protk 1.2.5 → 1.2.6.pre1

data/bin/mascot2xml.rb

@@ -0,0 +1,87 @@
+#!/usr/bin/env ruby
+#
+# This file is part of protk
+# Created by Ira Cooke 12/4/2010
+#
+# Convert mascot dat files to pepxml without using TPP Mascot2XML 
+#
+
+
+require 'protk/constants'
+require 'protk/search_tool'
+require 'mascot/dat'
+require 'libxml'
+
+include LibXML
+
+
+
+
+# Environment with global constants
+#
+genv=Constants.new
+
+tool=SearchTool.new([:database,:explicit_output,:over_write])
+tool.option_parser.banner = "Convert mascot dat files to pep.xml files.\n\nUsage: mascot2xml.rb [options] file1.dat file2.dat ... "
+tool.option_parser.parse!
+
+throw "Only one file at a time is allowed when using explicit output" if (tool.explicit_output && ARGV.length > 1)
+
+def update_msms_pipeline_analysis(pepxml_doc,mascot_dat,outname)
+  pipeline_analysis_node=pepxml_doc.find("//#{$pepxml_ns_prefix}msms_pipeline_analysis", $pepxml_ns)[0]
+  pipeline_analysis_node.attributes['date']=Time.at(mascot_dat.header.date.to_i).to_s
+  pipeline_analysis_node.attributes['summary_xml']=outname
+end
+
+def update_enzyme(pepxml_doc,mascot_dat)
+  dat_enzyme=mascot_dat.enzyme
+  enzyme_node=pepxml_doc.find("//#{$pepxml_ns_prefix}sample_enzyme", $pepxml_ns)[0]
+  enzyme_node.attributes['name']=dat_enzyme.title
+  specificity=enzyme_node.find("./#{$pepxml_ns_prefix}specificity",$pepxml_ns)[0]
+#  p dat_enzyme.cleavages
+  # TODO: What does the spec say about multiple cut sites
+#  specificity.attributes['cut']=
+end
+
+
+
+ARGV.each do |file_name| 
+  name=file_name.chomp
+
+  dat = Mascot::DAT.open(name)
+  pepxml_template_parser=XML::Parser.file("#{genv.data_lib_dir}/pepxml_mascot_template.xml")
+  pepxml_doc = pepxml_template_parser.parse
+
+  outname = nil
+  if ( tool.explicit_output !=nil)
+    outname = tool.explicit_output
+  else
+    basename = Pathname.new(name).basename
+    outname = "#{basename}.pepXML"
+  end
+
+  $pepxml_ns_prefix="xmlns:"
+  $pepxml_ns="xmlns:http://regis-web.systemsbiology.net/pepXML"
+  if not pepxml_doc.root.namespaces.default
+    $pepxml_ns_prefix=""
+    $pepxml_ns=nil
+  end
+
+  update_msms_pipeline_analysis(pepxml_doc,dat,outname)
+  update_enzyme(pepxml_doc,dat)
+
+  spectrum_queries={}
+
+  dat.peptides.each do |psm|
+    # psm.score
+    qnum= psm.query
+    if qnum
+      qid=qnum.to_s
+      spectrum_queries[qid]=[] if ( spectrum_queries[qid]==nil) 
+      spectrum_queries[qid] << psm
+    end
+  end
+
+  spectrum_queries.each_pair { |name, val| p "#{name} #{val[0].pep}" }
+
+end

data/ext/protk/simplealign/simplealign.c

@@ -0,0 +1,17 @@
+
+
+static VALUE simplealign_align (VALUE self, VALUE pep_in, VALUE n_in, VALUE gene_in,VALUE m_in)
+{
+  unsigned int n = NUM2INT(n_in);
+  unsigned int m = NUM2INT(m_in);
+
+  char *peptide = RSTRING_PTR(pep_in);
+  char *gene = RSTRING_PTR(gene_in);
+}
+void Init_simplealign(void)
+{
+  VALUE klass = rb_define_class("SimpleAlign",rb_cObject);
+
+  rb_define_singleton_method(klass,
+    "align",simplealign_align , 9);
+}

data/lib/protk/constants.rb

@@ -236,10 +236,13 @@ class Constants
       @protk_dir=ENV['PROTK_INSTALL_DIR']
     end
 
-
+    # Protk Defaults
+    #
     default_config_yml = YAML.load_file "#{File.dirname(__FILE__)}/data/default_config.yml"
     throw "Unable to read the config file at #{File.dirname(__FILE__)}/data/default_config.yml" unless default_config_yml!=nil
 
+    # User-defined defaults override protk defaults
+    #
     user_config_yml = nil
     user_config_yml = YAML.load_file "#{@protk_dir}/config.yml" if File.exist? "#{@protk_dir}/config.yml"
     if ( user_config_yml !=nil )
@@ -248,11 +251,22 @@ class Constants
       @env=default_config_yml
     end
 
-    protk_roots = ["tpp","omssa","blast","pwiz","msgfplus","openms"]
+    # Application installation directories. From environment variables
+    #
+    protk_roots = [["tpp","xinteract"],["omssa","omssacl"],["blast","blastdbcmd"],["pwiz","msconvert"],["msgfplus",""],["openms","ExecutePipeline"]]
 
