein_summary node of a protXML document
+# This is the root of the document
+#
+class ProteinSummary
+
+	attr_accessor :reference_database
+	attr_accessor :residue_substitution_list
+	attr_accessor :source_files
+	attr_accessor :source_files_alt
+	attr_accessor :min_peptide_probability
+	attr_accessor :min_peptide_weight
+	attr_accessor :num_predicted_correct_prots
+	attr_accessor :num_input_1_spectra
+	attr_accessor :num_input_2_spectra
+	attr_accessor :num_input_3_spectra
+	attr_accessor :num_input_4_spectra
+	attr_accessor :num_input_5_spectra
+	attr_accessor :initial_min_peptide_prob
+	attr_accessor :total_no_spectrum_ids
+	attr_accessor :sample_enzyme
+
+	attr_accessor :program_name
+	attr_accessor :analysis_time
+	attr_accessor :program_version
+
+
+	class << self
+
+		def from_mzid(mzid_doc)
+
+			summary = new()
+			# Things we cant retrieve
+			summary.residue_substitution_list = ""
+			summary.min_peptide_probability = ""
+			summary.min_peptide_weight = ""
+			summary.num_predicted_correct_prots = ""
+			summary.num_input_1_spectra = ""
+			summary.num_input_2_spectra = ""
+			summary.num_input_3_spectra = ""
+			summary.num_input_4_spectra = ""
+			summary.num_input_5_spectra = ""
+			summary.initial_min_peptide_prob = ""
+			summary.total_no_spectrum_ids = ""			
+			summary.analysis_time = ""
+
+			db = mzid_doc.search_databases.first
+			summary.reference_database = db.attributes['location']
+
+			summary.source_files = mzid_doc.source_files.collect { |sf| sf.attributes['location'] }
+			summary.source_files_alt = summary.source_files
+
+			summary.sample_enzyme = mzid_doc.enzymes.first.attributes['name']
+			if mzid_doc.enzymes.first.attributes['semiSpecific']=="true"
+				summary.sample_enzyme = "semi#{summary.sample_enzyme}"
+			end
+
+			analysis_software = mzid_doc.analysis_software.first
+			summary.program_name = analysis_software.attributes['name']
+			summary.program_version = analysis_software.attributes['version']
+
+			summary
+		end
+
+
+		private :new
+	end
+
+	def initialize()
+
+	end
+
+	def as_protxml()
+		node = XML::Node.new('protein_summary_header')
+		# node.space_preserve=true
+		node["reference_database"] = self.reference_database
+		node["min_peptide_probability"] = self.min_peptide_probability
+		node["min_peptide_weight"] = self.min_peptide_weight
+		node["num_predicted_correct_prots"] = self.num_predicted_correct_prots
+		node["num_input_1_spectra"] = self.num_input_1_spectra
+		node["num_input_2_spectra"] = self.num_input_2_spectra
+		node["num_input_3_spectra"] = self.num_input_3_spectra
+		node["num_input_4_spectra"] = self.num_input_4_spectra
+		node["num_input_5_spectra"] = self.num_input_5_spectra
+		node["initial_min_peptide_prob"] = self.initial_min_peptide_prob
+		node["total_no_spectrum_ids"] = self.total_no_spectrum_ids
+		node["sample_enzyme"] = self.sample_enzyme
+
+
+		cnode = XML::Node.new('program_details')
+		# node.space_preserve=true
+		cnode["program_name"] = self.program_name
+		cnode["analysis_time"] = self.analysis_time
+		cnode["program_version"] = self.program_version
+#		require 'byebug';byebug
+
+		node << cnode
+
+		# ddnode = XML::Node.new('dataset_derivation')
+		# ddnode["generation_no"]="0"
+
+		# node << ddnode
+
+  	node
+	end
+
+
+end

data/lib/protk/protxml_writer.rb

@@ -7,12 +7,22 @@ class ProtXMLWriter < Object
 
 	attr :template_doc
 	attr :protein_summary_node
+	XML.indent_tree_output = true
 
 	def initialize
 		template_path="#{File.dirname(__FILE__)}/data/template_prot.xml"
-		template_parser=XML::Parser.file(template_path)
+		template_parser=XML::Parser.file(template_path)#,:options => XML::Parser::Options::NOBLANKS)
 		@template_doc=template_parser.parse
 		@protein_summary_node=@template_doc.root
+		# @protein_summary_node.space_preserve=true
+		@protein_summary_node.content=""
+		puts @template_doc
+
+	end
+
+	def append_header(header_node)
+		# require 'byebug';byebug
+		@protein_summary_node << header_node.as_protxml
 	end
 
 	def append_protein_group(pg_node)
@@ -20,7 +30,17 @@ class ProtXMLWriter < Object
 		@protein_summary_node << pg_node
 	end
 
+	def append_dataset_derivation()
+		ddnode = XML::Node.new('dataset_derivation')
+		ddnode["generation_no"]="0"
+		@protein_summary_node << ddnode
+	end
+
 	def save(file_path)
+		# puts XML.indent_tree_output
+		# puts "|#{XML.default_tree_indent_string}|"
+		XML.indent_tree_output = true
+		# puts @template_doc.to_s
 		@template_doc.save(file_path,:indent=>true,:encoding => XML::Encoding::UTF_8)
 	end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.4.3
+  version: 1.4.4.beta1
 platform: ruby
 authors:
 - Ira Cooke
@@ -299,6 +299,7 @@ files:
 - lib/protk/prophet_tool.rb
 - lib/protk/protein.rb
 - lib/protk/protein_group.rb
+- lib/protk/protein_summary.rb
 - lib/protk/protein_to_genome_mapper.rb
 - lib/protk/protxml_to_gff_tool.rb
 - lib/protk/protxml_writer.rb
@@ -328,9 +329,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - '>'
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
 rubyforge_project: 
 rubygems_version: 2.2.1