protk 1.2.1 → 1.2.2

data/bin/tandem_search.rb

@@ -20,7 +20,10 @@ genv=Constants.new
 
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
-search_tool=SearchTool.new({:msms_search=>true,:background=>true,:glyco=>true,:database=>true,:explicit_output=>true,:over_write=>true,:msms_search_detailed_options=>true})
+search_tool=SearchTool.new([:background,:glyco,:database,:explicit_output,:over_write,
+:enzyme,:modifications,:mass_tolerance_units,:mass_tolerance,:strict_monoisotopic_mass,
+:missed_cleavages,:carbamidomethyl,:methionine_oxidation
+  ])
 search_tool.jobid_prefix="x"
 search_tool.option_parser.banner = "Run an X!Tandem msms search on a set of mzML input files.\n\nUsage: tandem_search.rb [options] file1.mzML file2.mzML ..."
 search_tool.options.output_suffix="_tandem"
@@ -94,7 +97,13 @@ search_tool.option_parser.on('--cleavage-c-terminal-mod-mass mass') do |mass|
     search_tool.options.cleavage_c_terminal_mod_mass = mass
 end
 
-search_tool.option_parser.parse!
+exit unless search_tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts search_tool.option_parser 
+    exit
+end
 
 
 # Set search engine specific parameters on the SearchTool object

data/bin/toppas_pipeline.rb

@@ -15,7 +15,7 @@ require 'libxml'
 
 include LibXML
 
-tool=Tool.new({:explicit_output=>false, :background=>true,:over_write=>false})
+tool=Tool.new([:explicit_output, :background,:over_write])
 tool.option_parser.banner = "Execute a toppas pipeline with a single inputs node\n\nUsage: toppas_pipeline.rb [options] input1 input2 ..."
 
 tool.options.outdir = ""
@@ -28,7 +28,13 @@ tool.option_parser.on( '--toppas-file f',"the toppas file to run" ) do |file|
   tool.options.toppas_file = file
 end
 
-tool.option_parser.parse!
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
 
 # Obtain a global environment object
 genv=Constants.new

data/bin/uniprot_annotation.rb

@@ -15,7 +15,7 @@ require 'protk/bio_sptr_extensions'
 
 # Setup specific command-line options for this tool. Other options are inherited from Tool
 #
-tool=Tool.new({:explicit_output=>true})
+tool=Tool.new([:explicit_output])
 tool.option_parser.banner = "Retrieve information from the Uniprot database given a list of ID's.\n\n\
 Usage: uniprot_annotation.rb [options] input.tsv"
 
@@ -29,7 +29,13 @@ tool.option_parser.on(  '--fields flds', 'A comma separated list of fields to ex
   tool.options.fields=flds
 end
 
-tool.option_parser.parse!
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
 
 # Obtain a global environment object
 genv=Constants.new

data/bin/uniprot_mapper.rb

@@ -13,7 +13,7 @@ require 'protk/uniprot_mapper'
 
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
-tool=Tool.new({:explicit_output=>true})
+tool=Tool.new([:explicit_output])
 
 tool.options.id_column=1
 tool.option_parser.on(  '--id-column num', 'Specify a column for ids (default is column 1)' ) do |col|
@@ -27,7 +27,13 @@ end
 
 tool.option_parser.banner = "Given a set of IDs convert them to a different type of ID\n\nUsage: uniprot_mapper.rb input_file.txt fromID_type"
 
-tool.option_parser.parse!
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
 
 
 from_file=ARGV.shift

data/bin/xls_to_table.rb

@@ -14,10 +14,16 @@ require 'spreadsheet'
 
 # Setup command-line options for this tool. 
 #
-tool=Tool.new({:explicit_output=>true})
+tool=Tool.new([:explicit_output])
 tool.option_parser.banner = "Convert an xls file to a tab delimited table.\n\nUsage: xls_to_table.rb [options] file1.xls"
 
