protk 1.1.2 → 1.1.4

data/README.md

@@ -23,6 +23,8 @@ On OSX
     rvm install 1.9.3 --with-gcc=clang
     rvm use 1.9.3
     gem install protk
+    protk_setup.rb package_manager
+    protk_setup.rb system_packages
     protk_setup.rb all
 
 On Linux
@@ -30,7 +32,7 @@ On Linux
     rvm install 1.9.3
     rvm use 1.9.3
     gem install protk
-    sudo protk_setup.rb system_dependencies
+    sudo protk_setup.rb system_packages
     protk_setup all
 
 
@@ -63,25 +65,19 @@ Although all the protk tools can be run directly from the command-line a nicer w
 2. Make the protk tools available to galaxy. 
     - Create a directory for galaxy tool dependencies. It's best if this directory is outside the galaxy-dist directory. I usually create a directory called `tool_depends` alongside `galaxy-dist`.
     - Open the file `universe_wsgi.ini` in the `galaxy-dist` directory and set the configuration option `tool_dependency_dir` to point to the directory you just created
-    - Create a symbolic link from the protk directory to the appropriate subdirectory of `<tool_dependency_dir>`. In the instructions below substitute 1.0.0 for the version number of [the protk galaxy tools](https://bitbucket.org/iracooke/protk-toolshed "protk galaxy tools") you are using.
+    - Create a protkgem directory inside `<tool_dependency_dir>`. 
 
             cd <tool_dependency_dir>
-            mkdir protk
-			cd protk
-            mkdir 1.0.0
-            ln -s 1.0.0 default
-            ln -s <path_where_protk_was_installed> 1.0.0/bin
+            mkdir protkgem
+			cd protkgem
+            mkdir rvm193
+            ln -s rvm193 default
+            cd default
+            ln -s ~/.protk/galaxy/env.sh env.sh
 
-3. Configure the shell in which galaxy tools will run.
-    - Create a symlink to the `env.sh` file so it will be sourced by galaxy as it runs each tool. This file should have been autogenerated by `setup.sh`
+3. Install any of the Proteomics tools that depend on protk from the galaxy toolshed
 
-            ln -s <path_where_protk_was_installed>/env.sh 1.0.0/env.sh
-
-4. Install the protk galaxy wrapper tools from the galaxy toolshed. You will need to restart galaxy after doing so for the new datatype sniffers to be activated.
-
-5. After installing the protk wrapper tools from the toolshed it will be necessary to tell those tools about databases you have installed. Use the manage_db.rb tool to do this. To do this, first edit config.yml to make sure the `galaxy_root` setting points to the root directory of your galaxy installation (this will allow `manage_db.rb` to update the `pepxml_databases.loc` file inside `galaxy_root/tool-data`). The run the following command and then restart the galaxy server;
-
-		manage_db.rb list -G
+4. After installing the protk wrapper tools from the toolshed it will be necessary to tell those tools about databases you have installed. Use the manage_db.rb tool to do this. 
 
 
 

data/bin/feature_finder.rb

@@ -1,37 +1,32 @@
+#!/usr/bin/env ruby
 #
 # This file is part of protk
 # Created by Ira Cooke 21/3/2012
 #
 # A wrapper for the OpenMS FeatureFinder tools (FeatureFinderCentroided and FeatureFinderIsotopeWavelet)
-#
-#
-#!/bin/sh
-if [ -z "$PROTK_RUBY_PATH" ] ; then
-  PROTK_RUBY_PATH=`which ruby`
-fi
-
-eval 'exec "$PROTK_RUBY_PATH" $PROTK_RUBY_FLAGS -rubygems -x -S $0 ${1+"$@"}'
-echo "The 'exec \"$PROTK_RUBY_PATH\" -x -S ...' failed!" >&2
-exit 1
-#! ruby
-#
 
-$LOAD_PATH.unshift("#{File.dirname(__FILE__)}/lib/")
+require 'protk/constants'
+require 'protk/command_runner'
+require 'protk/tool'
+require 'protk/openms_defaults'
+require 'libxml'
 
-require 'constants'
-require 'command_runner'
-require 'tool'
+include LibXML
 
-# Setup specific command-line options for this tool. Other options are inherited from ProphetTool
-#
-tool=Tool.new({:explicit_output=>true, :background=>true,:over_write=>true})
+tool=Tool.new({:explicit_output=>true, :background=>true,:over_write=>true,:prefix_suffix=>true})
 tool.option_parser.banner = "Find molecular features on a set of input files.\n\nUsage: feature_finder.rb [options] file1.mzML file2.mzML ..."
 
