protk 1.1.0.pre → 1.1.0

data/lib/protk/galaxy_util.rb

@@ -1,9 +1,46 @@
+require 'protk/pepxml'
+require 'protk/galaxy_stager'
+require 'protk/galaxy_util'
+require 'protk/convert_util'
+require 'fileutils'
+
 class GalaxyUtil
 
-  def self.for_galaxy
+  def self.for_galaxy?
     for_galaxy = ARGV[0] == "--galaxy"
     ARGV.shift if for_galaxy
     return for_galaxy
   end
 
-end
+
+  def self.stage_protxml(input_protxml_path)
+    # This method takes in the path to a protxml created in Galaxy,
+    # finds the dependent pepxml and peak lists (mzml files), creates
+    # symbolic links to the peak lists with the correct extension and
+    # and indexes them if needed (both seem required for TPP quant
+    # tools) and then produces new protxml and pepxml files with paths
+    # updated to these new peak list files.
+
+    protxml_path="interact.prot.xml"
+    FileUtils.copy(input_protxml_path, "interact.prot.xml")
+
+    protxml = ProtXML.new(protxml_path)
+    pepxml_path = protxml.find_pep_xml()
+
+    protxml_stager = GalaxyStager.new(protxml_path, :extension => ".prot.xml", :force_copy => true)
+    pepxml_stager = GalaxyStager.new(pepxml_path, :name => "interact", :extension => ".xml", :force_copy => true)
+    pepxml_path = pepxml_stager.staged_path
+    pepxml_stager.replace_references(protxml_path)
+    runs = PepXML.new(pepxml_stager.staged_path).find_runs()
+  
+    run_stagers = runs.map do |base_name, run|
+      run_stager = GalaxyStager.new(base_name, :extension => ".#{run[:type]}")
+      ConvertUtil.ensure_mzml_indexed(run_stager.staged_path)
+      run_stager.replace_references(pepxml_path, :base_only => true)
+      run_stager
+    end
+
+    protxml_path
+  end
+
+end

data/lib/protk/manage_db_rakefile.rake

@@ -35,6 +35,7 @@ def check_ftp_release_notes(release_notes)
 
   rn_path="#{$genv.database_downloads}/#{rn_uri.host}/#{rn_uri.path}"
 
+  update_needed=false
 
   host=rn_uri.host
   Net::FTP.open(host) do |ftp|
@@ -104,10 +105,12 @@ def check_ftp_release_notes(release_notes)
     when ( existing_digest != rn_digest )
       FileUtils.mkpath(Pathname.new(rn_path).dirname.to_s)
       File.open(rn_path, "w") {|file| file.puts(rn_data) }
+      update_needed = true
     else
       p "Release notes are up to date"
-    end  
+    end 
   end
+  update_needed
 end
 
 def download_ftp_file(ftp,file_name,dest_dir)
@@ -216,16 +219,23 @@ def ftp_source(ftpsource)
 
   release_notes_url=ftpsource[1]
   release_notes_exist=true
-  release_notes_exist=false if release_notes_url =~ /^\s*none\s*$/
+  release_notes_exist=false if (release_notes_url =~ /^\s*none\s*$/) || (release_notes_url==nil)
+
+  release_notes_show_update_needed = true
+
   if release_notes_exist
-    data_rn=URI.parse(release_notes_url) unless 
-    release_notes_file_path="#{$genv.database_downloads}/#{data_rn.host}/#{data_rn.path}"
 
-    task :check_rn do
-      check_ftp_release_notes(release_notes_url) 
-    end
+    data_rn=URI.parse(release_notes_url)
+
+    if ( data_rn != nil )
+      release_notes_file_path="#{$genv.database_downloads}/#{data_rn.host}/#{data_rn.path}"
 
-    file release_notes_file_path => :check_rn
+      task :check_rn do
+        release_notes_show_update_needed = check_ftp_release_notes(release_notes_url) 
+      end
+
+      file release_notes_file_path => :check_rn
+    end
   else
     task :check_date do
 
@@ -233,38 +243,41 @@ def ftp_source(ftpsource)
   end
 
   
-  
   if ( data_file_path=~/\*/) # A wildcard
     unpacked_data_path=data_file_path.gsub(/\*/,"_all_").gsub(/\.gz$/,'')
   end
 
-  file unpacked_data_path  do #Unpacking. Includes unzipping and/or concatenating
-    download_ftp_source(ftpsource[0])
+  task unpacked_data_path  do #Unpacking. Includes unzipping and/or concatenating
+      if ( release_notes_show_update_needed )
+        download_ftp_source(ftpsource[0])
+        file_pattern = Pathname.new(data_file_path).basename.to_s        
 
