mspire 0.7.9 → 0.7.10

data/VERSION

@@ -1 +1 @@
-0.7.9
+0.7.10

data/lib/mspire/isotope/aa.rb

@@ -1,10 +1,17 @@
+require 'mspire/molecular_formula'
+
+module Mspire
+  class MolecularFormula < Hash
+  end
+end
+
 
 module Mspire
   class Isotope
     module AA
       # These represent counts for the individual residues (i.e., no extra H
       # and OH on the ends)
-      ATOM_COUNTS_STR = {
+      aa_to_el_hash = {
         'A' => { :c =>3, :h =>5 , :o =>1 , :n =>1 , :s =>0 , :p =>0, :se =>0 },
         'R' => { :c =>6, :h =>12 , :o =>1 , :n =>4 , :s =>0 , :p =>0, :se =>0 },
         'N' => { :c =>4, :h =>6 , :o =>2 , :n =>2 , :s =>0 , :p =>0, :se =>0 },
@@ -28,11 +35,20 @@ module Mspire
         'U' => { :c =>3, :h =>5 , :o =>1 , :n =>1 , :s =>0 , :p =>0, :se =>1 },
         'O' => { :c =>12, :h =>19 , :o =>2 , :n =>3 , :s =>0 , :p =>0, :se =>0 }
       }
-      ATOM_COUNTS_SYM = Hash[ATOM_COUNTS_STR.map {|k,v| [k.to_sym, v] }]
 
-      # string and symbol access of amino acid (atoms are all lower case
-      # symbols)
-      ATOM_COUNTS = ATOM_COUNTS_SYM.merge ATOM_COUNTS_STR
+      # 
+      FORMULAS_STR = Hash[ 
+        aa_to_el_hash.map {|k,v| [k, Mspire::MolecularFormula.new(v)] }
+      ]
+
+      FORMULAS_SYM = Hash[FORMULAS_STR.map {|k,v| [k.to_sym, v] }]
+
+      # string and symbol access of amino acid residues (amino acids are
+      # accessed upper case and atoms are all lower case symbols)
+      FORMULAS = FORMULAS_SYM.merge FORMULAS_STR
+      
+      # an alias for FORMULAS
+      ATOM_COUNTS = FORMULAS
     end
   end
 end

data/lib/mspire/mass/aa.rb

@@ -3,6 +3,7 @@ require 'mspire/mass'
 module Mspire
   module Mass
     module AA
+
       # amino_acids keys as strings, average masses
       AVG_STRING = {
         "*"=>118.88603,
@@ -32,6 +33,7 @@ module Mspire
         "Y"=>163.17326,
         "Z"=>128.6231
       }
+
       # amino_acids keys as strings, monoisotopic masses
       MONO_STRING = {
         "*"=>118.805716,
@@ -69,10 +71,11 @@ module Mspire
       AVG_SYM = Hash[AVG_STRING.map {|aa,mass| [aa.to_sym, mass] } ]
 
       # Monoisotopic amino acid masses keyed as symbols and also strings (all
-      # upper case).  Also includes Mspire::Mass::MONO for things like protons ('h+')
+      # upper case).  Also includes Mspire::Mass::MONO for things like protons ('h+' and 'h2o')
       MONO = MONO_SYM.merge(MONO_STRING).merge(Mspire::Mass::MONO)
+
       # Average amino acid masses keyed as symbols and also strings (all
-      # uppder case).  Also includes Mspire::Mass::AVG for things like protons ('h+')
+      # uppder case).  Also includes Mspire::Mass::AVG for things like protons ('h+' and 'h2o')
       AVG = AVG_SYM.merge(AVG_STRING).merge(Mspire::Mass::AVG)
     end
   end

data/lib/mspire/mass.rb

@@ -16,6 +16,7 @@ module Mspire
       'e' => 0.0005486,   # www.mikeblaber.org/oldwine/chm1045/notes/Atoms/.../Atoms03.htm
       'neutron' => 1.0086649156,
     }
+
     Mspire::Isotope::BY_ELEMENT.each do |el, isotopes|
       MONO_STR[el.to_s] = isotopes.find {|iso| iso.mono }.atomic_mass
     end

data/lib/mspire/molecular_formula.rb

@@ -25,7 +25,7 @@ module Mspire
 
     def self.from_aaseq(aaseq)
       hash = aaseq.each_char.inject({}) do |hash,aa| 
-        hash.merge(Mspire::Isotope::AA::ATOM_COUNTS[aa]) {|h,o,n| (o ? o : 0) +n }
+        hash.merge(Mspire::Isotope::AA::FORMULAS[aa]) {|h,o,n| (o ? o : 0) +n }
       end
       hash[:h] += 2
       hash[:o] += 1

data/script/download_uniprotkb_db.rb

@@ -0,0 +1,146 @@
+#!/usr/bin/env ruby
+
+require 'optparse'
+require 'open-uri'
+require 'cgi'
+
+# see http://www.uniprot.org/faq/28
+
+# here are some example human files (tax ID = 9606)
+# CANONICAL SEQUENCES:
+# http://www.uniprot.org/uniprot/?query=taxonomy:9606&force=yes&format=fasta
+#   URL SAFE: 
+#   http://www.uniprot.org/uniprot/?query=taxonomy%3a9606&force=yes&format=fasta
+
+# CANONICAL + VARIANTS:
+# http://www.uniprot.org/uniprot/?query=taxonomy:9606&force=yes&format=fasta&include=yes
+#   URL SAFE: http://www.uniprot.org/uniprot/?query=taxonomy%3a9606&force=yes&format=fasta&include=yes
+
+
+FORMATS = %w(fasta gff xls tab txt xml rdf list)
+# list is just a list of accession numbers
+
+# include includes sequence variants (otherwise canonical)
+args = { :format => FORMATS.first, :force => 'yes', :include => 'yes', :compress => 'yes' }
+# force just makes the file a download (matters for browsers)
+
+# queries are in this format:
+# query=organism:9606+AND+organelle:mitochondrion
+
+#[OC] taxonomy
+#[OG] organelle
+
+TAXONOMY_BROWSER_URL = "http://www.ncbi.nlm.nih.gov/Taxonomy/taxonomyhome.html/index.cgi"
+
+=begin
+Y is a mnemonic species identification code of at most 5 alphanumeric
+characters representing the biological source of the protein. This
+code is generally made of the first three letters of the genus and
+the first two letters of the species. Examples: PSEPU is for
+Pseudomonas putida and NAJNI is for Naja nivea.
+
+However, for species commonly encountered in the data bank, self-
+explanatory codes are used. There are 16 of those codes. They are:
+BOVIN for Bovine, CHICK for Chicken, ECOLI for Escherichia coli,
+HORSE for Horse, HUMAN for Human, MAIZE for Maize (Zea mays) , MOUSE
+for Mouse, PEA for Garden pea (Pisum sativum), PIG for Pig, RABIT
+for Rabbit, RAT for Rat, SHEEP for Sheep, SOYBN for Soybean (Glycine
+max), TOBAC for Common tobacco (Nicotina tabacum), WHEAT for Wheat
+(Triticum aestivum), YEAST for Baker's yeast (Saccharomyces
+cerevisiae).
+
+BOVIN
+CHICK
+ECOLI
+HORSE
+HUMAN
+MAIZE
