mspire-sequest 0.2.5

data/.autotest

@@ -0,0 +1,30 @@
+# -*- ruby -*-
+
+require 'rubygems'
+require 'spec/more'
+require 'autotest/bacon'
+#require 'redgreen/autotest'
+
+class Autotest::Bacon < Autotest
+    undef make_test_cmd
+    def make_test_cmd(files_to_test)
+        args = files_to_test.keys.flatten.join(' ')
+        args = '-a' if args.empty?
+        # TODO : make regex to pass to -n using values
+        "#{ruby} -S bacon -I#{libs} -o TestUnit #{args}"
+    end
+end
+
+
+#Autotest.add_hook :initialize do |at|
+# at.clear_mappings
+#end
+
+#Autotest.add_hook :initialize do |at|
+#at.add_mapping(%r%^lib/(.*)\.rb$%) { |_, m|
+#    #["spec/#{m[1]}_spec.rb"]
+#    #["test/#{m[1]}_test.rb"]
+#    ## for both specs and tests:
+#    ["spec/#{m[1]}_spec.rb"]
+#}
+#end

data/.gitmodules

@@ -0,0 +1,9 @@
+[submodule "submodule/ms-testdata"]
+	path = submodule/ms-testdata
+	url = git://github.com/bahuvrihi/ms-testdata.git
+[submodule "submodule/ms-in_silico"]
+	path = submodule/ms-in_silico
+	url = git://github.com/bahuvrihi/ms-in_silico.git
+[submodule "submodule/tap-mechanize"]
+	path = submodule/tap-mechanize
+	url = git://github.com/bahuvrihi/tap-mechanize.git

data/History

@@ -0,0 +1,79 @@
+== 0.2.0 / 2011-09-13
+
+Breaking backwards compatbility.  Based on new msplat gem instead of ms-core, ms-ident, etc.  MS module instead of Ms module.
+
+== 0.1.0 / 2011-04-11
+
+* moved Arrayclass objects to Struct objects
+
+== 0.0.15 / 2010-08-25
+
+* Fixed another bug in the srf_to_sqt.rb commandline when called without an output file
+
+== 0.0.14 / 2010-08-24
+
+* Merged commandline programs into lib heirarchy for testing
+* Wrote specs for commandline programs (shared spec with programmatic interface)
+
+== 0.0.13 / 2010-08-16
+
+* compatible with ruby 1.9
+* simplified Rakefile, ditching efforts at gh-pages converter for now
+* removed dependency on Tap
+
+== 0.0.12 / 2010-01-01
+
+* moved over to jeweler and tests to bacon (spec/more)
+
+== 0.0.11 / 2010-01-01
+
+* peptides have sf value (read from srf file)
+
+== 0.0.10 / 2009-12-03
+
+* turned off warning if print_duplicates == 0
+
+== 0.0.9 / 2009-09-08
+
+* added capability to read srf files created by reading in .out/.dta folders (combined).
+  NOTE: please consider this functionality beta stage as it has not been extensively tested!
+* cleaned up the read_dta_files function since we don't need measured_mhs as we do that later
+
+== 0.0.8 / 2009-06-29
+
+* bugfix - only applies to windows: fixes an error on windows opening srf files and searching for the internal sequest.params file.  File.open(<srf>) -> File.open(<srf>, 'rb').
+
+== 0.0.7 / 2009-06-26
+
+* minor bug fix in srf to sqt output in compatibility with current ms-core ms/mass tables
+
+== 0.0.6 / 2009-06-26
+
+* fixed bug affecting only version 0.0.5 in srf reader affecting any file where print_duplicate_references was less than the number of protein references found for a peptide, but also > 0.
+* so, the srf reader now robustly supports reading srf files regardless of print_duplicate_references setting.
+
+== 0.0.5 / 2009-06-22
+
+* fixed handling of files with print_duplicate_references = 0
+* removes .hdr postfix on the fasta path for srf -> SQT output
+
+== 0.0.4 / 2009-06-18
+
+* srf_to_sqt.rb and srf_to_search.rb both working now
+
+== 0.0.3 / 2009-06-16
+
+* only dependent on very simple ms/fasta interface, no more on digest info, etc.
+
+== 0.0.2 / 2009-05-14
+
+* Basic SRF to SQT translation working
+* SQT reading working
+
+== 0.0.1 / 2009-05-11
+
+* pulled out of mspire core
+
+
+
+

