protk 1.2.4 → 1.2.5

data/lib/protk/manage_db_rakefile.rake

@@ -449,7 +449,8 @@ file db_filename do
 
     # Symlink to the source file
     #
-    File.symlink(source_db_filename,db_filename)
+    source_db_filename_relative = Pathname.new(source_db_filename).basename.to_s
+    File.symlink(source_db_filename_relative,db_filename)
   end
 end
 

data/lib/protk/mascot_util.rb

@@ -54,12 +54,17 @@ class MascotUtil
 
      if ( spec!=nil && rt!=nil)
        # Remove charge from the end of the title
-       spec_id= remove_charge_from_title_string(spec[1])
+       # spec_id= remove_charge_from_title_string(spec[1])
+       spec_id= spec[1]
+
+    #   $stdout.write "#{spec_id} \r"
+
        
        rt_table[spec_id]=rt[1]
      end
-     
+
    end
+#    $stdout.write "\n"
 
    return rt_table
     

data/lib/protk/randomize.rb

@@ -1,7 +1,7 @@
-require 'protk/protk'
+require 'protk/decoymaker'
 
 class Randomize
 	def self.make_decoys input_path, db_len, output_path, prefix
-		Protk.make_decoys input_path.to_s, db_len.to_i,  output_path.to_s, prefix.to_s
+		Decoymaker.make_decoys input_path.to_s, db_len.to_i,  output_path.to_s, prefix.to_s
 	end
 end

data/lib/protk/search_tool.rb

@@ -154,7 +154,7 @@ class SearchTool < Tool
   
   def jobid_from_filename(filename)
     jobid="protk"
-    jobnum_match=filename.match(/(.{1,10})\.d/)
+    jobnum_match=filename.match(/(.{1,10}).*?\./)
     if (jobnum_match!=nil)
       jobid="#{self.jobid_prefix}#{jobnum_match[1]}"
     end

data/lib/protk/setup_rakefile.rake

@@ -133,10 +133,10 @@ task :perl_locallib => [perl_locallib_installed_file]
 #
 # TPP
 #
-tpp_version="4.6.1"
+tpp_version="4.6.2"
 tpp_packagefile="TPP-#{tpp_version}.tgz"
 tpp_installed_file = "#{env.xinteract}"
-tpp_url = "https://dl.dropbox.com/u/226794/TPP-4.6.1.tgz"
+tpp_url = "https://dl.dropbox.com/u/226794/TPP-4.6.2.tgz"
 
 tpp_download_file = download_task tpp_url, tpp_packagefile
 
@@ -380,6 +380,29 @@ end
 
 task :galaxyenv => protk_galaxy_envfile
 
+
+#
+# NCBI GI and Taxonomy Databases
+#
+
+# gi_taxid_package_file="gi_taxid_prot.zip"
+# gi_taxid_url="ftp://ftp.ncbi.nih.gov/pub/taxonomy/#{gi_taxid_package_file}"
+# gi_taxid_installed_file=
+
+# file "gi_taxid_prot.zip" do
+#         %x[wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/gi_taxid_prot.zip]
+#         %x[unzip gi_taxid_prot.zip]
+# end
+
+# file "taxdmp.zip" do
+#         %x[wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdmp.zip]
+#         %x[unzip taxdmp.zip]
+# end
+
+
+# multitask :downloads => FileList["nr","env_nr","gi_taxid_prot.zip","taxdmp.zip"]
+
+
 task :all => [:tpp,:omssa,:blast,:msgfplus,:pwiz,:openms,:galaxyenv]
 
 # Special task when installing via toolshed

data/lib/protk/spreadsheet_extensions.rb

@@ -1,3 +1,4 @@
+require 'spreadsheet'
 # Add a method to the Spreadsheet::Worksheet class to insert a column
 class Spreadsheet::Worksheet < Object
     def insert_column(col,index)

data/lib/protk/swissprot_database.rb

@@ -1,6 +1,7 @@
 require 'rubygems'
 require 'bio'
 require 'protk/constants'
+require 'pathname'
 
 # Provides fast indexed access to a swissprot database in a flat .dat file
 #
@@ -13,7 +14,16 @@ class SwissprotDatabase
       @genv=Constants.new
     end
 
