protk 1.2.6.pre5 → 1.3.0.pre1

data/bin/libra.rb

@@ -1,70 +0,0 @@
-#!/usr/bin/env ruby
-#
-# Created by John Chilton
-#
-# Run libra quantification against protein prophet results.
-#
-#
-
-require 'protk/constants'
-require 'protk/protxml'
-require 'protk/galaxy_util'
-require 'optparse'
-
-for_galaxy = GalaxyUtil.for_galaxy?
-
-protxml_path = ARGV.shift
-
-if for_galaxy
-  protxml_path = GalaxyUtil.stage_protxml(protxml_path)
-end
-
-protxml = ProtXML.new(protxml_path)
-pepxml_path = protxml.find_pep_xml()
-
-genv=Constants.new
-
-option_parser=OptionParser.new()
-
-reagents = []
-mass_tolerance = "0.2"
-option_parser.on( '--mass-tolerance TOL',"Specifies the mass tolerance (window libra will search for the most intense m/z value in)." ) do |tol|
-  mass_tolerance = tol
-end
-
-option_parser.on( '--reagent MZ', "Specify a reagent (via m/z values).") do |reagent|
-  reagents << reagent
-end
-
-minimum_threshold_string = ""
-option_parser.on( '--minimum-threshold THRESH', "Minimum threshhold intensity (not required).") do |thresh|
-  minimum_threshold_string = "<minimumThreshhold value=\"#{thresh}\"/>"
-end
-
-option_parser.parse!
-
-
-reagent_strings = reagents.map do |reagent|
-  "<reagent mz=\"#{reagent}\" />"
-end
-reagents_string = reagent_strings.join(" ")
-
-isotopic_contributions = ""
-
-condition_contents = "<SUMmOnCondition description=\"libra_galaxy_run\">
-  <fragmentMasses>
-    #{reagents_string}
-  </fragmentMasses>
-  #{isotopic_contributions}
-  <massTolerance value=\"#{mass_tolerance}\"/>
-  <centroiding type=\"2\" iterations=\"1\"/>
-  <normalization type=\"4\"/>
-  <targetMs level=\"2\"/>
-  <output type=\"1\"/>
-  <quantitationFile name=\"quantitation.tsv\"/>
-  #{minimum_threshold_string}
-</SUMmOnCondition>"
-File.open("condition.xml", "w") { |f| f.write(condition_contents) }
-print condition_contents
-command="#{genv.librapeptideparser} '#{pepxml_path}' -ccondition.xml; #{genv.libraproteinratioparser} '#{protxml_path}' -c#{condition_file}"
-%x[#{command}]

data/bin/toppas_pipeline.rb

@@ -1,84 +0,0 @@
-#!/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([: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 = ""
-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.options.threads = "1"
-tool.option_parser.on( '--threads t',"Number of threads to use" ) do |tr|
-  tool.options.threads=tr
-end
-
-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
-
-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 = "#{Pathname.new(Tempfile.new(tool.toppas_file).path).basename.to_s}.trf"
-
-generate_trf(ARGV,trf_path)
-
-cmd=""
-cmd<<"export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:#{genv.openms_root}/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} -threads #{tool.threads}"
-
-run_pipeline(genv,tool,cmd,tool.outdir,tool.jobid_from_filename(tool.toppas_file))
-