-    case
-    when data_file_path=~/\*/ # Multiple files to unzip/concatenate and we don't know what they are yet
-      file_pattern = Pathname.new(data_file_path).basename.to_s
-      if file_pattern =~ /.gz$/
-        unzipcmd="gunzip -vdf #{file_pattern}"
-        p "Unzipping #{unzipcmd} ... this could take a while"
-        sh %{ cd #{Pathname.new(data_file_path).dirname}; #{unzipcmd}  }             
-      end
+        case
+
+      when data_file_path=~/\*/ # Multiple files to unzip/concatenate and we don't know what they are yet
 
-      file_pattern.gsub!(/\.gz$/,'')
-      catcmd="cat #{file_pattern} > #{unpacked_data_path}"
+        if file_pattern =~ /.gz$/
+          unzipcmd="gunzip -vdf #{file_pattern}"
+          p "Unzipping #{unzipcmd} ... this could take a while"
+          sh %{ cd #{Pathname.new(data_file_path).dirname}; #{unzipcmd}  }             
+        end
+
+        file_pattern.gsub!(/\.gz$/,'')
+        catcmd="cat #{file_pattern} > #{unpacked_data_path}"
       
-      p "Concatenating files #{catcmd} ... this could take a while"
-      sh %{ cd #{Pathname.new(data_file_path).dirname}; #{catcmd}  }
+        p "Concatenating files #{catcmd} ... this could take a while"
+        sh %{ cd #{Pathname.new(data_file_path).dirname}; #{catcmd}  }
       
-    else # Simple case. A single file 
-      if file_pattern =~ /.gz$/
-        p "Unzipping #{Pathname.new(data_file_path).basename} ... "
-        sh %{ cd #{Pathname.new(data_file_path).dirname}; gunzip -f #{Pathname.new(data_file_path).basename}  }           
+      else # Simple case. A single file 
+        if file_pattern =~ /.gz$/
+          p "Unzipping #{Pathname.new(data_file_path).basename} ... "
+          sh %{ cd #{Pathname.new(data_file_path).dirname}; gunzip -f #{Pathname.new(data_file_path).basename}  }           
+        end
       end
     end
   end
 
-  task release_notes_file_path => release_notes_file_path if release_notes_exist
+  file unpacked_data_path => release_notes_file_path if release_notes_exist
 
   unpacked_data_path
 end
@@ -380,8 +393,8 @@ file decoy_db_filename => raw_db_filename do
   
   p "Generating decoy sequences ... this could take a while"  
   # Make decoys, concatenate and delete decoy only file
-  Randomize.make_decoys #{raw_db_filename} #{db_length} #{decoys_filename} #{decoy_prefix}"
-  cmd << "cat #{raw_db_filename} #{decoys_filename} >> #{decoy_db_filename}; rm #{decoys_filename}"
+  Randomize.make_decoys raw_db_filename, db_length, decoys_filename, decoy_prefix
+  cmd = "cat #{raw_db_filename} #{decoys_filename} >> #{decoy_db_filename}; rm #{decoys_filename}"
   sh %{ #{cmd} }
 end
 

data/lib/protk/pepxml.rb

@@ -0,0 +1,22 @@
+require 'rubygems'
+require 'rexml/document'
+require 'rexml/xpath'
+
+class PepXML
+  def initialize(file_name)
+    @doc=REXML::Document.new(File.new(file_name))
+  end
+
+  def find_runs() 
+    runs = {}
+    REXML::XPath.each(@doc,"//msms_run_summary") do |summary|
+      base_name = summary.attributes["base_name"]
+      if not runs.has_key?(base_name)
+        runs[base_name] = {:base_name => summary.attributes["base_name"],
+                           :type => summary.attributes["raw_data"]}
+      end
+    end
+    runs
+  end
+  
+end

data/lib/protk/protxml.rb

@@ -2,7 +2,6 @@ require 'rubygems'
 require 'rexml/document'
 require 'rexml/xpath'
 
