mspire 0.6.26 → 0.7.2

data/lib/{ms → mspire}/mzml/spectrum_list.rb

@@ -1,6 +1,6 @@
-require 'ms/mzml/spectrum'
+require 'mspire/mzml/spectrum'
 
-module MS
+module Mspire
   class Mzml
     class SpectrumList < Array
 
@@ -13,10 +13,10 @@ module MS
       end
 
       # This method takes an object responding to :data, creates a new
-      # MS::Mzml::Spectrum object with that data and puts it in the internal
+      # Mspire::Mzml::Spectrum object with that data and puts it in the internal
       # list
       def add_ms_spectrum!(spectrum, id)
-        mzml_spec = MS::Mzml::Spectrum.new(id)
+        mzml_spec = Mspire::Mzml::Spectrum.new(id)
         mzml_spec.data = spectrum.data
         self << mzml_spec
       end

data/lib/{ms → mspire}/obo.rb

@@ -1,5 +1,5 @@
 
-module MS
+module Mspire
   class OBO
     attr_accessor :header
     attr_accessor :elements

data/lib/{ms → mspire}/peak.rb

@@ -1,8 +1,8 @@
 
-module MS ; end
-# an MS::Peak instance is an array of contiguous points (where each point is
+module Mspire ; end
+# an Mspire::Peak instance is an array of contiguous points (where each point is
 # a doublet: an x coordinate and a y coordinate)
-class MS::Peak < Array
+class Mspire::Peak < Array
 
   # returns an Array of peaks.  Splits peak with 1 or more local minima into
   # multiple peaks.  When a point is 'shared' between two adjacent peak-ish

data/lib/{ms → mspire}/peak/point.rb

@@ -1,5 +1,5 @@
 
-module MS
+module Mspire
   class Peak
     # A point is typically a doublet: an x value and a y value.  In a spectrum
     # this will be an m/z and intensity.  In a chromatogram this will be a

data/lib/{ms → mspire}/plms1.rb

@@ -1,10 +1,10 @@
 
 require 'write_file_or_string'
-require 'ms/spectrum'
+require 'mspire/spectrum'
 require 'stringio'
 require 'openany'
 
-module MS
+module Mspire
 
 =begin
   # if given scans, will use those, or optionally takes a block where an
@@ -42,7 +42,7 @@ module MS
   # Prince Lab MS 1: a simple format for reading and writing 
   # MS1 level mass spec data
   # 
-  # see MS::Plms1::SPECIFICATION for the file specification
+  # see Mspire::Plms1::SPECIFICATION for the file specification
   class Plms1
     SPECIFICATION =<<-HERE
         # The file format contains no newlines but is shown here broken into lines for
@@ -92,7 +92,7 @@ module MS
           data = read_uint32(io)[0].times.map do
             read_float64(io, read_uint32(io)[0])
           end
-          MS::Spectrum.new(data)
+          Mspire::Spectrum.new(data)
         end
       end
       self

data/lib/{ms → mspire}/quant/qspec.rb

@@ -1,7 +1,7 @@
-module MS ; end
-module MS::Quant ; end
+module Mspire ; end
+module Mspire::Quant ; end
 
-class MS::Quant::Qspec
+class Mspire::Quant::Qspec
 
   # personal communication with Hyungwon Choi: "We typically use nburn=2000,
   # niter=10000, which is quite sufficient to guarantee the reproducibility of
@@ -62,7 +62,7 @@ class MS::Quant::Qspec
 
   # writes a qspec formatted file to filename
   def write(filename)
-    ints = MS::Quant::Qspec.conditions_to_ints(conditions)
+    ints = Mspire::Quant::Qspec.conditions_to_ints(conditions)
     header_cats = INIT_HEADER + ints
     rows = @protname_length_pairs.map {|pair| pair.map.to_a }
     @condition_to_count_array.each do |cond,counts|

data/lib/{ms → mspire}/quant/qspec/protein_group_comparison.rb

@@ -1,14 +1,14 @@
-require 'ms/quant/protein_group_comparison'
+require 'mspire/quant/protein_group_comparison'
 
-module MS
+module Mspire
   module Quant
     module ProteinGroupComparison
     end
   end
 end
 