+MOUSE
+PEA
+PIG
+RABIT
+RAT
+SHEEP
+SOYBN
+TOBAC
+WHEAT
+YEAST
+
+=end
+
+TAXONOMY_IDS = 
+  { :human => [9606, 'Homo sapiens'],
+    :mouse => [10090, 'Mus musculus'],
+    :yeast => [4932, 'Saccharomyces cerevisiae'],
+    :ecoli => [562, 'Escherichia coli'],
+    :caeel => [6239, 'Caenorhabditis elegans'],
+    :drome => [7227, 'Drosophila melanogaster'],
+    :grpln => [33090, 'Viridiplantae'],
+  }
+
+def list_taxonomies
+  puts "  Key    ID     Genus/Species"
+  puts "  =====  =====  ============="
+  puts( TAXONOMY_IDS.map {|k,v| "  %s %6d  %s" % [k,*v] }.join("\n") )
+  puts ""
+  puts "See #{TAXONOMY_BROWSER_URL}"
+  true
+end
+
+opts = OptionParser.new do |op|
+  op.banner = "usage: #{File.basename(__FILE__)} <5-Letter-Species-Name|taxID>"
+  op.separator ""
+  op.separator "   requires 5-letter key (Swiss-Prot Mnemonic) (-l to see list)"
+  op.separator "   (note that outside the core ~12, these are just made up)"
+  op.separator "   or the actual NCBI taxonomy ID"
+  op.separator "   [add your key to TAXONOMY_IDS if you want]"
+  op.separator ""
+  op.on("-l", "--list-species", "lists available species and exits") { list_taxonomies && exit }
+  op.on("-c", "--canonical", "don't include sequence variants") { args[:include] = 'no' }
+  op.on("--no-compress", "don't compress the file") { args[:compress] = 'no' }
+  op.on("-f", "--format <string>", "Format type.  One of (1st is default):", "    #{FORMATS.join(' ')}") do |v| 
+    raise ArgumentError, "format needs to be one of: #{FORMATS.join(' ')}" unless FORMATS.include?(v)
+    args[:format] = v
+  end
+  op.on("-v", "--verbose", "talk about it") { $VERBOSE = true }
+end
+
+opts.parse!
+
+if ARGV.size == 0
+  puts opts
+  exit
+end
+
+mnemonic = ARGV.shift
+# use the taxonomy id if exists, otherwise use the tax ID itself
+tax_id = 
+  if val = TAXONOMY_IDS[mnemonic.to_sym]
+    val.first
+  else
+    mnemonic
+  end
+args[:query] = "taxonomy:#{tax_id}"
+
+base_url = "http://www.uniprot.org/uniprot/?"
+query_string = args.map {|k,v| [k,CGI.escape(v)].join('=') }.join("&")
+
+url = base_url + query_string
+
+prefix = "uni"
+variants = (args[:include] == 'yes') ? 'var' : 'can'
+short_date = Time.now.strftime("%y%m%d")
+decoytype = "fwd"
+postfix = ".fasta"
+
+filename = [prefix, mnemonic, variants, short_date, decoytype].join("_") << postfix
+(filename << ".gz") if args[:compress] == 'yes'
+puts "reading from url : #{url}"
+puts "writing to file  : #{filename}"
+File.open(filename,'w') do |out|
+  open(url) do |io|
+    out.print( io.read )
+  end
+end
+
+

data/script/quant_compare_direct_injections.rb

@@ -5,11 +5,21 @@ require 'mspire/mzml'
 require 'mspire/peak_list'
 require 'mspire/peak'
 
+def putsv(*args)
+  if $VERBOSE
+    puts(*args)
+  end
+end
+
 DEFAULT_OUTFILE = "quant_compare.tsv"
 
 DEFAULTS = { 
   :bin_width => Mspire::PeakList::DEFAULT_MERGE[:bin_width], 
   :bin_unit => Mspire::PeakList::DEFAULT_MERGE[:bin_unit],
+  :split => Mspire::PeakList::DEFAULT_MERGE[:split],
+  :round_mz => 6,
+  :round_intensity => 6,
+  :mz_prefix => "mz"
 }
 
 parser = Trollop::Parser.new do
@@ -19,11 +29,18 @@ parser = Trollop::Parser.new do
   opt :outfile, "write results to this file", :default => DEFAULT_OUTFILE
   opt :bin_width, "width of the bins for merging", :default => DEFAULTS[:bin_width]
   opt :bin_unit, "units for binning (ppm or amu)", :default => DEFAULTS[:bin_unit].to_s
+  opt :split, "share|greedy_y|zero method used to distinguish peaks", :default => DEFAULTS[:split].to_s
   opt :sample_ids, "a yml file pointing basename to id", :type => :string
+  opt :mz_prefix, "use this prefix for mz values", :default => DEFAULTS[:mz_prefix]
+  opt :round_mz, "round the final m/z values to this place", :default => DEFAULTS[:round_mz]
+  opt :round_intensity, "round the final int values to this place", :default => DEFAULTS[:round_intensity]
+  opt :verbose, "talk about it"
 end
 
 opts = parser.parse(ARGV)
 opts[:bin_unit] = opts[:bin_unit].to_sym
+opts[:split] = opts[:split].to_sym
+$VERBOSE = opts.delete(:verbose)
 
 if ARGV.size == 0
   parser.educate 
@@ -36,6 +53,14 @@ class TracedPeak < Array
   # the intensity or y value
   alias_method :y, :last
 
+  def x=(val)
+    self[0] = val
+  end
+
+  def y=(val)
+    self[2] = val
+  end
+
   def initialize(data, sample_id)
     self[0] = data.first
     self[1] = sample_id
@@ -63,7 +88,7 @@ index_to_sample_id = {}
 sample_ids = files.each_with_index.map do |filename,index|
   basename = filename.chomp(File.extname(filename))
   sample_id = basename_to_sample_id ? basename_to_sample_id[basename] : basename
-  puts "processing: #{filename}"
+  putsv "processing: #{filename}"
   Mspire::Mzml.open(filename) do |mzml|
     mzml.each_with_index do |spec,i|
       if spec.ms_level == 1
@@ -80,31 +105,32 @@ sample_ids = files.each_with_index.map do |filename,index|
   sample_id
 end
 
-puts "gathered #{peaklist.size} peaks!"
+putsv "gathered #{peaklist.size} peaks!"
 
-puts "sorting all peaks"
+putsv "sorting all peaks"
 peaklist.sort! 
 
-puts "merging peaks"
-#share_method = :greedy_y
-share_method = :share
+putsv "merging peaks"
+share_method = :greedy_y
+#share_method = :share
+
 
-$VERBOSE = true
-data = Mspire::PeakList.merge([peaklist], opts.merge( {:only_data => true, :split => share_method} ))
-p data.size
-p data.first.size
+peaks, data = Mspire::PeakList.merge([peaklist], opts.merge( {:split => share_method, :return_data => true} ))
 
 File.open(opts[:outfile],'w') do |out|
 
   header = ["mzs", *sample_ids]
   out.puts header.join("\t")
 
-  data.each do |bucket_of_peaks|
+  data.zip(peaks) do |bucket_of_peaks, meta_peak|
+
     signal_by_sample_index = Hash.new {|h,k| h[k] = 0.0 }
-    mz = weighted_mz
-    row = [mz.round(6), *sample_ids.each_with_index.map {|id,index| signal_by_sample_index[index] }]
+    bucket_of_peaks.each do |peak|
+      signal_by_sample_index[peak.sample_id] += peak.y
+    end
+
+    row = [opts[:mz_prefix] + meta_peak.x.round(opts[:round_mz]).to_s, *sample_ids.each_with_index.map {|id,index| signal_by_sample_index[index].round(opts[:round_intensity]) }]
     out.puts row.join("\t")
   end
 end
 
-

data/spec/mspire/isotope/aa_spec.rb

@@ -8,12 +8,12 @@ describe 'accessing an amino acid atom count' do
   end
 
   it 'residue can be accessed with a symbol' do
-    hash = Mspire::Isotope::AA::ATOM_COUNTS[:A]
+    hash = Mspire::Isotope::AA::FORMULAS[:A]
     [:c, :h, :o, :n, :s].each {|key| hash[key].should == @alanine[key] }
   end
     
   it 'residue can be accessed with a string' do
-    hash = Mspire::Isotope::AA::ATOM_COUNTS['A']
+    hash = Mspire::Isotope::AA::FORMULAS['A']
     [:c, :h, :o, :n, :s].each {|key| hash[key].should == @alanine[key] }
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mspire
 version: !ruby/object:Gem::Version
-  version: 0.7.9
+  version: 0.7.10
   prerelease: 
 platform: ruby
 authors:
@@ -10,11 +10,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-14 00:00:00.000000000 Z
+date: 2012-04-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &23083440 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -22,10 +22,15 @@ dependencies:
         version: '1.5'
   type: :runtime
   prerelease: false
-  version_requirements: *23083440
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
 - !ruby/object:Gem::Dependency
   name: bsearch
-  requirement: &23080720 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +38,15 @@ dependencies:
         version: 1.5.0
   type: :runtime
   prerelease: false
-  version_requirements: *23080720
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.5.0
 - !ruby/object:Gem::Dependency
   name: andand
-  requirement: &23078680 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,10 +54,15 @@ dependencies:
         version: 1.3.1
   type: :runtime
   prerelease: false
-  version_requirements: *23078680
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.3.1
 - !ruby/object:Gem::Dependency
   name: obo
-  requirement: &23076600 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +70,15 @@ dependencies:
         version: 0.1.0
   type: :runtime
   prerelease: false
-  version_requirements: *23076600
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.1.0
 - !ruby/object:Gem::Dependency
   name: builder
-  requirement: &23074560 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -66,10 +86,15 @@ dependencies:
         version: 3.0.0
   type: :runtime
   prerelease: false
-  version_requirements: *23074560
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.0.0
 - !ruby/object:Gem::Dependency
   name: bio
-  requirement: &23073060 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -77,10 +102,15 @@ dependencies:
         version: 1.4.2
   type: :runtime
   prerelease: false
-  version_requirements: *23073060
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.4.2
 - !ruby/object:Gem::Dependency
   name: trollop
-  requirement: &23071860 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -88,10 +118,15 @@ dependencies:
         version: 1.16.2
   type: :runtime
   prerelease: false
-  version_requirements: *23071860
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.16.2
 - !ruby/object:Gem::Dependency
   name: uuid
-  requirement: &23070700 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -99,10 +134,15 @@ dependencies:
         version: 2.3.5
   type: :runtime
   prerelease: false
-  version_requirements: *23070700
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 2.3.5
 - !ruby/object:Gem::Dependency
   name: fftw3
-  requirement: &23068400 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -110,10 +150,15 @@ dependencies:
         version: '0.3'
   type: :development
   prerelease: false
-  version_requirements: *23068400
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.3'
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &23066100 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -121,10 +166,15 @@ dependencies:
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *23066100
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.6'
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &23063900 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -132,7 +182,12 @@ dependencies:
         version: 1.5.2
   type: :development
   prerelease: false
-  version_requirements: *23063900
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.5.2
 description: mass spectrometry proteomics, lipidomics, and tools, a rewrite of mspire,
   merging of ms-* gems
 email: jtprince@gmail.com
@@ -244,6 +299,7 @@ files:
 - obo/ims.obo
 - obo/ms.obo
 - obo/unit.obo
+- script/download_uniprotkb_db.rb
 - script/mzml_read_binary.rb
 - script/quant_compare_direct_injections.rb
 - spec/cv/param_spec.rb
@@ -333,7 +389,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.15
+rubygems_version: 1.8.18
 signing_key: 
 specification_version: 3
 summary: mass spectrometry proteomics, lipidomics, and tools