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright shared among contributing institutions:
+Copyright (c) 2006-2008 University of Texas at Austin (the initial project)
+Copyright (c) 2009 Regents of the University of Colorado and Howard Hughes Medical Institute. (modularization of the project)
+Author: John T. Prince under direction of Edward Marcotte and Natalie Ahn
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.rdoc

@@ -0,0 +1,85 @@
+= ms-sequest
+
+An {mspire}[http://mspire.rubyforge.org] library supporting SEQUEST, Bioworks, SQT and associated formats.
+
+== {Current API}[http://rubydoc.info/gems/ms-sequest]
+
+== Examples
+
+Provides two executables for extracting information from an Srf file (run without file for usage):
+
+    srf_to_sqt.rb file.srf     # => file.sqt
+    srf_to_search.rb file.srf  # => file.mgf  (also can make .dta files)
+
+=== MS::Sequest::Srf
+
+Can read and convert Bioworks Sequest Results Files (SRF).
+
+    require 'ms/sequest/srf'
+    srf = MS::Sequest::Srf.new("file.srf")
+
+Conversions (see api for options):
+
+    require 'ms/sequest/srf/sqt'  # require this in addition to 'ms/sequest/srf'
+    srf.to_sqt            # (outputs a file) -> file.sqt
+
+    require 'ms/sequest/srf/search' # require this in addition to 'ms/sequest/srf'
+    srf.to_mgf            # (outputs a file) -> file.mgf
+    srf.to_dta            # (outputs a dir)  -> file
+    srf.to_dta("file.tgz", :tgz)  # on the fly tgz (requires archive-tar-minitar)
+
+Object access (see MS::Sequest::Srf for much more):
+
+    srf.header         # MS::Sequest::Srf::Header object
+    srf.params         # MS::Sequest::Params object
+    srf.dta_files      # MS::Sequest::Srf::Dta objects
+    srf.out_files      # MS::Sequest::Srf::Out objects
+    srf.peptide_hits   # MS::Sequest::Srf::Out::Peptide objects
+
+=== MS::Sequest::Params
+
+Object or hash access to any parameter in the file.  Also provides a unified interface across several versions (3.1 - 3.3)
+
+    require 'ms/sequest/params'
+    params = MS::Sequest::Params.new("sequest.params")
+    params.any_existing_param    # -> some value or empty string if no value
+    params['any_existing_param'] # -> some value or empty string if no value
+    params.non_existent_param    # -> nil
+
+    # some unified interace methods:
+    params.enzyme              # -> enzyme name with no parentheses
+    params.database            # -> first_database_name
+    params.enzyme_specificity  # -> [offset, cleave_at, expect_if_after]
+    params.precursor_mass_type  # => "average" | "monoisotopic"
+    params.fragment_mass_type   # => "average" | "monoisotopic"
+
+=== MS::Sequest::Sqt
+
+    sqt = MS::Sequest::Sqt.new("file.sqt")
+    sqt.header
+    sqt.spectra.each do |spectrum|      # an MS::Sequest::Sqt::Spectrum object
+      spectrum.matches.each do |match|    # an MS::Sequest::Sqt::Match object
+        match.loci.each do |locus|          # an MS::Sequest::Sqt::Locus object
+        end
+      end
+    end
+
+    # or more direct access to Match objects:
+    sqt.peptide_hits
+
+Also reads Percolator SQT output files intelligently:
+
+    psqt = MS::Sequest::Sqt.new("percolator_output.sqt")
+    psqt.peptide_hits.each do |pmatch|
+      pmatch.percolator_score  ==  pmatch.xcorr
+      pmatch.negative_q_value  ==  pmatch.sp
+      pmatch.q_value           ==  -pmatch.negative_q_value 
+    end
+
+== Installation
+
+    gem install ms-sequest
+
+== Copyright
+
+See LICENSE (MIT)