-
 class ProtXML 
     
   attr_accessor :groups
@@ -60,6 +59,11 @@ class ProtXML
     @doc=REXML::Document.new(File.new(file_name))
     @groups=self.init_groups
   end
+
+  def find_pep_xml()
+    header = REXML::XPath.first(@doc, "//protein_summary_header")
+    source_file = header.attributes["source_files"]
+  end
   
   def peptide_sequences_from_protein(prot)
     peptides=prot[:peptides]

data/lib/protk/setup_rakefile.rake

@@ -11,10 +11,18 @@ directory @build_dir
 directory @download_dir
 
 def package_manager_name 
-	if RbConfig::CONFIG['host_os'] =~ /darwin/ 
-		return 'brew'
+	package_managers = ["brew","yum","apt-get"]
+
+	package_managers.each do |pmname|  
+		if supports_package_manager pmname
+			return pmname
+		end
 	end
-	'apt-get'
+end
+
+def supports_package_manager name
+	res = %x[which #{name}]
+	(res == "")
 end
 
 def clean_build_dir
@@ -105,6 +113,9 @@ file perl_locallib_installed_file =>  [@build_dir,"#{@download_dir}/#{perl_local
 	if !Pathname.new("~/.bash_profile").exist? || File.read("~/.bash_profile") =~ /Mlocal::lib/
 		sh "echo 'eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir})' >>~/.bash_profile"
 	end
+
+	sh "eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir})"
+	sh "curl -L http://cpanmin.us | perl - --self-upgrade"
 end
 
 task :perl_locallib => [perl_locallib_installed_file]
@@ -129,7 +140,7 @@ download_task tpp_url, tpp_packagefile
 file tpp_installed_file => [:perl_locallib,@build_dir,"#{@download_dir}/#{tpp_packagefile}"] do
 	sh %{cp #{@download_dir}/#{tpp_packagefile} #{@build_dir}}
 	sh %{cpanm --local-lib=#{env.protk_dir}/perl5 XML::Parser}
-	sh %{cpanm --local-lib=#{env.protk_dir}/perl5 XML::CGI --force}
+	sh %{cpanm --local-lib=#{env.protk_dir}/perl5 CGI --force}
 
 	sh %{cd #{@build_dir};tar -xvzf TPP-#{tpp_version}.tgz}
 
@@ -226,9 +237,9 @@ task :blast => blast_installed_file
 #
 # MSGFPlus
 #
-msgfplus_version="20120823"
-msgfplus_packagefile="MSGFPlus.20120823.zip"
-msgfplus_url="http://proteomics.ucsd.edu/Downloads/MSGFPlus.20120823.zip"
+msgfplus_version="20121116"
+msgfplus_packagefile="MSGFPlus.#{msgfplus_version}.zip"
+msgfplus_url="http://proteomics.ucsd.edu/Downloads/MSGFPlus.#{msgfplus_version}.zip"
 msgfplus_installed_file="#{env.msgfplusjar}"
 
 download_task msgfplus_url, msgfplus_packagefile
@@ -242,4 +253,40 @@ end
 
 task :msgfplus => msgfplus_installed_file
 
-task :all => [:tpp,:omssa,:blast]
+#
+# pwiz
+#
+def pwiz_platform 
+	if RbConfig::CONFIG['host_os'] =~ /darwin/ 
+		return 'darwin-x86-xgcc40'
+	end
+	'linux-x86_64-gcc42'
+end
+
+def platform_bunzip
+	if RbConfig::CONFIG['host_os'] =~ /darwin/ 
+		return 'pbunzip2'
+	end
+	'bunzip2'
+end
+
+pwiz_version="3_0_4146"
+pwiz_packagefile="pwiz-bin-#{pwiz_platform}-release-#{pwiz_version}.tar.bz2"
+pwiz_url="https://dl.dropbox.com/u/226794/#{pwiz_packagefile}"
+pwiz_installed_file="#{env.idconvert}"
+
+download_task pwiz_url, pwiz_packagefile
+
+file pwiz_installed_file => [@build_dir,"#{@download_dir}/#{pwiz_packagefile}"] do 
+	sh %{cp #{@download_dir}/#{pwiz_packagefile} #{@build_dir}}
+    sh %{cd #{@build_dir}; #{platform_bunzip} -f #{pwiz_packagefile}}
+    sh %{cd #{@build_dir}; tar -xvf #{pwiz_packagefile.chomp('.bz2')}}
+    sh %{mkdir -p #{env.pwiz_root}}
+    sh %{cd #{@build_dir}; cp idconvert msconvert #{env.pwiz_root}/}
+end
+
+task :pwiz => pwiz_installed_file
+
+task :all => [:tpp,:omssa,:blast,:msgfplus,:pwiz]
+
+

data/lib/protk/swissprot_database.rb

@@ -16,7 +16,7 @@ class SwissprotDatabase
     if ( 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}")
+      @db_object=Bio::FlatFileIndex.new("#{@genv.protein_database_root}/#{@genv.uniprot_trembl_annotation_database}")
     end
     