-tool.options.profile = false
-tool.option_parser.on( '--profile',"Input files are profile data" ) do 
-  tool.options.profile = true
+tool.options.intensity_type = "ref"
+tool.option_parser.on( '--intensity-type type',"method used to calculate intensities (ref,trans,corrected). Default = ref. See OpenMS documentation for details" ) do |type|
+  tool.options.intensity_type = type
 end
 
+tool.options.intensity_threshold = "3"
+tool.option_parser.on( '--intensity-threshold thresh',"discard features below this intensity (Default=3). Set to -1 to retain all detected features" ) do |thresh|
+  tool.options.intensity_threshold = thresh
+end
+
+
 tool.option_parser.parse!
 
 # Obtain a global environment object
@@ -42,32 +37,44 @@ def run_ff(genv,tool,cmd,output_path,jobid)
     genv.log("Skipping analysis on existing file #{output_path}",:warn)   
   else
     jobscript_path="#{output_path}.pbs.sh"
-    job_params={:jobid=>jobid, :vmem=>"12Gb", :queue => "sixteen"}
+    job_params={:jobid=>jobid, :vmem=>"14Gb", :queue => "sixteen"}
     code=tool.run(cmd,genv,job_params,jobscript_path)
     throw "Command failed with exit code #{code}" unless code==0
   end
 end
 
+def generate_ini(tool,out_path)
+  base_ini_file=OpenMSDefaults.new.featurefinderisotopewavelet
+  parser = XML::Parser.file(base_ini_file)
+  doc = parser.parse
+  intensity_threshold_node = doc.find('//ITEM[@name="intensity_threshold"]')[0]
+  intensity_type_node = doc.find('//ITEM[@name="intensity_type"]')[0]
+  intensity_threshold_node['value']=tool.intensity_threshold
+  intensity_type_node['value']=tool.intensity_type
+  doc.save(out_path)
+end
 
 throw "Cannot use explicit output in combination with multiple input files" if ( tool.explicit_output && ARGV.length>1)
-throw "The profile option is not yet implemented" if ( tool.profile )
 
-ini_file="#{File.dirname(__FILE__)}/params/FeatureFinderCentroided.ini"
+ini_file="#{Pathname.new(ARGV[0]).dirname.realpath.to_s}/feature_finder.ini"
+
+generate_ini(tool,ini_file)
 
 ARGV.each do |filen|
   input_file=filen.chomp
   throw "Input must be an mzML file" unless input_file=~/\.mzML$/
 
   input_basename=input_file.gsub(/\.mzML$/,'')  
-  output_filename=tool.explicit_output 
-  output_file="#{input_basename}.featureXML" if output_filename==nil
-  
+  output_dir=Pathname.new(input_basename).dirname.realpath.to_s
+  output_base=Pathname.new(input_basename).basename.to_s
+  output_file = "#{output_dir}/#{tool.output_prefix}#{output_base}#{tool.output_suffix}.featureXML"
+
   if ( tool.over_write || !Pathname.new(output_file).exist? )
-    output_dir=Pathname.new(output_file).dirname.realpath.to_s
     output_base_filename=Pathname.new(output_file).basename.to_s
     cmd=""
-    cmd<<"#{genv.openms_root}/FeatureFinderCentroided -in #{Pathname.new(input_file).realpath.to_s} -out #{output_dir}/#{output_base_filename} -ini #{ini_file}"
-
+    cmd<<"export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$HOME/.protk/tools/openms/lib;
+#{genv.featurefinderisotopewavelet} -in #{Pathname.new(input_file).realpath.to_s} -out #{output_dir}/#{output_base_filename} -ini #{ini_file}"
+  
     run_ff(genv,tool,cmd,output_file,tool.jobid_from_filename(input_basename))
   