data/Rakefile

@@ -0,0 +1,52 @@
+require 'rubygems'
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  gem.name = "mspire-sequest"
+  gem.homepage = "http://github.com/princelab/mspire-sequest"
+  gem.license = "MIT"
+  gem.summary = %Q{An mspire library supporting SEQUEST, Bioworks, SQT, etc}
+  gem.description = %Q{reads .SRF, .SQT and supports conversions}
+  gem.email = "jtprince@gmail.com"
+  gem.authors = ["John T. Prince"]
+  gem.rubyforge_project = 'mspire'
+  gem.add_runtime_dependency "mspire", "~> 0.7.3"
+  gem.add_runtime_dependency "trollop", "~> 1.16"
+  gem.add_development_dependency "jeweler", "~> 1.5.2"
+  gem.add_development_dependency "bio", "~> 1.4.2"
+  gem.add_development_dependency "ms-testdata", "= 0.2.1"
+  gem.add_development_dependency "rspec", "~> 2.8.0"
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new
+
+#require 'rcov/rcovtask'
+#Rcov::RcovTask.new do |spec|
+#  spec.libs << 'spec'
+#  spec.pattern = 'spec/**/*_spec.rb'
+#  spec.verbose = true
+#end
+
+task :default => :spec
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "mspire-sequest #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+
+
+
+
+
+
+
+
+
+

data/VERSION

@@ -0,0 +1 @@
+0.2.5

data/bin/srf_to_pepxml.rb

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'mspire/sequest/srf/pepxml'
+
+Mspire::Sequest::Srf::Pepxml.commandline(ARGV, File.basename(__FILE__))
+

data/bin/srf_to_search.rb

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'mspire/sequest/srf/search'
+
+Mspire::Sequest::Srf::Search.commandline(ARGV, File.basename(__FILE__))
+

data/bin/srf_to_sqt.rb

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'mspire/sequest/srf/sqt'
+
+Mspire::Sequest::Srf::Sqt.commandline(ARGV, File.basename(__FILE__))
+
+