     @db_object.always_check_consistency=false

data/lib/protk/uniprot_mapper.rb

@@ -0,0 +1,47 @@
+require 'rubygems'
+require 'net/http'
+require 'protk/constants'
+
+# Provides access to uniprot.org via its API
+# See docs and examples here http://www.uniprot.org/faq/28#id_mapping_examples
+#
+class UniprotMapper
+
+  def initialize
+    @genv = Constants.new
+  end
+
+  def map(from_id_type,from_ids,output_id)
+
+    from_query = from_ids.join(" ")
+
+    base = 'www.uniprot.org'
+    tool = 'mapping'
+    params = {
+      'from' => from_id_type, 'to' => output_id, 'format' => 'tab',
+      'query' => from_query
+    }
+
+    http = Net::HTTP.new base
+    @genv.log "Mapping to #{output_id}" ,:info
+    response = http.request_post '/' + tool + '/',
+    params.keys.map {|key| key + '=' + params[key]}.join('&')
+
+    loc = nil
+    while response.code == '302'
+      loc = response['Location']
+      response = http.request_get loc
+    end
+
+    while loc
+      wait = response['Retry-After'] or break
+      @genv.log "Waiting (#{wait})..." , :info
+      sleep wait.to_i
+      response = http.request_get loc
+    end
+
+    response.value # raises http error if not 2xx
+    return response.body
+  end
+
+end

data/lib/protk.rb

@@ -16,3 +16,4 @@ require 'protk/constants.rb'
 require 'protk/command_runner.rb'
 require 'protk/biotools_excel_converter.rb'
 require 'protk/bio_sptr_extensions.rb'
+require 'protk/galaxy_stager.rb'

metadata

@@ -1,8 +1,8 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.1.0.pre
-  prerelease: 6
+  version: 1.1.0
+  prerelease: 
 platform: ruby
 authors:
 - Ira Cooke
@@ -144,6 +144,9 @@ email: iracooke@gmail.com
 executables:
 - protk_setup.rb
 - manage_db.rb
+- asapratio.rb
+- libra.rb
+- xpress.rb
 - tandem_search.rb
 - mascot_search.rb
 - omssa_search.rb
@@ -162,6 +165,7 @@ executables:
 - annotate_ids.rb
 - unimod_to_loc.rb
 - generate_omssa_loc.rb
+- uniprot_mapper.rb
 extensions:
 - ext/protk/extconf.rb
 extra_rdoc_files: []
@@ -171,12 +175,15 @@ files:
 - lib/protk/biotools_excel_converter.rb
 - lib/protk/command_runner.rb
 - lib/protk/constants.rb
+- lib/protk/convert_util.rb
+- lib/protk/data/make_uniprot_table.rb
 - lib/protk/eupathdb_gene_information_table.rb
 - lib/protk/galaxy_stager.rb
 - lib/protk/galaxy_util.rb
 - lib/protk/manage_db_tool.rb
 - lib/protk/mascot_util.rb
 - lib/protk/omssa_util.rb
+- lib/protk/pepxml.rb
 - lib/protk/plasmodb.rb
 - lib/protk/prophet_tool.rb
 - lib/protk/protein_annotator.rb
@@ -187,18 +194,21 @@ files:
 - lib/protk/spreadsheet_extensions.rb
 - lib/protk/swissprot_database.rb
 - lib/protk/tool.rb
+- lib/protk/uniprot_mapper.rb
 - lib/protk/xtandem_defaults.rb
 - lib/protk.rb
 - lib/protk/big_search_rakefile.rake
 - lib/protk/manage_db_rakefile.rake
 - lib/protk/setup_rakefile.rake
 - bin/annotate_ids.rb
+- bin/asapratio.rb
 - bin/big_search.rb
 - bin/correct_omssa_retention_times.rb
 - bin/feature_finder.rb
 - bin/file_convert.rb
 - bin/generate_omssa_loc.rb
 - bin/interprophet.rb
+- bin/libra.rb
 - bin/make_decoy.rb
 - bin/manage_db.rb
 - bin/mascot_search.rb
@@ -213,7 +223,9 @@ files:
 - bin/tandem_search.rb
 - bin/template_search.rb
 - bin/unimod_to_loc.rb
+- bin/uniprot_mapper.rb
 - bin/xls_to_table.rb
+- bin/xpress.rb
 - README.md
 - lib/protk/data/apt-get_packages.yaml
 - lib/protk/data/brew_packages.yaml
@@ -226,6 +238,10 @@ files:
 - lib/protk/data/tandem_params.xml
 - lib/protk/data/taxonomy_template.xml
 - lib/protk/data/unimod.xml
+- lib/protk/data/uniprot_accessions.loc
+- 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
 homepage: http://rubygems.org/gems/protk
@@ -244,9 +260,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
-  - - ! '>'
+  - - ! '>='
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.24