-class MS::Quant::ProteinGroupComparison::Qspec
-  include MS::Quant::ProteinGroupComparison
+class Mspire::Quant::ProteinGroupComparison::Qspec
+  include Mspire::Quant::ProteinGroupComparison
 
   attr_accessor :qspec_results_struct
 

data/lib/{ms → mspire}/spectrum.rb

@@ -1,13 +1,13 @@
-require 'ms/spectrum_like'
+require 'mspire/spectrum_like'
 require 'bsearch'
 require 'bin'
-require 'ms/peak'
+require 'mspire/peak'
 
-module MS
+module Mspire
   # note that a point is an [m/z, intensity] doublet.
   # A peak is considered a related string of points
   class Spectrum
-    include MS::SpectrumLike
+    include Mspire::SpectrumLike
 
     DEFAULT_MERGE = {
       :bin_width => 5,
@@ -45,7 +45,7 @@ module MS
       #                                     number of spectra
       #     :return_data => false           returns a parallel array containing
       #                                     the peaks associated with each returned point
-      #     :split => false | :share | :greedy_y   see MS::Peak#split
+      #     :split => false | :share | :greedy_y   see Mspire::Peak#split
       #
       # The binning algorithm is the fastest possible algorithm that would allow
       # for arbitrary, non-constant bin widths (a ratcheting algorithm O(n + m))
@@ -109,7 +109,7 @@ module MS
             #abort 'here'
 
 
-            peaks = MS::Peak.new(pseudo_points).split(opt[:split])
+            peaks = Mspire::Peak.new(pseudo_points).split(opt[:split])
 
             return_data = []
             _mzs = [] ; _ints = []

data/lib/{ms → mspire}/spectrum/centroid.rb

@@ -1,5 +1,5 @@
 
-module MS
+module Mspire
   class Spectrum
     # this module can be used to extend the behavior of some peaks as desired
     module Centroidish

data/lib/{ms → mspire}/spectrum_like.rb

@@ -1,4 +1,4 @@
-module MS
+module Mspire
   module SpectrumLike
     include Enumerable
 
@@ -17,7 +17,7 @@ module MS
 
     def centroided?() centroided end
 
-    # @return [MS::Spectrum]
+    # @return [Mspire::Spectrum]
     # @param [Array] data two element array of mzs and intensities
     # @param [Boolean] centroided is the spectrum centroided or not
     def initialize(data_arrays, centroided=true)
@@ -80,7 +80,7 @@ module MS
     # of another given value
     def normalize(norm_by=:tic)
       norm_by = tic if norm_by == :tic
-      MS::Spectrum.new([self.mzs, self.intensities.map {|v| v / norm_by }])
+      Mspire::Spectrum.new([self.mzs, self.intensities.map {|v| v / norm_by }])
     end
 
     def tic
@@ -134,9 +134,9 @@ module MS
       find_all_nearest_index(val).map {|i| mzs[i] }
     end
 
-    # uses MS::Spectrum.merge
+    # uses Mspire::Spectrum.merge
     def merge(other_spectra, opts={})
-      MS::Spectrum.merge([self, *other_spectra], opts)
+      Mspire::Spectrum.merge([self, *other_spectra], opts)
     end
   end
 end

data/lib/{ms → mspire}/user_param.rb

@@ -1,5 +1,5 @@
 
-module MS
+module Mspire
 
   class UserParam
 
@@ -24,7 +24,7 @@ module MS
       @unit = 
         if args.size > 1 && ((args.last.is_a?(::CV::Param) || args.last =~ /^[A-Za-z]+:\d+$/))
           unit_arg = args.pop
-          unit_arg.is_a?(::CV::Param) ? unit_arg : MS::CV::Param[unit_arg]
+          unit_arg.is_a?(::CV::Param) ? unit_arg : Mspire::CV::Param[unit_arg]
         end
       @name, @value, @type = args
     end

data/script/mzml_read_binary.rb

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
 require 'trollop'
-require 'ms/mzml/data_array'
+require 'mspire/mzml/data_array'
 
 parser = Trollop::Parser.new do
   banner "usage: #{File.basename(__FILE__)} [OPTIONS] <base64> ..."

data/spec/{ms → mspire}/cv/param_spec.rb

@@ -1,28 +1,28 @@
 require 'spec_helper'
 
-require 'ms/cv/param'
+require 'mspire/cv/param'
 require 'cv/param'
 
-describe MS::CV::Param do
+describe Mspire::CV::Param do
   describe 'object creation from class methods' do
 
     it '::new allows full description' do
-      param1 = MS::CV::Param.new('MS', 'MS:1000052', 'suspension')
+      param1 = Mspire::CV::Param.new('MS', 'MS:1000052', 'suspension')
       param1.value.should be_nil
       # just nonsense: 32 ng suspensions
-      param2 = MS::CV::Param.new('MS', 'MS:1000052', 'suspension', 32, ::CV::Param.new('UO', 'UO:0000024', 'nanogram'))
+      param2 = Mspire::CV::Param.new('MS', 'MS:1000052', 'suspension', 32, ::CV::Param.new('UO', 'UO:0000024', 'nanogram'))
       param2.cv_ref.should == 'MS'
       param2.value.should == 32
       param2.unit.accession.should == 'UO:0000024'
     end
 
     it '::[] requires shortcut accession strings' do
-      param1 = MS::CV::Param['MS:1000052']
+      param1 = Mspire::CV::Param['MS:1000052']
       param1.cv_ref.should == 'MS'
       param1.value.should be_nil
 
       # just nonsense: 32 ng suspensions
-      param2 = MS::CV::Param['MS:1000052', 32, 'UO:0000024']
+      param2 = Mspire::CV::Param['MS:1000052', 32, 'UO:0000024']
       param2.cv_ref.should == 'MS'
       param2.name.should == 'suspension'
       param2.value.should == 32

data/spec/{ms → mspire}/digester_spec.rb

@@ -1,11 +1,11 @@
 require 'spec_helper.rb'
 
-require 'ms/digester'
+require 'mspire/digester'
 require 'pp'
 
 describe 'a digester' do
   before do
-    @digester = MS::Digester.new('arg', 'R')
+    @digester = Mspire::Digester.new('arg', 'R')
   end
   
   def spp(input, str="")
@@ -50,7 +50,7 @@ describe 'a digester' do
   end
 
   it 'finds cleavage sites with exception' do
-    @digester = MS::Digester.new('argp', 'R', 'P')
+    @digester = Mspire::Digester.new('argp', 'R', 'P')
     {
       "" => [0,0],
       "A" => [0,1],
@@ -232,7 +232,7 @@ end
 
 describe 'performs as documented in readme' do
  it 'runs cleavage sites documentation' do
-    d = MS::Digester.new('Trypsin', 'KR', 'P')
+    d = Mspire::Digester.new('Trypsin', 'KR', 'P')
     seq = "AARGGR"
     sites = d.cleavage_sites(seq)
     sites.should == [0, 3, 6]
@@ -251,7 +251,7 @@ end
   
 describe 'basic trypsin digestion' do
   it 'performs digestion and can specify sites of digestion' do
-    trypsin = MS::Digester['Trypsin']
+    trypsin = Mspire::Digester['Trypsin']
     
     expected = [
     'MIVIGR',
@@ -281,11 +281,11 @@ describe 'basic trypsin digestion' do
     "\tMIVIGR",
     "SIVHP\nYITNEYEPFAAE K",
     "QQILSI\rMAG"]
-    MS::Digester['Trypsin'].digest("\tMIVIGRSIVHP\nYITNEYEPFAAE KQQILSI\rMAG").should == expected
+    Mspire::Digester['Trypsin'].digest("\tMIVIGRSIVHP\nYITNEYEPFAAE KQQILSI\rMAG").should == expected
   end
 
   it 'does a trypsin digest' do
-    trypsin = MS::Digester[:trypsin]
+    trypsin = Mspire::Digester[:trypsin]
     {
       "" => [''],
       "A" => ["A"],
@@ -315,7 +315,7 @@ end
 describe 'digestion with other enzymes' do
 
   # This is how to access the already created enzyme:
-  # MS::Digester['Arg-C']  (or :arg_c, 'ARG-C', :ARG_C')
+  # Mspire::Digester['Arg-C']  (or :arg_c, 'ARG-C', :ARG_C')
   {
       ['Arg-C', :arg_c] => { 
       "AARC" => ["AAR", "C"], 
@@ -337,8 +337,8 @@ describe 'digestion with other enzymes' do
     }
   }.each do |enzyme_names, test_hash|
     it "digests with '#{enzyme_names.first}'" do
-      digester = MS::Digester[enzyme_names.first]
-      digester.should == MS::Digester[enzyme_names.last]
+      digester = Mspire::Digester[enzyme_names.first]
+      digester.should == Mspire::Digester[enzyme_names.last]
       digester.name.should == enzyme_names.first
       test_hash.each do |sequence, expected|
         digester.digest(sequence).should == expected

data/spec/{ms → mspire}/error_rate/qvalue_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-require 'ms/error_rate/qvalue'
+require 'mspire/error_rate/qvalue'
 
 Hit = Struct.new(:score, :charge)
 HitWeird = Struct.new(:some_obscure_score, :charge)
@@ -20,14 +20,14 @@ describe 'calculating q-values' do
   end
 
   it 'can calculate qvalues on target/decoy sets (:score is default)' do
-    pairs = MS::ErrorRate::Qvalue.target_decoy_qvalues(@target_hits, @decoy_hits)
+    pairs = Mspire::ErrorRate::Qvalue.target_decoy_qvalues(@target_hits, @decoy_hits)
     pairs.each do |hit, qval|
       @qval_by_hit[hit].should be_within(0.00000001).of(qval)
     end
   end
 
   it 'can calculate qvalues on target/decoy sets with custom sorting' do
-    pairs = MS::ErrorRate::Qvalue.target_decoy_qvalues(@target_hits_weird, @decoy_hits_weird) {|hit| hit.some_obscure_score }
+    pairs = Mspire::ErrorRate::Qvalue.target_decoy_qvalues(@target_hits_weird, @decoy_hits_weird) {|hit| hit.some_obscure_score }
     pairs.each do |hit, qval|
       @qval_by_hit[hit].should be_within(0.00000001).of(qval)
     end

data/spec/{ms → mspire}/fasta_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-require 'ms/fasta'
+require 'mspire/fasta'
 
 describe 'basic fasta operations' do
   before do
@@ -47,7 +47,7 @@ describe 'basic fasta operations' do
 
   it 'can read a file' do
     %w(newlines_file carriage_returns_and_newlines_file).each do |file|
-      MS::Fasta.open(@data[file]) do |fasta|
+      Mspire::Fasta.open(@data[file]) do |fasta|
         fasta_correct? fasta
       end
     end
@@ -56,7 +56,7 @@ describe 'basic fasta operations' do
   it 'can read an IO object' do
     %w(newlines_file carriage_returns_and_newlines_file).each do |file|
       File.open(@data[file]) do |io|
-        fasta = MS::Fasta.new(io)
+        fasta = Mspire::Fasta.new(io)
         fasta_correct? fasta
       end
     end
@@ -64,28 +64,28 @@ describe 'basic fasta operations' do
 
   it 'can read a string' do
     %w(newlines carriage_returns_and_newlines).each do |key|
-      fasta = MS::Fasta.new @data[key]
+      fasta = Mspire::Fasta.new @data[key]
       fasta_correct? fasta
     end
   end
 
   it 'iterates entries with foreach' do
     %w(newlines_file carriage_returns_and_newlines_file).each do |file|
-      MS::Fasta.foreach(@data[file]) do |entry|
+      Mspire::Fasta.foreach(@data[file]) do |entry|
         entry.should be_an_instance_of Bio::FastaFormat
       end
     end
   end
 
-  it 'gives an iterator called with MS::Fasta.foreach and no block' do
-    seqs = MS::Fasta.foreach(@data['newlines_file']).select {|e| e.header =~ /^gi/ }.map(&:sequence)
+  it 'gives an iterator called with Mspire::Fasta.foreach and no block' do
+    seqs = Mspire::Fasta.foreach(@data['newlines_file']).select {|e| e.header =~ /^gi/ }.map(&:sequence)
     seqs.size.should == 1
     seqs.first[0,4].should == 'LCLY'
   end
 
   it 'runs the documentation' do
     fasta_file = @data['newlines_file']
-    ids = MS::Fasta.open(fasta_file) do |fasta| 
+    ids = Mspire::Fasta.open(fasta_file) do |fasta| 
       fasta.map(&:entry_id)
     end
     ids.is_a?(Array)
@@ -93,12 +93,12 @@ describe 'basic fasta operations' do
    
     # this code is already tested above
     # File.open(fasta_file) do |io| 
-    #   fasta = MS::Fasta.new(io)
+    #   fasta = Mspire::Fasta.new(io)
     # end
 