-    protk_roots.each do |r|  
+    protk_roots.each do |r,binaryname|  
       env_value = ENV["PROTK_#{r.upcase}_ROOT"]
       if ( env_value!=nil)
+        # "FROMPATH" means detect the root value
+        if env_value=="FROMPATH"
+          bin_path=Pathname.new(%x[which #{binaryname}].chomp)
+          if bin_path.exist?
+            env_value=bin_path.realpath.dirname.to_s
+          else
+            env_value=""
+          end
+        end
         p "Using #{r} root #{env_value}"
         @env["#{r}_root"]=env_value
       end

data/lib/protk/data/pepxml_mascot_template.xml

@@ -0,0 +1,29 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-stylesheet type="text/xsl" href="/home/iracooke/.protk/tools/tpp/schema/pepXML_std.xsl"?>
+<msms_pipeline_analysis date="2013-01-07T18:29:15" xmlns="http://regis-web.systemsbiology.net/pepXML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://regis-web.systemsbiology.net/pepXML /home/iracooke/.protk/tools/tpp/schema/pepXML_v117.xsd" summary_xml="/home/iracooke/FionaHela/mr176/mr176-HeLa4hrx2_GC1_01_8136.d_mascot2xml.pep.xml">
+  <msms_run_summary base_name="/home/iracooke/FionaHela/mr176/mr176-HeLa4hrx2_GC1_01_8136.d_mascot2xml" raw_data_type="raw" raw_data="(null)">
+<sample_enzyme name="trypsin">
+<specificity cut="KR" no_cut="P" sense="C"/>
+</sample_enzyme>
+<search_summary base_name="/home/iracooke/FionaHela/mr176/mr176-HeLa4hrx2_GC1_01_8136.d_mascot2xml" search_engine="MASCOT" precursor_mass_type="monoisotopic" fragment_mass_type="monoisotopic" search_id="1">
+<search_database local_path="/home/iracooke/.protk/Databases/sphuman/current.fasta" type="AA"/>
+<enzymatic_search_constraint enzyme="trypsin" max_num_internal_cleavages="2" min_number_termini="2"/>
+<aminoacid_modification aminoacid="C" massdiff="57.0215" mass="160.0306" variable="N"/>
+<parameter name="" value=""/>
+</search_summary>
+    <spectrum_query spectrum="" start_scan="" end_scan="" precursor_neutral_mass="" assumed_charge="" index="">
+    <search_result>
+      <search_hit hit_rank="" peptide="" peptide_prev_aa="" peptide_next_aa="" protein="" num_tot_proteins="" num_matched_ions="" tot_num_ions="" calc_neutral_pep_mass="" massdiff="" num_tol_term="" num_missed_cleavages="" is_rejected="">
+<modification_info>
+<mod_aminoacid_mass position="" mass=""/>
+</modification_info>
+        <search_score name="ionscore" value=""/>
+        <search_score name="identityscore" value=""/>
+        <search_score name="star" value="0"/>
+        <search_score name="homologyscore" value=""/>
+        <search_score name="expect" value=""/>
+      </search_hit>
+    </search_result>
+    </spectrum_query>
+  </msms_run_summary>
+</msms_pipeline_analysis>

data/lib/protk/data/predefined_db.trembl_annotation.yaml

@@ -0,0 +1,20 @@
+#
+# This is a predefined setup file for manage_db 
+#
+# Swissprot_uniprot annotation database (full entries for each protein)
+#
+--- 
+:description: Swissprot Trembl annotation database (full entries for each protein)
+:archive_old: false
+:is_annotation_db: true
+:decoy_prefix: decoy_
+:include_filters: []
+
+:format: dat
+:id_regexes: []
+
+:make_blast_index: false
+:sources: 
+- - ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.dat.gz
+  - ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/reldate.txt
+:decoys: false

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.2.5
-  prerelease: 
+  version: 1.2.6.pre1
+  prerelease: 6
 platform: ruby
 authors:
 - Ira Cooke
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-06 00:00:00.000000000 Z
+date: 2013-10-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ftools
@@ -256,6 +256,7 @@ files:
 - bin/libra.rb
 - bin/make_decoy.rb
 - bin/manage_db.rb
+- bin/mascot2xml.rb
 - bin/mascot_search.rb
 - bin/mascot_to_pepxml.rb
 - bin/msgfplus_search.rb
@@ -283,10 +284,12 @@ files:
 - lib/protk/data/FeatureFinderCentroided.ini
 - lib/protk/data/FeatureFinderIsotopeWavelet.ini
 - lib/protk/data/galaxyenv.sh
+- lib/protk/data/pepxml_mascot_template.xml
 - lib/protk/data/predefined_db.crap.yaml
 - lib/protk/data/predefined_db.sphuman.yaml
 - lib/protk/data/predefined_db.swissprot_annotation.yaml
 - lib/protk/data/predefined_db.swissprot_fasta_annotation.yaml
+- lib/protk/data/predefined_db.trembl_annotation.yaml
 - lib/protk/data/tandem_params.xml
 - lib/protk/data/taxonomy_template.xml
 - lib/protk/data/unimod.xml
@@ -295,6 +298,7 @@ files:
 - lib/protk/data/uniprot_input_accessions.loc
 - lib/protk/data/yum_packages.yaml
 - ext/protk/decoymaker/decoymaker.c
+- ext/protk/simplealign/simplealign.c
 - ext/protk/decoymaker/extconf.rb
 - ext/protk/simplealign/extconf.rb
 homepage: http://rubygems.org/gems/protk
@@ -313,9 +317,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
-  - - ! '>='
+  - - ! '>'
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.24
@@ -323,3 +327,4 @@ signing_key:
 specification_version: 3
 summary: Proteomics Toolkit
 test_files: []
+has_rdoc: