ms-quant 0.0.1

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/LICENSE

@@ -0,0 +1,21 @@
+Copyright (c) 2011 Brigham Young University
+authored by John T. Prince
+
+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 +1,9 @@
+= ms-quant
+
+Tools for the quantitation of mass spectrometry proteomics experiments.  This
+is not associated with {MSQuant}[http://msquant.sourceforge.net] although the
+goals are similar.
+
+== Copyright
+
+See LICENSE

data/Rakefile

@@ -0,0 +1,49 @@
+require 'rubygems'
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "ms-quant"
+  gem.homepage = "http://github.com/princelab/ms-quant"
+  gem.license = "MIT"
+  gem.summary = %Q{quantitation of mass spectrometry datasets (proteomic, metabolomic/lipidomic)}
+  gem.description = %Q{quantitation of mass spectrometry datasets (proteomic, metabolomic/lipidomic).  Not related to MSQuant}
+  gem.email = "jtprince@gmail.com"
+  gem.authors = ["John T. Prince"]
+  # Include your dependencies below. Runtime dependencies are required when using your gem,
+  # and development dependencies are only needed for development (ie running rake tasks, tests, etc)
+  #  gem.add_runtime_dependency 'jabber4r', '> 0.1'
+  #  gem.add_development_dependency 'rspec', '> 1.2.3'
+  gem.add_runtime_dependency 'ms-ident', ">= 0.0.19"
+  gem.add_development_dependency "spec-more", ">= 0"
+  gem.add_development_dependency "jeweler", "~> 1.5.2"
+  gem.add_development_dependency "rcov", ">= 0"
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.verbose = true
+end
+
+require 'rcov/rcovtask'
+Rcov::RcovTask.new do |spec|
+  spec.libs << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.verbose = true
+end
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "ms-quant #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/bin/peptide_hit_qvalues_to_spectral_counts_table.rb

@@ -0,0 +1,126 @@
+#!/usr/bin/env ruby
+
+require 'ms/ident/peptide_hit/qvalue'
+require 'ms/ident/protein_hit'
+require 'ms/ident/peptide/db'
+require 'ms/quant/spectral_counts'
+
+require 'trollop'
+
+def putsv(*args)
+  if $VERBOSE
+    puts(*args) ; $stdout.flush
+  end
+end
+
+opts = Trollop::Parser.new do
+  banner %Q{usage: #{File.basename(__FILE__)} peptide_centric_db.yml, file1.psq ...
+}
+  opt :names, "array of names for the table (otherwise filenames)", :type => String
+  opt :fdr_percent, "%FDR as cutoff", :default => 1.0
+  opt :write_subset, "(development) write subset db", :default => false
+end
+
+opt = opts.parse(ARGV)
+
+if ARGV.size < 2
+  opts.educate && exit
+end
+
+peptide_centric_db_file = ARGV.shift
+
+opt[:names] ||= ARGV.map do |file| 
+  base = file.chomp(File.extname(file))
+  base=base.chomp(File.extname(base)) if File.extname(base) == '.phq'
+  base
+end
+
+class Ms::Ident::PeptideHit
+  attr_accessor :experiment_name
+end
+fdr_cutoff = opt[:fdr_percent] / 100
+
+start=Time.now
+
+$VERBOSE = true
+
+ar_of_peptide_hit_ars = Ms::Ident::Peptide::Db::IO.open(peptide_centric_db_file) do |peptide_to_proteins|
+  putsv "#{Time.now-start} seconds to read #{peptide_centric_db_file}"
+  ARGV.zip(opt[:names]).map do |file,exp| 
+    peptide_hits = Ms::Ident::PeptideHit::Qvalue.from_file(file)
+    putsv "#{file}: #{peptide_hits.size} hits"
+    peptide_hits.select! do |hit|
+      if hit.qvalue <= fdr_cutoff
+        # update each peptide with its protein hits
+        prot_ids = peptide_to_proteins[hit.aaseq]
+        if prot_ids
+          hit.experiment_name = exp
+          hit.proteins = prot_ids
+        else ; false end
+      else
+        false
+      end
+    end
+    peptide_hits
+  end
+end
+
+if opt[:write_subset] 
+  aaseqs_to_prots = {} 
+  ar_of_peptide_hit_ars.each do |pephits|
+    pephits.each do |pephit|
+      aaseqs_to_prots[pephit.aaseq] = pephit.proteins
+    end
+  end
+  outfile = "peptidecentric_subset.yml"
+  puts "writing #{outfile} with #{aaseqs_to_prots.size} aaseq->protids"
+  File.open(outfile,'w') do |out| 
+    aaseqs_to_prots.each do |k,v| 
+      out.puts(%Q{#{k}: #{v.map(&:id).join("\t") }}) 
+    end
+  end
+end
+
+$VERBOSE = true
+if $VERBOSE
+  opt[:names].zip(ar_of_peptide_hit_ars) do |name, pep_ar|
+    puts "#{name}: #{pep_ar.size}"
+  end
+end
+
+all_peptide_hits = ar_of_peptide_hit_ars.flatten(1)
+
+
+# because peptide_hit#proteins yields id strings (which hash properly),
+# each protein group is an array of 
+protein_groups = Ms::Ident::ProteinGroup.peptide_hits_to_protein_groups(all_peptide_hits)
+
+pephit_to_protein_groups = Hash.new {|h,k| h[k] = [] }
+protein_groups.each do |protein_group|
+  protein_group.peptide_hits.each {|hit| pephit_to_protein_groups[hit] << protein_group }
+end
+
+# partition them all out by filename
+
+ar_of_count_data = opt[:names].map do |name|
+  pep_hit_to_prot_groups = Hash.new {|h,k| h[k] = [] }
+  groups_of_pephits = protein_groups.map do |prot_group|
+    pep_hits = prot_group.peptide_hits.select {|hit| hit.experiment_name == name }
+    pep_hits.each do |pep_hit|
+      pep_hit_to_prot_groups[pep_hit] << prot_group
+    end # returns the group of pep_hits
+  end
+  counts = Ms::Quant::SpectralCounts.counts(groups_of_pephits) # do |pephit|
+  #  pephit_to_protein_groups[pephit].size
+  #end
+end
+
+# protein_groups
+# [ ar_of_counts_for_exp1, ar_of_counts_for_exp2, ar_of_counts_for_exp3 ]
+
+protein_groups.zip(*ar_of_count_data) do |row|
+  pg = row.shift
+  puts (row.map(&:to_a).flatten + pg.to_a).join("\t")
+end
+
+

data/lib/ms/quant/spectral_counts.rb

@@ -0,0 +1,35 @@
+require 'set'
+require 'ms/ident/protein_group'
+
+module Ms
+  module Quant
+    module SpectralCounts
+      Counts = Struct.new(:spectral, :aaseqcharge, :aaseq)
+
+      # returns a parallel array of Count objects.  If split_hits then counts
+      # are split between groups sharing the hit.  peptide_hits must respond
+      # to :charge and :aaseq.  If split_hits, then each peptide_hit must
+      # respond to :linked_to yielding an object with a :size reflective of
+      # the number of shared peptide_hits.
+      def self.counts(groups_of_peptide_hits, &share_the_pephit)
+        groups_of_peptide_hits.map do |peptide_hits|
+          uniq_aaseq = {}
+          uniq_aaseq_charge = {}
+          linked_sizes = peptide_hits.map do |hit|
+            linked_to_size = share_the_pephit ? share_the_pephit.call(hit) : 1
+            # these guys will end up clobbering themselves, but the
+            # linked_to_size should be consistent if the key is the same
+            uniq_aaseq_charge[[hit.aaseq, hit.charge]] = linked_to_size
+            uniq_aaseq[hit.aaseq] = linked_to_size
+            linked_to_size
+          end
+          counts_data = [linked_sizes, uniq_aaseq_charge.values, uniq_aaseq.values].map do |array|
+            share_the_pephit ?  array.inject(0.0) {|sum,size| sum+=(1.0/size) } : array.size
+          end
+          Counts.new(*counts_data)
+        end
+      end
+
+    end
+  end
+end