-tool.option_parser.parse!
+exit unless tool.check_options 
+
+if ( ARGV[0].nil? )
+    puts "You must supply an input file"
+    puts tool.option_parser 
+    exit
+end
 
 input_file=ARGV[0]
 

data/lib/protk/constants.rb

@@ -29,6 +29,7 @@ class Constants
 
   attr :info_level
   attr :protk_dir
+  attr :data_lib_dir
 
   # Provides direct access to constants through methods of the same name
   # This will be used for all constants other than paths
@@ -227,6 +228,7 @@ class Constants
   #
   def initialize 
 
+    @data_lib_dir="#{File.dirname(__FILE__)}/data"
     @protk_dir="#{Dir.home}/.protk"
 
     if ( ENV['PROTK_INSTALL_DIR']!=nil )

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/mascot_util.rb

@@ -23,6 +23,7 @@ class MascotUtil
   end
   
   def self.remove_charge_from_title_string(tstring)
+
     if ( tstring=~/(.*)\..*?\..*?\.$/)
       return tstring.chop
     end
@@ -30,6 +31,10 @@ class MascotUtil
     if ( tstring=~/(.*)\..*?\..*?\.\d$/)
       return tstring.chop!.chop
     end
+
+    if ( tstring=~/(.*)\..*?\..*?$/)
+      return tstring
+    end    
     
     throw "Unrecognised title string format #{tstring}"
     

data/lib/protk/prophet_tool.rb

@@ -17,9 +17,7 @@ class ProphetTool < SearchTool
 
 
   # Initializes the commandline options
-  def initialize(option_support={})
-    option_support[:prefix_suffix]=true;
-    option_support[:over_write]=true;
+  def initialize(option_support=[:prefix_suffix,:over_write])
     
     super(option_support)
 

data/lib/protk/search_tool.rb

@@ -18,11 +18,10 @@ class SearchTool < Tool
   # Initializes commandline options common to all search tools.
   # Individual search tools can add their own options, but should use Capital letters to avoid conflicts
   #
-  def initialize(option_support={})
+  def initialize(option_support=[])
     super(option_support)
 
-    if (option_support[:database]==true)          
-          
+    if (option_support.include? :database)          
       @options.database = "sphuman"
       @option_parser.on( '-d', '--database dbname', 'Specify the database to use for this search. Default=sphuman' ) do |dbname|
         options.database = dbname
@@ -30,78 +29,45 @@ class SearchTool < Tool
 
     end
     
-    if ( option_support[:msms_search_detailed_options]==true)      
-       @options.allowed_charges="1+,2+,3+"
-       @option_parser.on(  '--allowed-charges ac', 'Allowed precursor ion charges. Default=1+,2+,3+' ) do |ac|
-         @options.allowed_charges = ac
-       end       
-       
+    if ( option_support.include? :enzyme )
        @options.enzyme = "Trypsin"
        @option_parser.on('--enzyme enz', 'Enzyme') do |enz|
          @options.enzyme=enz
        end
-       
-       @options.instrument = "ESI-QUAD-TOF"
-       @option_parser.on('--instrument instrument', 'Instrument') do |instrument|
-         @options.instrument=instrument
-       end
-       
-       
-       @options.var_mods = ""
-        @option_parser.on('--var-mods vm', 'Variable modifications (Overrides -g)' ) do |vm|
-          @options.var_mods = vm
-        end
-
-        @options.fix_mods = ""
-        @option_parser.on('--fix-mods fm', 'Fixed modifications (Overrides -c and -m options)' ) do |fm|
-          @options.fix_mods = fm
-        end
-
-        @options.searched_ions = ""
-        @option_parser.on('--searched-ions si', 'Ion series to search (default=b,y)' ) do |si|
-          @options.searched_ions = si
-        end
-
-        
-        @options.fragment_tolu="Da"
-        @option_parser.on('--fragment-ion-tol-units tolu', 'Fragment ion mass tolerance units (Da or mmu). Default=Da' ) do |tolu|
-          @options.fragment_tolu = tolu
-        end
-        
-        @options.precursor_tolu="ppm"
-        @option_parser.on('--precursor-ion-tol-units tolu', 'Precursor ion mass tolerance units (ppm or Da). Default=ppm' ) do |tolu|
-          @options.precursor_tolu = tolu
-        end
-        
-        @options.email=""
-        @option_parser.on('--email em', 'User email.') do |em|
-          @options.email = em
-        end
+    end
 
-        @options.username=""
-        @option_parser.on('--username un', 'Username.') do |un|
-          @options.username = un
-        end
+    if ( option_support.include? :modifications )
+      @options.var_mods = ""
+      @option_parser.on('--var-mods vm', 'Variable modifications' ) do |vm|
+        @options.var_mods = vm
+      end
 
-        @options.mascot_server="www.matrixscience.com"
-        @option_parser.on( '-S', '--server url', 'The url to the cgi directory of the mascot server' ) do |url| 
-          @options.mascot_server=url
-        end
+      @options.fix_mods = ""
+      @option_parser.on('--fix-mods fm', 'Fixed modifications' ) do |fm|
+        @options.fix_mods = fm
+      end
+    end
 
-        @options.mascot_server=""
-        @option_parser.on('--username un', 'Username.') do |un|
-          @options.username = un
-        end
+    if ( option_support.include? :instrument )
+      @options.instrument = "ESI-QUAD-TOF"
+      @option_parser.on('--instrument instrument', 'Instrument') do |instrument|
+       @options.instrument=instrument
+     end
+    end
 
-        @options.num_peaks_for_multi_isotope_search="0"
-        @option_parser.on("--num-peaks-for-multi-isotope-search np","Number of peaks to include in multi-isotope search") do |np|
-          @options.num_peaks_for_multi_isotope_search=np
-        end
+    if ( option_support.include? :mass_tolerance_units )
+      @options.fragment_tolu="Da"
+      @option_parser.on('--fragment-ion-tol-units tolu', 'Fragment ion mass tolerance units (Da or mmu). Default=Da' ) do |tolu|
+        @options.fragment_tolu = tolu
+      end
+        
+      @options.precursor_tolu="ppm"
+      @option_parser.on('--precursor-ion-tol-units tolu', 'Precursor ion mass tolerance units (ppm or Da). Default=ppm' ) do |tolu|
+        @options.precursor_tolu = tolu
+      end
+    end
 
-       
-     end
-    
-    if ( option_support[:msms_search]==true)      
+    if ( option_support.include? :mass_tolerance )
       @options.fragment_tol=0.65
       @option_parser.on( '-f', '--fragment-ion-tol tol', 'Fragment ion mass tolerance (unit dependent). Default=0.65' ) do |tol|
         @options.fragment_tol = tol
@@ -111,49 +77,72 @@ class SearchTool < Tool
       @option_parser.on( '-p', '--precursor-ion-tol tol', 'Precursor ion mass tolerance in (ppm if precursor search type is monoisotopic or Da if it is average). Default=200' ) do |tol|
         @options.precursor_tol = tol.to_f
       end
-      
-      @options.respect_precursor_charges=false
-      @option_parser.on( '-q', '--respect-charges','Dont respect charges in the input file. Instead impute them by trying various options') do 
-        @options.respect_precursor_charges=true
-      end
-      
+    end
+    
+    if ( option_support.include? :precursor_search_type )
       @options.precursor_search_type="monoisotopic"
       @option_parser.on( '-a', '--search-type type', 'Use monoisotopic or average precursor masses. (monoisotopic or average)' ) do |type| 
         @options.precursor_search_type = type
       end
-      
+    end
+
+    if ( option_support.include? :strict_monoisotopic_mass )
       @options.strict_monoisotopic_mass=false
       @option_parser.on( '-s', '--strict-monoisotopic-mass', 'Dont allow for misassignment of monoisotopic mass to another isotopic peak') do
         @options.strict_monoisotopic_mass=true
       end
-      
+    end
+
+    if ( option_support.include? :missed_cleavages )
       @options.missed_cleavages=2
       @option_parser.on( '-v', '--num-missed-cleavages num', 'Number of missed cleavages allowed' ) do |num| 
         @options.missed_cleavages = num
       end
-    
-      @options.carbamidomethyl=true
-      @option_parser.on( '-c', '--no-carbamidomethyl', 'Run a search without a carbamidomethyl fixed modification' ) do 
-        @options.carbamidomethyl = false
-      end
+    end
 