   else

data/bin/gffmerge.rb

@@ -0,0 +1,199 @@
+#!/usr/bin/env ruby
+#
+# This file is part of protk
+# Original python version created by Max Grant
+# Translated to ruby by Ira Cooke 29/1/2013
+#
+# 
+
+require 'protk/constants'
+require 'protk/tool'
+require 'protk/fastadb'
+require 'libxml'
+require 'bio'
+
+include LibXML
+
+tool=Tool.new(:explicit_output=>true)
+tool.option_parser.banner = "Create a gff containing peptide observations.\n\nUsage: gffmerge.rb "
+
+
+tool.options.gff_predicted=nil
+tool.option_parser.on( '-g filename','--gff filename', 'Predicted Data (GFF3 Format)' ) do |file| 
+  tool.options.gff_predicted=file
+end
+
+tool.options.protxml=nil
+tool.option_parser.on( '-p filename','--protxml filename', 'Observed Data (ProtXML Format)' ) do |file| 
+  tool.options.protxml=file
+end
+
+tool.options.sixframe=nil
+tool.option_parser.on( '-t filename','--sixframe filename', 'Sixframe Translations (Fasta Format)' ) do |file| 
+  tool.options.sixframe=file
+end
+
+tool.options.skip_fasta_indexing=false
+tool.option_parser.on('--skip-index','Don\'t index sixframe translations (Index should already exist)') do 
+  tool.options.skip_fasta_indexing=true
+end
+
+tool.options.peptide_probability_threshold=0.95
+tool.option_parser.on('--threshold prob','Peptide Probability Threshold (Default 0.95)') do |thresh|
+  tool.options.peptide_probability_threshold=thresh.to_f
+end
+
+# Checking for required options
+begin
+  tool.option_parser.parse!
+  mandatory = [:protxml,:sixframe] 
+  missing = mandatory.select{ |param| tool.send(param).nil? }
+  if not missing.empty?                                            
+    puts "Missing options: #{missing.join(', ')}"                  
+    puts tool.option_parser                                                  
+    exit                                                           
+  end                                                              
+rescue OptionParser::InvalidOption, OptionParser::MissingArgument      
+  puts $!.to_s                                                           
+  puts tool.option_parser                                              
+  exit                                                                   
+end
+
+gff_out_file="merged.gff"
+if ( tool.explicit_output != nil)
+  gff_out_file=tool.explicit_output
+end
+
+gff_db = Bio::GFF.new()
+if ( tool.gff_predicted !=nil)
+  p "Reading source gff file"
+  gff_db = Bio::GFF::GFF3.new(File.open(tool.gff_predicted))
+  # p gff_db.records[1].attributes
+  # exit
+end
+
+f = open(gff_out_file,'w+')
+gff_db.records.each { |rec| 
+  f.write(rec.to_s)
+}
+
+p "Parsing proteins from protxml"
+protxml_parser=XML::Parser.file(tool.protxml)
+protxml_doc=protxml_parser.parse
+proteins = protxml_doc.find('.//protxml:protein','protxml:http://regis-web.systemsbiology.net/protXML')
+
+p "Indexing sixframe translations"
+db_filename = Pathname.new(tool.sixframe).realpath.to_s
+
+if tool.skip_fasta_indexing 
+  orf_lookup = FastaDB.new(db_filename)
+else
+  orf_lookup = FastaDB.create(db_filename,db_filename,'prot')
+end
+
+p "Aligning peptides and writing GFF data..."
+low_prob = 0
+skipped = 0
+peptide_count = 0
+protein_count = 0
+total_peptides = 0
+for prot in proteins
+  prot_prob = prot['probability']
+  indis_proteins = prot.find('protxml:indistinguishable_protein','protxml:http://regis-web.systemsbiology.net/protXML')
+  prot_names = [prot['protein_name']]
+  for protein in indis_proteins
+    prot_names += [protein['protein_name']]
+  end
+
+  peptides = prot.find('protxml:peptide','protxml:http://regis-web.systemsbiology.net/protXML')
+
+  for protein_name in prot_names
+    protein_count += 1
+    prot_qualifiers = {"source" => "OBSERVATION", "score" => prot_prob, "ID" => 'pr' + protein_count.to_s}
+    begin
+      p "Looking up #{protein_name}"
+      orf = orf_lookup.get_by_id protein_name
+      if ( orf == nil)
+        raise KeyError
+      end
+
+
+      position = orf.identifiers.description.split('|').collect { |pos| pos.to_i }
+
+      if ( position.length != 2 )
+        raise EncodingError
+      end
+      orf_name = orf.entry_id.scan(/lcl\|(.*)/)[0][0]
+      frame=orf_name.scan(/frame_(\d)/)[0][0]
+      scaffold_name = orf_name.scan(/(scaffold_\d+)/)[0][0]
+
+      # strand = frame > 3 ? -1 : 1 
+      strand = +1
+
+      prot_id = "pr#{protein_count.to_s}"
+      prot_attributes = [["ID",prot_id]]
+      prot_gff_line = Bio::GFF::GFF3::Record.new(seqid = scaffold_name,source="OBSERVATION",feature_type="protein",
+        start_position=position[0],end_position=position[1],score=prot_prob,strand=strand,frame=frame,attributes=prot_attributes)
+      gff_db.records += [prot_gff_line]
+
+      prot_seq = orf.aaseq.to_s
+      throw "Not amino_acids" if prot_seq != orf.seq.to_s
+
+
+      for peptide in peptides
+        pprob = peptide['nsp_adjusted_probability'].to_f
+        if ( pprob >= tool.peptide_probability_threshold )
+          total_peptides += 1
+          pep_seq = peptide['peptide_sequence']
+
+
+          start_indexes = [0]
+          prot_seq.scan /#{pep_seq}/  do |match| 
+              start_indexes << prot_seq.index(match,start_indexes.last)
+          end
+          start_indexes.delete_at(0)
+
+          # Now convert peptide coordinate to genome coordinates
+          # And create gff lines for each match
+          start_indexes.collect do |si|
+            pep_genomic_start = position[0] + 3*si
+            pep_genomic_end = pep_genomic_start + 3*pep_seq.length
+            peptide_count+=1
+            pep_attributes = [["ID","p#{peptide_count.to_s}"],["Parent",prot_id]]
+            pep_gff_line = Bio::GFF::GFF3::Record.new(seqid = scaffold_name,source="OBSERVATION",
+              feature_type="peptide",start_position=pep_genomic_start,end_position=pep_genomic_end,score=pprob,
+              strand=strand,frame=frame,attributes=pep_attributes)
+            gff_db.records += [pep_gff_line]
+            # p pep_gff_line
+
+          end
+
+
+        end
+      end
+
+    rescue KeyError,EncodingError
+      skipped+=0
+      p "Lookup failed for #{protein_name}"
+    end
+
+    # p orf_name
+    # p prot_gff_line
+    # exit
+  end
+
+end
+
+f = open(gff_out_file,'w+')
+gff_db.records.each { |rec| 
+  f.write(rec.to_s)
+}
+f.close
+
+p "Finished."
+p "Proteins: #{protein_count}"
+p "Skipped Decoys: #{skipped}"
+p "Total Peptides: #{total_peptides}"
+p "Peptides Written: #{total_peptides - low_prob}"
+p "Peptides Culled: #{low_prob}"
+exit(0)

data/bin/protk_setup.rb

@@ -16,16 +16,38 @@ require 'pp'
 # Setup specific command-line options for this tool. Other options are inherited from Tool
 #
 tool=SetupTool.new
-if ( tool.option_parser.banner=="")
-  tool.option_parser.banner = "Post install tasks for protk.\nUsage: protk_setup.rb [options] toolname"
-end
+tool.option_parser.banner = "Post install tasks for protk.\nUsage: protk_setup.rb [options] toolname"
 
 tool.option_parser.parse!
 
+if ( ARGV.length < 1)
+	p "You must supply a setup task [all,system_packages]"
+	p tool.option_parser
+	exit
+end
+
+# Checking for required options
+# begin
+#   tool.option_parser.parse!
+#   mandatory = [:gff_predicted, :protxml,:sixframe] 
+#   missing = mandatory.select{ |param| tool.send(param).nil? }
+#   if not missing.empty?                                            
+#     puts "Missing options: #{missing.join(', ')}"                  
+#     puts tool.option_parser                                                  
+#     exit                                                           
+#   end                                                              
+# rescue OptionParser::InvalidOption, OptionParser::MissingArgument      
+#   puts $!.to_s                                                           
+#   puts tool.option_parser                                              
+#   exit                                                                   
+# end
+
+
 # Create install directory if it doesn't already exist
 #
 env=Constants.new
 
 ARGV.each do |toolname|
-  tool.install toolname
+	p toolname
+	tool.install toolname
 end

data/bin/sixframe.rb

@@ -0,0 +1,62 @@
+#!/usr/bin/env ruby
+#
+# This file is part of protk
+# Original python version created by Max Grant
+# Translated to ruby by Ira Cooke 7/2/2013
+#
+# 
+
+require 'protk/constants'
+require 'protk/tool'
+require 'bio'
+
+tool=Tool.new(:explicit_output=>true)
+tool.option_parser.banner = "Create a sixframe translation of a genome.\n\nUsage: sixframe.rb [options] genome.fasta"
+
+tool.option_parser.parse!
+
+inname=ARGV.shift
+
+outfile=File.open("#{inname}.translated.fasta",'w')
+if ( tool.explicit_output != nil)
+  outfile=File.open(tool.explicit_output,'w')
+end
+
+
+file = Bio::FastaFormat.open(inname)
+
+file.each do |entry|
+  length = entry.naseq.length
+  (1...7).each do |frame|
+    translated_seq= entry.naseq.translate(frame)
+    orfs=translated_seq.split("*")
+    orf_index = 0
+    position = ((frame - 1) % 3) + 1    
+
+    oi=0
+    orfs.each do |orf|
+      oi+=1
+      if ( orf.length > 20 )
+        position_start = position
+        position_end = position_start + orf.length*3 -1
+
+        if ( frame > 3)
+            position_start = length - (position - 1)
+            position_end = position_start - orf.length * 3 + 1          
+        end
+
+
+        # Create accession compliant with NCBI naming standard
+        # See http://www.ncbi.nlm.nih.gov/books/NBK7183/?rendertype=table&id=ch_demo.T5
+        ncbi_scaffold_id = entry.entry_id.gsub('|','_').gsub(' ','_')
+        ncbi_accession = "lcl|#{ncbi_scaffold_id}_frame_#{frame}_orf_#{oi}"
+
+        # Output in fasta format
+        outfile.write(">#{ncbi_accession} #{position_start}|#{position_end}\n#{orf}\n")
+
+      end
+      position += orf.length*3+3
+    end
+
+  end
+end