data/lib/mspire/sequest/params.rb

@@ -0,0 +1,331 @@
+require 'mspire/mass/aa'
+
+# In the future, this guy should accept any version of bioworks params file
+# and spit out any param queried.
+
+module Mspire ; end
+module Mspire::Sequest ; end
+
+# 1) provides a reader and simple parameter lookup for SEQUEST params files
+# supporting Bioworks 3.1-3.3.1.  
+#     params = Mspire::Sequest::Params.new("sequest.params") # filename by default
+#     params = Mspire::Sequest::Params.new.parse_io(some_io_object)
+#
+#     params.some_parameter  # => any parameter defined has a method
+#     params.nonexistent_parameter # => nil 
+#
+# Provides consistent behavior between different versions important info:
+#    
+#     # some basic methods shared by all versions:
+#     params.version              # => '3.1' | '3.2' | '3.3'
+#     params.enzyme               # => enzyme name with no parentheses
+#     params.min_number_termini 
+#     params.database             # => first_database_name 
+#     params.enzyme_specificity   # => [offset, cleave_at, expect_if_after]
+#     params.precursor_mass_type  # => "average" | "monoisotopic"
+#     params.fragment_mass_type   # => "average" | "monoisotopic"
+#
+#     # some backwards/forwards compatibility methods:
+#     params.max_num_internal_cleavages  # == max_num_internal_cleavage_sites
+#     params.fragment_ion_tol     # => fragment_ion_tolerance
+#     
+class Mspire::Sequest::Params
+
+  Bioworks31_Enzyme_Info_Array = [
+    ['No_Enzyme', 0, '-', '-'],   # 0
+    ['Trypsin', 1, 'KR', '-'],  # 1
+    ['Trypsin(KRLNH)', 1, 'KRLNH', '-'],  # 2
+    ['Chymotrypsin', 1, 'FWYL', '-'],  # 3
+    ['Chymotrypsin(FWY)', 1, 'FWY', 'P'],  # 4
+    ['Clostripain', 1, 'R', '-'],  # 5
+    ['Cyanogen_Bromide', 1, 'M', '-'],  # 6
+    ['IodosoBenzoate', 1, 'W', '-'],  # 7
+    ['Proline_Endopept', 1, 'P', '-'],  # 8
+    ['Staph_Protease', 1, 'E', '-'],  # 9
+    ['Trypsin_K', 1, 'K', 'P'],  # 10
+    ['Trypsin_R', 1, 'R', 'P'],  # 11
+    ['GluC', 1, 'ED', '-'],  # 12
+    ['LysC', 1, 'K', '-'],  # 13
+    ['AspN', 0, 'D', '-'],  # 14
+    ['Elastase', 1, 'ALIV', 'P'],  # 15
+    ['Elastase/Tryp/Chymo', 1, 'ALIVKRWFY', 'P'],  # 16
+  ]
+
+  # current attributes supported are:
+  # bioworks 3.2:
+  @@param_re = / = ?/o
+  @@param_two_split = ';'
+  @@sequest_line = /\[SEQUEST\]/o
+
+  # the general options
+  attr_accessor :opts
+  # the static weights added to amino acids
+  attr_accessor :mods
+
+  # all keys and values stored as strings!
+  # will accept a sequest.params file or .srf file
+  def initialize(file=nil)
+    if file
+      parse_file(file)
+    end
+  end
+
+  # returns hash of params up until add_U_user_amino_acid
+  def grab_params(fh)
+    hash = {}
+    in_add_amino_acid_section = false
+    add_section_re = /^\s*add_/
+      prev_pos = nil
+    while line = fh.gets
+      if line =~ add_section_re
+        in_add_amino_acid_section = true
+      end
+      if (in_add_amino_acid_section and !(line =~ add_section_re))
+        fh.pos = prev_pos
+        break
+      end
+      prev_pos = fh.pos
+      if line =~ /\w+/
+        one,two = line.split @@param_re
+        two,comment = two.split @@param_two_split
+        hash[one] = two.rstrip
+      end
+    end
+    hash
+  end
+
+  # returns self or nil if no sequest found in the io
+  def parse_io(fh)
+    # seek to the SEQUEST file
+    if fh.respond_to?(:set_encoding)
+      # this mimics ruby1.8 behavior as we read in the file
+      fh.set_encoding('ASCII-8BIT')
+    end
+    loop do
+      line = fh.gets
+      return nil if line.nil?  # we return nil if we reach then end of the file without seeing sequest params
+      if line =~ @@sequest_line
+        # double check that we are in a sequest params file:
+        pos = fh.pos
+        if fh.gets =~ /^first_database_name/
+          fh.pos = pos
+          break
+        end
+      end
+    end
+    @opts = grab_params(fh)
+    @opts["search_engine"] = "SEQUEST"
+    # extract out the mods
+    @mods = {}
+    @opts.each do |k,v|
+      if k =~ /^add_/
+        @mods[k] = @opts.delete(k)
+      end
+    end
+
+    ## this gets rid of the .hdr postfix on indexed databases
+    @opts["first_database_name"] = @opts["first_database_name"].sub(/\.hdr$/, '')
+    self
+  end
+
+  ## parses file
+  ## and drops the .hdr behind indexed fasta files
+  ## returns self
+  ## can read sequest.params file or .srf file handle
+  def parse_file(file)
+    File.open(file) do |fh|
+      parse_io(fh)
+    end
+    self
+  end
+
+  # returns( offset, cleave_at, except_if_after )
+  # offset is an Integer specifying how far after an amino acid to cut
+  # cleave_at is a string of all amino acids that should be cut at
+  # except_if_after for not cutting after those
+  # normal tryptic behavior would be: [1, 'KR', 'P']
+  # NOTE: a '-' in a params file is returned as an '' (empty string)
+  # AspN is [0,'D','']
+  def enzyme_specificity
+    enzyme_ar = 
+      if version == '3.1'
+        Bioworks31_Enzyme_Info_Array[@opts['enzyme_number'].to_i][1,3]
+      elsif version >= '3.2'
+        arr = enzyme_info.split(/\s+/)[2,3]
+        arr[0] = arr[0].to_i
+        arr
+      else
+        raise ArgumentError, "don't recognize anything but Bioworks 3.1--3.3"
+      end
+    enzyme_ar.map! do |str|
+      if str == '-' ; ''
+      else ; str
+      end
+    end
+    enzyme_ar
+  end
+
+  # Returns the version of the sequest.params file
+  # Returns String "3.3" if contains "fragment_ion_units"
+  # Returns String "3.2" if contains "enyzme_info"
+  # Returns String "3.1" if contains "enzyme_number"
+  def version
+    if @opts['fragment_ion_units'] ; return '3.3'
+    elsif @opts['enzyme_info'] ; return '3.2'
+    elsif @opts['enzyme_number'] ; return '3.1'
+    end
+  end
+
+  ####################################################
+  # TO PEPXML
+  ####################################################
+  # In some ways, this is merely translating to the older Bioworks
+  # sequest.params files
+
+  # I'm not sure if this is the right mapping for sequence_search_constraint?
+  def sequence
+    pseq = @opts['partial_sequence'] 
+    if !pseq || pseq == "" ; pseq = "0" end
+    pseq
+  end
+
+  def precursor_mass_type
+    case @opts['mass_type_parent']
+    when '0' ; "average" 
+    when '1' ; "monoisotopic"
+    else ; abort "error in mass_type_parent in sequest!"
+    end
+  end
+
+  def fragment_mass_type
+    fmtype = 
+      case @opts['mass_type_fragment']
+      when '0' ; "average"
+      when '1' ; "monoisotopic"
+      else ; abort "error in mass_type_fragment in sequest!"
+      end
+  end
+
+  def method_missing(name, *args)
+    string = name.to_s
+    if @opts.key?(string)    ; return @opts[string]
+    elsif @mods.key?(string) ; return @mods[string]
+    else                     ; return nil
+    end
+  end
+
+  ## We only need to define values if they are different than sequest.params
+  ## The method_missing will look them up in the hash!
+
+  # Returns a system independent basename
+  # Splits on "\" or "/"
+  def _sys_ind_basename(file)
+    return file.split(/[\\\/]/)[-1]
+  end
+
+  # changes the path of the database
+  def database_path=(newpath)
+    db = @opts["first_database_name"]
+    newpath = File.join(newpath, _sys_ind_basename(db))
+    @opts["first_database_name"] = newpath
+  end
+
+  def database
+    @opts["first_database_name"]
+  end
+
+  # returns the appropriate aminoacid mass lookup table from Mspire::Mass::AA
+  # based_on may be :precursor or :fragment
+  def mass_index(based_on=:precursor)
+    reply = case based_on
+            when :precursor ; precursor_mass_type
+            when :fragment ; fragment_mass_type
+            end
+    case reply
+    when 'average'
+      Mspire::Mass::AA::AVG
+    when 'monoisotopic'
+      Mspire::Mass::AA::MONO
+    end
+  end
+
+  # at least in Bioworks 3.2, the First number after the enzyme
+  # is the indication of the enzymatic end stringency (required):
+  #   1 = Fully enzymatic
+  #   2 = Either end
+  #   3 = N terminal only
+  #   4 = C terminal only
+  # So, to get min_number_termini we map like this:
+  #   1 => 2
+  #   2 => 1
+  def min_number_termini
+    if e_info = @opts["enzyme_info"]
+      case e_info.split(" ")[1]
+      when "1" ; return "2"
+      when "2" ; return "1"
+      end
+    end
+    warn "No Enzyme termini info, using min_number_termini = '1'"
+    return "1"
+  end
+
+  # returns the enzyme name (but no parentheses connected with the name).
+  # this will likely be capitalized.
+  # the regular expression splits the name and returns the first part (or just
+  # the name if not found)
+  def enzyme(split_on=/[_\(]/)
+    basic_name = 
+      if self.version == '3.1'
+        Bioworks31_Enzyme_Info_Array[ @opts['enzyme_number'].to_i ][0]
+      else    # v >= '3.2' applies to all later versions??
+        @opts["enzyme_info"]
+      end
+    name_plus_parenthesis = basic_name.split(' ',2).first
+    name_plus_parenthesis.split(split_on,2).first
+  end
+
+  def max_num_internal_cleavages
+    @opts["max_num_internal_cleavage_sites"]
+  end
+
+  # my take on peptide_mass_units:
+  # (see http://www.ionsource.com/tutorial/isotopes/slide2.htm)
+  # amu = atomic mass units = (mass_real - mass_measured).abs (??abs??)
+  # mmu = milli mass units (amu / 1000)
+  # ppm = parts per million = 10^6 * ∆m_accuracy / mass_measured  [ where ∆m_accuracy = mass_real – mass_measured ]
+
+  def peptide_mass_tol
+    if @opts["peptide_mass_units"] != "0"
+      puts "WARNING: peptide_mass_tol units need to be adjusted!"
+    end
+    @opts["peptide_mass_tolerance"]
+  end
+
+  def fragment_ion_tol
+    @opts["fragment_ion_tolerance"]
+  end
+
+  def max_num_differential_AA_per_mod
+    @opts["max_num_differential_AA_per_mod"] || @opts["max_num_differential_per_peptide"]
+  end
+
+  # returns a hash by add_<whatever> of any static mods != 0
+  # the values are still as strings
+  def static_mods
+    hash = {}
+    @mods.each do |k,v|
+      if v.to_f != 0.0
+        hash[k] = v
+      end
+    end
+    hash
+  end
+
+  ## @TODO: We could add some of the parameters not currently being asked for to be more complete
+  ## @TODO: We could always add the Bioworks 3.2 specific params as params
+
+  ####################################################
+  ####################################################
+
+end
+