     # taking a string
     string = ">id1 a simple header\nAAASDDEEEDDD\n>id2 header again\nPPPPPPWWWWWWTTTTYY\n"
-    fasta = MS::Fasta.new(string)
+    fasta = Mspire::Fasta.new(string)
     (simple, not_simple) = fasta.partition {|entry| entry.header =~ /simple/ }
     simple.first.header.include?("simple").should == true
     not_simple.first.header.include?("simple").should == false

data/spec/{ms → mspire}/ident/peptide/db_spec.rb

@@ -1,7 +1,7 @@
 require 'spec_helper'
 
 require 'yaml'
-path = 'ms/ident/peptide/db'
+path = 'mspire/ident/peptide/db'
 require path 
 
 module Kernel
@@ -28,18 +28,18 @@ describe 'a uniprot fasta file' do
   describe 'amino acid expansion' do
 
     it 'can expand out wildcard amino acid combinations' do
-      array = MS::Ident::Peptide::Db.expand_peptides('ALXX', 'X' =>  %w(* % &), 'L' => %w(P Q) )
+      array = Mspire::Ident::Peptide::Db.expand_peptides('ALXX', 'X' =>  %w(* % &), 'L' => %w(P Q) )
       array.sort.should == %w(AP** AP*% AP*& AP%* AP%% AP%& AP&* AP&% AP&& AQ** AQ*% AQ*& AQ%* AQ%% AQ%& AQ&* AQ&% AQ&&).sort
     end
 
     it 'will not expand explosive combinations (>MAX_NUM_AA_EXPANSION)' do
       # this is from real data
       worst_case = 'LTLLRPEKHEAATGVDTICTHRVDPIGPGLXXEXLYWELSXLTXXIXELGPYTLDR'
-      MS::Ident::Peptide::Db.expand_peptides(worst_case, 'X' =>  %w(* % &)).nil?.should == true
+      Mspire::Ident::Peptide::Db.expand_peptides(worst_case, 'X' =>  %w(* % &)).nil?.should == true
     end
 
     it 'returns the peptide in the array if no expansion' do
-      array = MS::Ident::Peptide::Db.expand_peptides('ZZZZZ', 'X' =>  %w(* % &), 'L' => %w(P Q) )
+      array = Mspire::Ident::Peptide::Db.expand_peptides('ZZZZZ', 'X' =>  %w(* % &), 'L' => %w(P Q) )
       array.should == ['ZZZZZ']
     end
 
@@ -53,7 +53,7 @@ describe 'a uniprot fasta file' do
     end
 
     it 'converts a fasta file into peptide centric db' do
-      output_files = MS::Ident::Peptide::Db.cmdline([@fasta_file])
+      output_files = Mspire::Ident::Peptide::Db.cmdline([@fasta_file])
       output_files.first.should == File.expand_path(@output_file)
       File.exist?(@output_file).should == true
       hash = {}
@@ -71,7 +71,7 @@ describe 'a uniprot fasta file' do
     it 'lists approved enzymes and exits' do
       output = capture_stdout do
         begin
-          MS::Ident::Peptide::Db.cmdline(['--list-enzymes'])
+          Mspire::Ident::Peptide::Db.cmdline(['--list-enzymes'])
         rescue SystemExit
           1.should == 1 # we exited
         end
@@ -84,18 +84,18 @@ describe 'a uniprot fasta file' do
 
   describe 'reading a peptide centric database' do
     before do
-      outfiles = MS::Ident::Peptide::Db.cmdline([@fasta_file])
+      outfiles = Mspire::Ident::Peptide::Db.cmdline([@fasta_file])
       @outfile = outfiles.first
     end
 
     it 'creates a hash that can retrieve peptides as an array' do
-      hash = MS::Ident::Peptide::Db.new(@outfile)
+      hash = Mspire::Ident::Peptide::Db.new(@outfile)
       hash["AVTEQGHELSNEER"].should == %w(sp|P31946|1433B_HUMAN	sp|P31946-2|1433B_HUMAN)
       hash["VRAAR"].should == ["tr|D3DX18|D3DX18_HUMAN"]
     end
 
     it 'reads the file on disk with random access or is enumerable' do
-      MS::Ident::Peptide::Db::IO.open(@outfile) do |io|
+      Mspire::Ident::Peptide::Db::IO.open(@outfile) do |io|
         io["AVTEQGHELSNEER"].should == %w(sp|P31946|1433B_HUMAN	sp|P31946-2|1433B_HUMAN)
         io["VRAAR"].should == ["tr|D3DX18|D3DX18_HUMAN"]
         io.each_with_index do |key_prots, i|