data/bin/toppas_pipeline.rb

@@ -0,0 +1,73 @@
+#!/usr/bin/env ruby
+#
+# This file is part of protk
+# Created by Ira Cooke 30/01/13
+#
+# A wrapper for the OpenMS tool ExecutePipeline. 
+# Executes simple toppas pipelines, automatically creating the trf file.
+
+require 'protk/constants'
+require 'protk/command_runner'
+require 'protk/tool'
+require 'protk/openms_defaults'
+require 'tempfile'
+require 'libxml'
+
+include LibXML
+
+tool=Tool.new({:explicit_output=>false, :background=>true,:over_write=>false})
+tool.option_parser.banner = "Execute a toppas pipeline with a single inputs node\n\nUsage: toppas_pipeline.rb [options] input1 input2 ..."
+
+tool.options.outdir = ""
+tool.option_parser.on( '--outdir dir',"save outputs to dir" ) do |dir|
+  tool.options.outdir = dir
+end
+
+tool.options.toppas_file = ""
+tool.option_parser.on( '--toppas-file f',"the toppas file to run" ) do |file|
+  tool.options.toppas_file = file
+end
+
+tool.option_parser.parse!
+
+# Obtain a global environment object
+genv=Constants.new
+
+def run_pipeline(genv,tool,cmd,output_path,jobid)
+  jobscript_path="#{output_path}.pbs.sh"
+  job_params={:jobid=>jobid, :vmem=>"14Gb", :queue => "sixteen"}
+  code=tool.run(cmd,genv,job_params,jobscript_path)
+  throw "Command failed with exit code #{code}" unless code==0
+end
+
+def generate_trf(input_files,out_path)
+  p OpenMSDefaults.new.trf_path
+  parser=XML::Parser.file(OpenMSDefaults.new.trf_path)
+  doc=parser.parse
+  itemlist_node=doc.find('/PARAMETERS/NODE/ITEMLIST')[0]
+
+  input_files.each do |f|
+
+    mnode=XML::Node.new('LISTITEM')
+    mnode["value"]="file://#{Pathname.new(f).realpath.to_s}"
+    
+    itemlist_node << mnode
+  end
+  p out_path
+  doc.save(out_path)
+end
+
+throw "outdir is a required parameter" if tool.outdir==""
+throw "toppas-file is a required parameter" if tool.toppas_file==""
+throw "outdir must exist" unless Dir.exist?(tool.outdir)
+
+trf_path = "#{tool.toppas_file}.trf"
+
+generate_trf(ARGV,trf_path)
+
+cmd=""
+cmd<<"export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$HOME/.protk/tools/openms/lib;
+#{genv.executepipeline} -in #{Pathname.new(tool.toppas_file).realpath.to_s} -out_dir #{Pathname.new(tool.outdir).realpath.to_s} -resource_file #{Pathname.new(trf_path).realpath.to_s}"
+
+run_pipeline(genv,tool,cmd,tool.outdir,tool.jobid_from_filename(tool.toppas_file))
+

data/lib/protk/constants.rb

@@ -121,15 +121,6 @@ class Constants
   def omssa2pepxml
     return "#{self.omssa_root}/omssa2pepXML"
   end
-
-  def openms_root
-    path=@env['openms_root']
-    if ( path =~ /^\// )
-      return path
-    else
-      return "#{@protk_dir}/#{@env['openms_root']}"
-    end
-  end
   
   def msgfplus_root
     path=@env['msgfplus_root']
@@ -161,6 +152,22 @@ class Constants
     return "#{self.pwiz_root}/msconvert"
   end
 
+  def openms_root
+    path=@env['openms_root']
+    if ( path =~ /^\//)
+      return path 
+    else
+      return "#{@protk_dir}/#{@env['openms_root']}"
+    end
+  end
+
+  def featurefinderisotopewavelet
+    return "#{self.openms_root}/bin/FeatureFinderIsotopeWavelet"
+  end
+
+  def executepipeline
+    return "#{self.openms_root}/bin/ExecutePipeline"
+  end
 
   def protein_database_root
     path=@env['protein_database_root']
@@ -187,6 +194,10 @@ class Constants
   def makeblastdb
     return "#{self.blast_root}/bin/makeblastdb"
   end
+
+  def searchblastdb
+    return "#{self.blast_root}/bin/blastdbcmd"
+  end
   
   def log_file
     path=@env['log_file']
@@ -209,10 +220,18 @@ class Constants
     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
 
-    @env=default_config_yml
+    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 )
+      @env = default_config_yml.merge user_config_yml
+    else
+      @env=default_config_yml
+    end
+    
     throw "No data found in config file" unless @env!=nil
     @info_level=default_config_yml['message_level']
 
+
     
   end
 

data/lib/protk/data/ExecutePipeline.trf

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<PARAMETERS version="1.3" xsi:noNamespaceSchemaLocation="http://open-ms.sourceforge.net/schemas/Param_1_3.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+  <NODE name="1" description="">
+    <ITEMLIST name="url_list" type="string" description="">
+    </ITEMLIST>
+  </NODE>
+</PARAMETERS>

data/lib/protk/data/FeatureFinderIsotopeWavelet.ini

@@ -0,0 +1,26 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<PARAMETERS version="1.3" xsi:noNamespaceSchemaLocation="http://open-ms.sourceforge.net/schemas/Param_1_3.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+  <NODE name="FeatureFinderIsotopeWavelet" description="Detects two-dimensional features in LC-MS data.">
+    <ITEM name="version" value="1.9.0" type="string" description="Version of the tool that generated this parameters file." tags="advanced" />
+    <NODE name="1" description="Instance &apos;1&apos; section for &apos;FeatureFinderIsotopeWavelet&apos;">
+      <ITEM name="in" value="" type="string" description="input file" tags="input file,required" restrictions="*.mzML" />
+      <ITEM name="out" value="" type="string" description="output file" tags="output file,required" restrictions="*.featureXML" />
+      <ITEM name="log" value="" type="string" description="Name of log file (created only when specified)" tags="advanced" />
+      <ITEM name="debug" value="0" type="int" description="Sets the debug level" tags="advanced" />
+      <ITEM name="threads" value="1" type="int" description="Sets the number of threads allowed to be used by the TOPP tool" />
+      <ITEM name="no_progress" value="false" type="string" description="Disables progress logging to command line" tags="advanced" restrictions="true,false" />
+      <ITEM name="test" value="false" type="string" description="Enables the test mode (needed for internal use only)" tags="advanced" restrictions="true,false" />
+      <NODE name="algorithm" description="Algorithm section">
+        <ITEM name="max_charge" value="3" type="int" description="The maximal charge state to be considered." restrictions="1:" />
+        <ITEM name="intensity_threshold" value="3" type="float" description="The final threshold t&apos; is build upon the formula: t&apos; = av+t*sd, where t is the intensity_threshold, av the average intensity within the wavelet transformed signal and sd the standard deviation of the transform. If you set intensity_threshold=-1, t&apos; will be zero.#br#As the &apos;optimal&apos; value for this parameter is highly data dependent, we would recommend to start with -1, which will also extract features with very low signal-to-noise ratio. Subsequently, one might increase the threshold to find an optimized trade-off between false positives and true positives. Depending on the dynamic range of your spectra, suitable value ranges include: -1, [0:10], and if your data features even very high intensity values, t can also adopt values up to around 30. Please note that this parameter is not of an integer type, s.t. you can also use t:=0.1, e.g." />
+        <ITEM name="intensity_type" value="ref" type="string" description="Determines the intensity type returned for the identified features. &apos;ref&apos; (default) returns the sum of the intensities of each isotopic peak within an isotope pattern. &apos;trans&apos; refers to the intensity of the monoisotopic peak within the wavelet transform. &apos;corrected&apos; refers also to the transformed intensity with an attempt to remove the effects of the convolution. While the latter ones might be preferable for qualitative analyses, &apos;ref&apos; might be the best option to obtain quantitative results. Please note that intensity values might be spoiled (in particular for the option &apos;ref&apos;), as soon as patterns overlap (see also the explanations given in the class documentation of FeatureFinderAlgorihtmIsotopeWavelet)." tags="advanced" restrictions="ref,trans,corrected" />
+        <ITEM name="check_ppm" value="true" type="string" description="Enables/disables a ppm test vs. the averagine model, i.e. potential peptide masses are checked for plausibility. In addition, a heuristic correcting potential mass shifts induced by the wavelet is applied." tags="advanced" restrictions="true,false" />
+        <ITEM name="hr_data" value="false" type="string" description="Must be true in case of high-resolution data, i.e. for spectra featuring large m/z-gaps (present in FTICR and Orbitrap data, e.g.). Please check a single MS scan out of your recording, if you are unsure." restrictions="true,false" />
+        <NODE name="sweep_line" description="">
+          <ITEM name="rt_votes_cutoff" value="5" type="int" description="Defines the minimum number of subsequent scans where a pattern must occur to be considered as a feature." tags="advanced" restrictions="0:" />
+          <ITEM name="rt_interleave" value="1" type="int" description="Defines the maximum number of scans (w.r.t. rt_votes_cutoff) where an expected pattern is missing. There is usually no reason to change the default value." tags="advanced" restrictions="0:" />
+        </NODE>
+      </NODE>
+    </NODE>
+  </NODE>
+</PARAMETERS>