data/bin/uniprot_annotation.rb

@@ -1,141 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of Protk
-# Created by Ira Cooke 24/3/2013
-#
-# Retrieve annotation information for proteins from the Uniprot Swissprot database
-#
-# 
-require 'protk/constants'
-require 'protk/command_runner'
-require 'protk/tool'
-require 'protk/swissprot_database'
-require 'protk/bio_sptr_extensions'
-
-
-# Setup specific command-line options for this tool. Other options are inherited from Tool
-#
-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"
-
-tool.options.id_column=1
-tool.option_parser.on(  '--id-column num', 'Specify a column for ids (default is column 1)' ) do |col|
-  tool.options.id_column=col.to_i
-end
-
-tool.options.flatfiledb="swissprot"
-tool.option_parser.on(  '--flatfiledb dbname', 'Specify path to a Uniprot flatfile' ) do |dbname|
-  tool.options.flatfiledb=dbname
-end
-
-tool.options.fields=nil
-tool.option_parser.on(  '--fields flds', 'A comma separated list of fields to extract' ) do |flds|
-  tool.options.fields=flds
-end
-
-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
-
-input_file=ARGV[0]
-
-swissprotdb=SwissprotDatabase.new(genv,tool.flatfiledb)
-
-output_file=nil
-
-if ( tool.explicit_output==nil)
-  output_file=$stdout
-else
-  output_file=File.open(tool.explicit_output,'w+')
-end
-
-ac_column = tool.id_column-1
-
-db_fields = {
-  'recname'=>"Primary Name",
-  'cd'=>"CD Antigen Name",
-  'altnames'=>"Alternate Names", 
-  'location' => "Subcellular Location",
-  'function' => "Known Function",
-  'similarity' => "Similarity",
-  'tissues' => "Tissue Specificity",
-  'disease' => "Disease Association",
-  'domain' => "Domain",
-  'subunit' => "Sub Unit",
-  'nextbio' => "NextBio",
-  'ipi' => "IPI",
-  'intact' => "Interactions",
-  'pride' => 'Pride',
-  'ensembl'=> 'Ensembl',
-  'num_transmem'=>"Transmembrane Regions",
-  'signalp'=>'Signal Peptide',
-  'ref_dump'=>'References',
-  'tax_dump'=>'Taxonomy Cross Ref',
-  'species_dump'=>'Species',
-  'feature_dump'=>'Feature Table',
-  'seq_dump' => 'AA Sequence'
-  }
-
-hyperlink_fields = {
-  'uniprot_link'=>"Uniprot Link",
-  'nextbio_link'=>'NextBio Link',
-  'intact_link'=>"Interactions Link",
-  'pride_link'=>"Pride Link",
-  'ensembl_link'=>"Ensembl Link"
-}
-
-if tool.fields !=nil
-  fields = tool.fields.split(",").collect { |f| f.lstrip.rstrip }.reject {|e| e.empty? }
-  db_fields = db_fields.select { |k| fields.include? k }
-  hyperlink_fields = hyperlink_fields.select { |k| fields.include? k}
-end
-
-output_file.write db_fields.values.join("\t")
-if ( hyperlink_fields.count > 0 )
-  output_file.write("\t")
-  output_file.write hyperlink_fields.values.join("\t")
-end
-output_file.write("\n")
-
-line_num=0
-File.foreach(input_file) { |line|  
-  input_cols=line.split("\t")
-  throw "Not enough columns in line #{line_num}" unless input_cols.count > ac_column
-  accession=input_cols[ac_column].chomp
-
-  sptr_entry=swissprotdb.get_entry_for_name(accession)
-
-  if ( sptr_entry==nil)
-    genv.log("No entry for #{accession} in uniprot database",:warn)  
-  else
-
-    db_values = db_fields.collect { |key,value|     
-      sptr_entry.send(key)
-    }
-
-    hyperlink_values = hyperlink_fields.collect { |key,value|
-      sptr_entry.send(key)
-    }
-
-    output_file.write db_values.join("\t")
-    if ( hyperlink_fields.count > 0 )
-      output_file.write("\t")
-      output_file.write hyperlink_values.join("\t")
-    end
-    output_file.write "\n"
-  end
-
-  line_num+=1
-
-}
-
-
-

data/bin/xls_to_table.rb

@@ -1,52 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Created by Ira Cooke 18/1/2011
-#
-# Converts an Excel Spreadsheet to a tab delimited table
-#
-#
-
-require 'protk/constants'
-require 'protk/command_runner'
-require 'protk/tool'
-require 'spreadsheet'
-
-# Setup command-line options for this tool. 
-#
-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"
-
-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]
-
-output_file=tool.explicit_output
-output_file="#{input_file}.csv" unless ( output_file != nil )
-
-output_fh = File.new(output_file,'w')
-
-
-# Open the original excel workbook for reading
-Spreadsheet.client_encoding = 'UTF-8'   
-inputBook = Spreadsheet.open "#{input_file}"
-inputSheet = inputBook.worksheet 0
-
-inputSheet.each do |row|
-  line=""
-  row.each do |colv| 
-    line << "#{colv}\t" 
-  end
-  line.chop!
-  output_fh.write "#{line}\n"
-end
-
-output_fh.close
-
-

data/bin/xpress.rb

@@ -1,27 +0,0 @@
-#!/usr/bin/env ruby
-#
-# Created by John Chilton
-#
-# Run XPRESS against protein prophet results.
-#
-#
-
-require 'protk/constants'
-require 'protk/protxml'
-require 'protk/galaxy_util'
-
-for_galaxy = GalaxyUtil.for_galaxy?
-
-protxml_path = ARGV.shift
-
-if for_galaxy
-  protxml_path = GalaxyUtil.stage_protxml(protxml_path)
-end
-
-protxml = ProtXML.new(protxml_path)
-pepxml_path = protxml.find_pep_xml()
-
-genv=Constants.new
-
-command="#{genv.xpresspeptideparser} '#{pepxml_path}' #{ARGV.join(" ")} ; #{genv.xpressproteinratioparser} '#{protxml_path}'"
-%x[#{command}]

data/ext/protk/decoymaker/extconf.rb

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

data/ext/protk/simplealign/extconf.rb

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

data/lib/protk/biotools_excel_converter.rb

@@ -1,60 +0,0 @@
-require 'rubygems'
-require 'spreadsheet'
-
-
-class BioToolsExcelConverter 
-  
-  def initialize(filename)
-    @inputBook = Spreadsheet.open File.new("#{filename}")
-  end
-  
-  def self.isBiotools(filename)
-    testBook = Spreadsheet.open File.new("#{filename}")
-    testSheet = testBook.worksheet 0
-    
-    isbiotools=FALSE
-    testSheet.each do |row|
-      if  (row[0].class==String) && row[0].match(/Digest Matches.*?Score:\s(.*)\)/)   
-        isbiotools=TRUE
-      end
-    end
-    
-    
-    isbiotools
-  end
-  
-  def get_rows
-    
-    sheet=@inputBook.worksheet 0
-    
-    protein_rows=[]
-
-    n_rows=sheet.dimensions[1]
-
-    protein_rows=(0...n_rows).collect do |row_i|      
-      new_row=nil
-      
-      row=sheet.row row_i      
-      if ( row[0]!=nil)
-        digmatch=row[0].match(/Digest Matches.*?Score:\s(.*)\)/)
-        if  ( digmatch!=nil )
-          new_row=[]          
-          text= sheet.row(row_i-1)[0] 
-          m=text.match(/\s(\S*)\s*$/)
-          throw "Badly formed protein line in biotools file ... could not parse protein name from #{text}" unless m!=nil
-          new_row[0]=m[1]
-          new_row[1]=digmatch[1]
-        end
-      end
-      
-      new_row
-    end
-    
-    protein_rows.compact!
-    protein_rows.insert(0,["Accession","Ion Scores"])
-    
-    protein_rows
-    
-  end
-  
-end