-      @options.methionine_oxidation=false
-      @option_parser.on( '-m', '--methionine-oxidation', 'Run a search with oxidised methionines as a variable modification' ) do 
-        @options.methionine_oxidation = true
+    if ( option_support.include? :respect_precursor_charges )
+      @options.respect_precursor_charges=false
+      @option_parser.on( '-q', '--respect-charges','Dont respect charges in the input file. Instead impute them by trying various options') do 
+        @options.respect_precursor_charges=true
       end
-      
     end
-      
-    if ( option_support[:glyco]==true)
 
+    if ( option_support.include? :searched_ions )
+        @options.searched_ions = ""
+        @option_parser.on('--searched-ions si', 'Ion series to search (default=b,y)' ) do |si|
+          @options.searched_ions = si
+        end
+    end
+
+    if ( option_support.include? :num_peaks_for_multi_isotope_search )
+        @options.num_peaks_for_multi_isotope_search="0"
+        @option_parser.on("--num-peaks-for-multi-isotope-search np","Number of peaks to include in multi-isotope search") do |np|
+          @options.num_peaks_for_multi_isotope_search=np
+        end
+    end
+
+    if ( option_support.include? :glyco)
       @options.glyco = false
       @option_parser.on( '-g', '--glyco', 'Expect N-Glycosylation modifications as variable mod in a search or as a parameter when building statistical models' ) do 
         @options.glyco = true
       end
+    end
 
+    if ( option_support.include? :methionine_oxidation)
+      @options.methionine_oxidation = false
+      @option_parser.on( '-m', '--methionineo', 'Expect Oxidised Methionine modifications as variable mod in a search' ) do 
+        @options.methionine_oxidation = true
+      end
+    end
+
+    if ( option_support.include? :carbamidomethyl)
+      @options.carbamidomethyl = false
+      @option_parser.on( '-c', '--carbamidomethyl', 'Expect Carbamidomethyl C modifications as fixed mod in a search' ) do 
+        @options.carbamidomethyl = true
+      end
     end
     
-    if ( option_support[:maldi]==true)
+    if ( option_support.include? :maldi)
       @options.maldi=false
       @option_parser.on( '-l', '--maldi', 'Run a search on MALDI data') do
         @options.maldi=true

data/lib/protk/setup_rakefile.rake

@@ -143,8 +143,9 @@ tpp_download_file = download_task tpp_url, tpp_packagefile
 # Build
 file tpp_installed_file => [@build_dir,tpp_download_file] do
 	sh %{cp #{@download_dir}/#{tpp_packagefile} #{@build_dir}}
-	sh %{eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir});cpanm --local-lib=#{env.protk_dir}/perl5 XML::Parser}
-	sh %{eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir});cpanm --local-lib=#{env.protk_dir}/perl5 CGI --force}
+	use_perl_locallib_cmd="eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir})"
+	sh %{#{use_perl_locallib_cmd};cpanm --local-lib=#{env.protk_dir}/perl5 XML::Parser}
+	sh %{#{use_perl_locallib_cmd};cpanm --local-lib=#{env.protk_dir}/perl5 CGI --force}
 
 	sh %{cd #{@build_dir};tar -xvzf TPP-#{tpp_version}.tgz}
 
@@ -172,8 +173,14 @@ file tpp_installed_file => [@build_dir,tpp_download_file] do
 			f.write subs_text
 		end
 	end
-	sh %{eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir});cd #{@build_dir}/TPP-#{tpp_version}/trans_proteomic_pipeline/src ; make; make install}
-
+	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}}
+	env.log "Done Building", :info
+	env.log install_cmd, :info
+	sh %{#{install_cmd}}
+	env.log "Done Installing", :info
 end
 
 task :tpp => tpp_installed_file
@@ -241,7 +248,7 @@ task :blast => blast_installed_file
 #
 # MSGFPlus
 #
-msgfplus_version="20130227"
+msgfplus_version="20130410"
 msgfplus_packagefile="MSGFPlus.#{msgfplus_version}.zip"
 msgfplus_url="http://proteomics.ucsd.edu/Downloads/MSGFPlus.#{msgfplus_version}.zip"
 msgfplus_installed_file="#{env.msgfplusjar}"