data/lib/protk/data/brew_packages.yaml

@@ -4,7 +4,13 @@
 
 common:
 - wget
+- cpanm
+- libxml2
 - gd
 - libpng12
-- cpanm
-- libxml2
+
+openms:
+- autoconf
+- automake
+- libtool
+- cmake

data/lib/protk/data/galaxyenv.sh

@@ -0,0 +1,17 @@
+temp_file=`mktemp /tmp/protkXXX`
+export temp_file
+
+bash << %%%
+
+[[ -s "$HOME/.rvm/scripts/rvm" ]] && source "$HOME/.rvm/scripts/rvm"
+
+
+rvm 1.9.3
+
+export | grep 'declare -x' | sed 's/declare -x/export/g' > $temp_file
+
+%%%
+
+. $temp_file
+
+rm $temp_file

data/lib/protk/fastadb.rb

@@ -0,0 +1,48 @@
+require 'protk/constants'
+require 'bio'
+
+#
+# Warning: Uses Bio::Command which is a private API of the Bio package
+#
+
+class FastaDB
+
+  def initialize(blast_database_file_path)
+    env = Constants.new
+    @database = blast_database_file_path
+    @makedbcmd = env.makeblastdb
+    @searchdbcmd = env.searchblastdb
+  end
+
+  def self.create(blast_database_file_path,input_fasta_filepath,type='nucl')
+    db = FastaDB.new(blast_database_file_path)
+    db.make_index(input_fasta_filepath,type)
+    db
+  end
+
+  def get_by_id(entry_id)
+    fetch(entry_id).shift
+  end
+
+  def make_index(input_fasta,dbtype)
+    cmd = [ @makedbcmd, '-in', input_fasta, '-parse_seqids','-out',@database,'-dbtype',dbtype]
+    res = Bio::Command.call_command(cmd) do |io|
+      puts io.read
+    end
+  end
+
+  def fetch(list)
+    if list.respond_to?(:join)
+      entry_id = list.join(",")
+    else
+      entry_id = list
+    end
+
+    cmd = [ @searchdbcmd, '-db', @database, '-entry', entry_id ]
+    Bio::Command.call_command(cmd) do |io|
+      io.close_write
+      Bio::FlatFile.new(Bio::FastaFormat, io).to_a
+    end
+  end
+
+end

data/lib/protk/galaxy_stager.rb

@@ -1,3 +1,5 @@
+$VERBOSE=nil
+
 require 'pathname'
 
 class GalaxyStager 

data/lib/protk/openms_defaults.rb

@@ -0,0 +1,11 @@
+require 'libxml'
+include LibXML
+
+class OpenMSDefaults
+	attr :featurefinderisotopewavelet
+	attr :trf_path
+	def initialize
+		@featurefinderisotopewavelet="#{File.dirname(__FILE__)}/data/FeatureFinderIsotopeWavelet.ini"
+		@trf_path = "#{File.dirname(__FILE__)}/data/ExecutePipeline.trf"
+	end
+end

data/lib/protk/setup_rakefile.rake

@@ -22,7 +22,7 @@ end
 
 def supports_package_manager name
 	res = %x[which #{name}]
-	(res == "")
+	(res != "")
 end
 
 def clean_build_dir
@@ -53,9 +53,10 @@ task :package_manager do
 	end
 
 	if needs_homebrew
-		sh { "ruby -e \"$(curl -fsSkL raw.github.com/mxcl/homebrew/go)" }
-		sh { "brew update"}
-		sh { "brew tap homebrew/versions"}
+		puts "Installing Homebrew"
+		sh %{ ruby -e \"$(curl -fsSkL raw.github.com/mxcl/homebrew/go)\" }
+		sh %{ brew update}
+		sh %{ brew tap homebrew/versions}
 	end
 