data/spec/ms/quant/spectral_counts_spec.rb

@@ -0,0 +1,67 @@
+require 'spec_helper'
+
+require 'ms/quant/spectral_counts'
+
+
+
+PeptideHit = Struct.new(:aaseq, :charge, :proteins) do
+  def initialize(*args)
+    super(*args)
+    self.proteins ||= []
+  end
+  def inspect # easier to read output
+    "<PeptideHit aaseq=#{self.aaseq} charge=#{self.charge} proteins(ids)=#{self.proteins.map(&:id).join(',')}>"
+  end
+  def hash ; self.object_id end
+end
+ProteinHit = Struct.new(:id, :peptide_hits) do
+  def inspect # easier to read output
+    "<Prt #{self.id}>"
+  end
+  def hash ; self.object_id end
+end
+
+describe 'groups of peptide hits' do
+  before do
+    @pep_hits = [ 
+      ['AABBCCDD', 2], #bg,mg1,mg2 0.33
+      ['BBCC', 2],     #bg,mg1,mg2 0.33
+      ['DDEEFFGG', 2], #bg,mg1,mg2,sbm 0.25
+      ['DDEEFFGG', 2], #bg,mg1,mg2,sbm 0.25
+      ['DDEEFFGG', 3], #bg,mg1,mg2,sbm 0.25
+      ['HIYA', 2],     #bg,lg 0.5
+    ].map {|ar| PeptideHit.new(*ar) }
+    @prot_hits = {
+                              # spectral_counts, aaseq+charge counts, aaseq counts
+      'big_guy' => @pep_hits, # 6, 5, 4; 
+      'little_guy' => [@pep_hits.last], # 1, 1, 1, 0.5, 0.5, 0.5
+      'medium_guy1' => @pep_hits[0,5], # 5, 4, 3 
+      'medium_guy2' => @pep_hits[0,5], # 5, 4, 3 
+      'subsumed_by_medium' => @pep_hits[2,3], # 3, 2, 1
+    }.map {|data| ProteinHit.new(*data) }
+    # doubly linked for this
+    @prot_hits.each do |prot| 
+      prot.peptide_hits.each {|pephit| pephit.proteins << prot }
+    end
+    # DEPENDS ON AN ORDERED HASH (RUBY 1.9!!!!)
+    @expected_counts = [ [6,5,4], [1,1,1], [5,4,3], [5,4,3], [3,2,1] ]
+    @expected_counts_split = [ [1.9167,1.6667,1.4167], [0.5,0.5,0.5], [1.41667, 1.1667, 0.91667], [1.41667, 1.16667, 0.91667], [0.75, 0.5, 0.25] ]
+  end
+
+  it 'finds spectral counts (without sharing)' do
+    groups_of_pephits = @prot_hits.map(&:peptide_hits)
+    counts = Ms::Quant::SpectralCounts.counts(groups_of_pephits)
+    @expected_counts.zip(counts) do |exp, act|
+      act.to_a.is exp
+    end
+  end
+
+  it 'finds spectral counts (splitting counts between shared)' do
+    groups_of_pephits = @prot_hits.map(&:peptide_hits)
+    counts = Ms::Quant::SpectralCounts.counts(groups_of_pephits) {|pephit| pephit.proteins.size }
+    @expected_counts_split.zip(counts) do |exp, act|
+      exp.zip(act) {|e,a| a.should.be.close e, 0.0001 }
+    end
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,7 @@
+require 'rubygems'
+require 'spec/more'
+
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+
+Bacon.summary_on_exit

metadata

@@ -0,0 +1,129 @@
+--- !ruby/object:Gem::Specification 
+name: ms-quant
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- John T. Prince
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-03-30 00:00:00 -06:00
+default_executable: peptide_hit_qvalues_to_spectral_counts_table.rb
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: ms-ident
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 0
+        - 19
+        version: 0.0.19
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: spec-more
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: jeweler
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 1
+        - 5
+        - 2
+        version: 1.5.2
+  type: :development
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: rcov
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id004
+description: quantitation of mass spectrometry datasets (proteomic, metabolomic/lipidomic).  Not related to MSQuant
+email: jtprince@gmail.com
+executables: 
+- peptide_hit_qvalues_to_spectral_counts_table.rb
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- LICENSE
+- README.rdoc
+- Rakefile
+- bin/peptide_hit_qvalues_to_spectral_counts_table.rb
+- lib/ms-quant.rb
+- lib/ms/quant/spectral_counts.rb
+- spec/ms/quant/spectral_counts_spec.rb
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: http://github.com/princelab/ms-quant
+licenses: 
+- MIT
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: quantitation of mass spectrometry datasets (proteomic, metabolomic/lipidomic)
+test_files: 
+- spec/ms/quant/spectral_counts_spec.rb
+- spec/spec_helper.rb