-    if ( database=="swissprot")
+
+    dbpath=Pathname.new(database)
+
+    if ( dbpath.exist? )
+#      require 'debugger';debugger
+      dbclass=Bio::SPTR
+      parser = Bio::FlatFileIndex::Indexer::Parser.new(dbclass, nil, nil)
+      Bio::FlatFileIndex::Indexer::makeindexFlat(dbpath.realpath.dirname.to_s, parser, {}, dbpath.realpath.to_s)
+      @db_object=Bio::FlatFileIndex.new("#{dbpath.realpath.dirname.to_s}")
+    elsif ( database=="swissprot")
       @db_object=Bio::FlatFileIndex.new("#{@genv.protein_database_root}/#{@genv.uniprot_sprot_annotation_database}")
     else
       @db_object=Bio::FlatFileIndex.new("#{@genv.protein_database_root}/#{@genv.uniprot_trembl_annotation_database}")

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.2.4
+  version: 1.2.5
   prerelease: 
 platform: ruby
 authors:
@@ -139,6 +139,22 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: 0.3.1
+- !ruby/object:Gem::Dependency
+  name: bio-blastxmlparser
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.1.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.1.1
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -172,6 +188,7 @@ executables:
 - make_decoy.rb
 - correct_omssa_retention_times.rb
 - repair_run_summary.rb
+- add_retention_times.rb
 - peptide_prophet.rb
 - interprophet.rb
 - protein_prophet.rb
@@ -185,10 +202,13 @@ executables:
 - toppas_pipeline.rb
 - gffmerge.rb
 - sixframe.rb
+- augustus_to_proteindb.rb
+- protxml_to_gff.rb
 - uniprot_annotation.rb
 - protxml_to_table.rb
+- blastxml_to_table.rb
 extensions:
-- ext/protk/extconf.rb
+- ext/protk/decoymaker/extconf.rb
 extra_rdoc_files: []
 files:
 - lib/protk/bio_sptr_extensions.rb
@@ -201,6 +221,7 @@ files:
 - lib/protk/fastadb.rb
 - lib/protk/galaxy_stager.rb
 - lib/protk/galaxy_util.rb
+- lib/protk/gapped_aligner.rb
 - lib/protk/manage_db_tool.rb
 - lib/protk/mascot_util.rb
 - lib/protk/omssa_util.rb
@@ -221,8 +242,11 @@ files:
 - lib/protk.rb
 - lib/protk/manage_db_rakefile.rake
 - lib/protk/setup_rakefile.rake
+- bin/add_retention_times.rb
 - bin/annotate_ids.rb
 - bin/asapratio.rb
+- bin/augustus_to_proteindb.rb
+- bin/blastxml_to_table.rb
 - bin/correct_omssa_retention_times.rb
 - bin/feature_finder.rb
 - bin/file_convert.rb
@@ -232,7 +256,6 @@ 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
@@ -241,6 +264,7 @@ files:
 - bin/pepxml_to_table.rb
 - bin/protein_prophet.rb
 - bin/protk_setup.rb
+- bin/protxml_to_gff.rb
 - bin/protxml_to_table.rb
 - bin/repair_run_summary.rb
 - bin/sixframe.rb
@@ -259,12 +283,10 @@ 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
@@ -272,8 +294,9 @@ files:
 - lib/protk/data/uniprot_accessions_table.txt
 - lib/protk/data/uniprot_input_accessions.loc
 - lib/protk/data/yum_packages.yaml
-- ext/protk/protk.c
-- ext/protk/extconf.rb
+- ext/protk/decoymaker/decoymaker.c
+- ext/protk/decoymaker/extconf.rb
+- ext/protk/simplealign/extconf.rb
 homepage: http://rubygems.org/gems/protk
 licenses: []
 post_install_message: Now run protk_setup.rb to install third party tools and manage_db.rb
@@ -300,4 +323,3 @@ signing_key:
 specification_version: 3
 summary: Proteomics Toolkit
 test_files: []
-has_rdoc: 

data/bin/mascot2xml.rb

@@ -1,87 +0,0 @@
-#!/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/extconf.rb

@@ -1,3 +0,0 @@
-require 'mkmf'
-
-create_makefile('protk/protk')

data/lib/protk/data/pepxml_mascot_template.xml

@@ -1,29 +0,0 @@
-<?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

@@ -1,20 +0,0 @@
-#
-# 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