 end
@@ -265,7 +266,7 @@ end
 
 def platform_bunzip
 	if RbConfig::CONFIG['host_os'] =~ /darwin/ 
-		return 'pbunzip2'
+		return 'bunzip2'
 	end
 	'bunzip2'
 end
@@ -287,6 +288,50 @@ end
 
 task :pwiz => pwiz_installed_file
 
-task :all => [:tpp,:omssa,:blast,:msgfplus,:pwiz]
+#
+# openms
+#
+
+def platform_cmake_args
+	if RbConfig::CONFIG['host_os'] =~ /darwin/ 
+		return '-D CMAKE_CXX_COMPILER=/usr/bin/g++ -D CMAKE_C_COMPILER=/usr/bin/gcc '
+	end
+	''
+end
+
+openms_version="1.9.0"
+openms_packagefile="OpenMS-#{openms_version}.tar.gz"
+openms_url="https://dl.dropbox.com/u/226794/#{openms_packagefile}"
+openms_installed_file="#{env.featurefinderisotopewavelet}"
+
+download_task openms_url, openms_packagefile
+
+file openms_installed_file => [@build_dir,"#{@download_dir}/#{openms_packagefile}"] do 
+	sh %{cp #{@download_dir}/#{openms_packagefile} #{@build_dir}}
+    sh %{cd #{@build_dir}; gunzip -f #{openms_packagefile}}
+    sh %{cd #{@build_dir}; tar -xvf #{openms_packagefile.chomp('.gz')}}
+    sh %{mkdir -p #{env.openms_root}}
+    sh %{cd #{@build_dir}/OpenMS-#{openms_version}/contrib; cmake #{platform_cmake_args} .}
+    sh %{cd #{@build_dir}/OpenMS-#{openms_version}; cmake -D INSTALL_PREFIX=#{env.openms_root} .}
+    sh %{cd #{@build_dir}/OpenMS-#{openms_version}; make install}
+end
+
+task :openms => openms_installed_file
+
+#
+# Galaxy Environment
+#
+
+protk_galaxy_envfile = "#{env.protk_dir}/galaxy/env.sh"
+
+file protk_galaxy_envfile do
+	sh %{mkdir -p #{env.protk_dir}/galaxy}
+	this_dir=File.dirname(__FILE__)
+	sh %{cp #{this_dir}/data/galaxyenv.sh #{protk_galaxy_envfile}}
+end
+
+task :galaxy => protk_galaxy_envfile
+
+task :all => [:tpp,:omssa,:blast,:msgfplus,:pwiz,:openms,:galaxy]
 
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.1.2
+  version: 1.1.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-12-19 00:00:00.000000000 Z
+date: 2013-01-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ftools
@@ -166,6 +166,10 @@ executables:
 - unimod_to_loc.rb
 - generate_omssa_loc.rb
 - uniprot_mapper.rb
+- feature_finder.rb
+- toppas_pipeline.rb
+- gffmerge.rb
+- sixframe.rb
 extensions:
 - ext/protk/extconf.rb
 extra_rdoc_files: []
@@ -178,11 +182,13 @@ files:
 - lib/protk/convert_util.rb
 - lib/protk/data/make_uniprot_table.rb
 - lib/protk/eupathdb_gene_information_table.rb
+- lib/protk/fastadb.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/openms_defaults.rb
 - lib/protk/pepxml.rb
 - lib/protk/plasmodb.rb
 - lib/protk/prophet_tool.rb
@@ -207,6 +213,7 @@ files:
 - bin/feature_finder.rb
 - bin/file_convert.rb
 - bin/generate_omssa_loc.rb
+- bin/gffmerge.rb
 - bin/interprophet.rb
 - bin/libra.rb
 - bin/make_decoy.rb
@@ -220,8 +227,10 @@ files:
 - bin/protein_prophet.rb
 - bin/protk_setup.rb
 - bin/repair_run_summary.rb
+- bin/sixframe.rb
 - bin/tandem_search.rb
 - bin/template_search.rb
+- bin/toppas_pipeline.rb
 - bin/unimod_to_loc.rb
 - bin/uniprot_mapper.rb
 - bin/xls_to_table.rb
@@ -230,7 +239,10 @@ files:
 - lib/protk/data/apt-get_packages.yaml
 - lib/protk/data/brew_packages.yaml
 - lib/protk/data/default_config.yml
+- lib/protk/data/ExecutePipeline.trf
 - lib/protk/data/FeatureFinderCentroided.ini
+- lib/protk/data/FeatureFinderIsotopeWavelet.ini
+- lib/protk/data/galaxyenv.sh
 - lib/protk/data/predefined_db.crap.yaml
 - lib/protk/data/predefined_db.sphuman.yaml
 - lib/protk/data/predefined_db.swissprot_annotation.yaml