data/lib/protk/eupathdb_gene_information_table.rb

@@ -1,158 +0,0 @@
-# Code for interacting with EuPathDB gene information files e.g. http://cryptodb.org/common/downloads/release-4.3/Cmuris/txt/CmurisGene_CryptoDB-4.3.txt
-# These gene information files contain a large amount of information about individual genes/proteins in EuPathDBs.
-
-require 'tempfile'
-
-# A class for extracting gene info from a particular gene from the information file
-class EuPathDBGeneInformationFileExtractor
-  # A filename path to the gene information file
-  attr_accessor :filename
-  
-  def initialize(filename = nil)
-    @filename = filename
-  end
-  
-  # Returns a EuPathDBGeneInformation object corresponding to the wanted key. If
-  # there are multiple in the file, only the first is returned. If none are found, nil is returned.
-  #
-  # If grep_hack_lines is defined (as an integer), then a shortcut is applied to speed things up. Before parsing the gene info file, grep some lines after the "Gene Id: .." line. Then feed that into the parser. 
-  def extract_gene_info(wanted_gene_id, grep_hack_lines = nil)
-    inside_iterator = lambda do |gene|
-      return gene if wanted_gene_id == gene.info['Gene Id']
-    end
-    
-    filename = @filename
-    p @filename
-    if grep_hack_lines and grep_hack_lines.to_i != 0
-      tempfile=Tempfile.new('reubypathdb_grep_hack')
-      # grep however many lines from past the point. Rather dodgy, but faster.
-      raise Exception, "grep_hack_lines should be an integer" unless grep_hack_lines.is_a?(Integer)
-      `grep -A #{grep_hack_lines} 'Gene Id: #{wanted_gene_id}' '#{@filename}' >#{tempfile.path}`
-      EuPathDBGeneInformationTable.new(File.open(tempfile.path)).each do |gene|
-        return inside_iterator.call(gene)
-      end
-    else
-      # no grep hack. Parse the whole gene information file
-      EuPathDBGeneInformationTable.new(File.open(@filename)).each do |gene|
-        return inside_iterator.call(gene)
-      end
-    end
-    return nil
-  end
-end
-
-# A class for parsing the 'gene information table' files from EuPathDB, such
-# as http://cryptodb.org/common/downloads/release-4.3/Cmuris/txt/CmurisGene_CryptoDB-4.3.txt
-#
-# The usual way of interacting with these is the use of the each method, 
-# which returns a EuPathDBGeneInformation object with all of the recorded
-# information in it.
-class EuPathDBGeneInformationTable
-  include Enumerable
-  
-  # Initialise using an IO object, say File.open('/path/to/CmurisGene_CryptoDB-4.3.txt'). After opening, the #each method can be used to iterate over the genes that are present in the file
-  def initialize(io)
-    @io = io
-  end
-  
-  # Return a EuPathDBGeneInformation object with
-  # the contained info in it, one at a time
-  def each
-    while g = next_gene
-      yield g
-    end
-  end
-  
-  # Returns a EuPathDBGeneInformation object with all the data you could
-  # possibly want.
-  def next_gene
-    info = EuPathDBGeneInformation.new
-    
-    # first, read the table, which should start with the ID column
-    line = @io.readline.strip
-    while line == ''
-      return nil if @io.eof?
-      line = @io.readline.strip
-    end
-    
-    while line != ''
-      if matches = line.match(/^(.*?)\: (.*)$/)
-        info.add_information(matches[1], matches[2])
-      else
-        raise Exception, "EuPathDBGeneInformationTable Couldn't parse this line: #{line}"
-      end
-      
-      line = @io.readline.strip
-    end
-    
-    # now read each of the tables, which should start with the
-    # 'TABLE: <name>' entry
-    line = @io.readline.strip
-    table_name = nil
-    headers = nil
-    data = []
-    while line != '------------------------------------------------------------'
-      if line == ''
-        # add it to the stack unless we are just starting out
-        info.add_table(table_name, headers, data) unless table_name.nil?
-        
-        # reset things
-        table_name = nil
-        headers = nil
-        data = []
-      elsif matches = line.match(/^TABLE\: (.*)$/)
-        # name of a table
-        table_name = matches[1]
-      elsif line.match(/^\[.*\]/)
-        # headings of the table
-        headers = line.split("\t").collect do |header|
-          header.gsub(/^\[/,'').gsub(/\]$/,'')
-        end
-      else
-        # a proper data row
-        data.push line.split("\t")
-      end
-      line = @io.readline.strip      
-    end
-            
-    # return the object that has been created
-    return info
-  end
-end
-
-# Each gene in the gene information table is represented
-# by 2 types of information - info and tables.
-# info are 1 line data, whereas tables are tables of
-# data with possibly multiple rows
-class EuPathDBGeneInformation
-  def info
-    @info
-  end
-  
-  def get_info(key)
-    @info[key]
-  end
-  alias_method :[], :get_info
-  
-  def get_table(table_name)
-    @tables[table_name]
-  end
-  
-  def add_information(key, value)
-    @info ||= {}
-    @info[key] = value
-    "Added info #{key}, now is #{@info[key]}"
-  end
-  
-  def add_table(name, headers, data)
-    @tables ||= {}
-    @tables[name] = []
-    data.each do |row|
-      final = {}
-      row.each_with_index do |cell, i|
-        final[headers[i]] = cell
-      end
-      @tables[name].push final
-    end
-  end
-end