mspire 0.6.26 → 0.7.2

data/VERSION

@@ -1 +1 @@
-0.6.26
+0.7.2

data/lib/mspire.rb

@@ -1,5 +1,5 @@
 
-require 'ms/mass/aa' # requires ms/mass
+require 'mspire/mass/aa' # requires mspire/mass
 
 module Mspire
   VERSION = IO.read(File.join(File.dirname(__FILE__), '..', 'VERSION')).chomp

data/lib/{ms → mspire}/cv.rb

@@ -4,7 +4,7 @@ require 'obo/ms'
 require 'obo/ims'
 require 'obo/unit'
 
-module MS
+module Mspire
   module CV
     Obo = {
       'MS' => Obo::MS.id_to_name,

data/lib/{ms → mspire}/cv/param.rb

@@ -1,7 +1,7 @@
 require 'cv/param'
-require 'ms/cv'
+require 'mspire/cv'
 
-module MS
+module Mspire
   module CV
 
     # a mass spec related CVParam.  
@@ -22,12 +22,12 @@ module MS
           when 1
             nil
           when 2
-            MS::CV::Param[args.pop] if args.last.is_a?(String) && args.last =~ /^[A-Za-z]+:/
+            Mspire::CV::Param[args.pop] if args.last.is_a?(String) && args.last =~ /^[A-Za-z]+:/
           when 3
-            MS::CV::Param[args.pop]
+            Mspire::CV::Param[args.pop]
           end
         obo_type = args[0][/([A-Za-z]+):/,1]
-        self.new(obo_type, args[0], MS::CV::Obo[obo_type][args.first], args[1], unit)
+        self.new(obo_type, args[0], Mspire::CV::Obo[obo_type][args.first], args[1], unit)
       end
     end
   end

data/lib/{ms → mspire}/cv/paramable.rb

@@ -1,6 +1,6 @@
-require 'ms/cv/param'
+require 'mspire/cv/param'
 
-module MS
+module Mspire
   module CV
     module Paramable
 
@@ -10,15 +10,15 @@ module MS
         describe!(*opts[:params])
       end
 
-      # casts each string or array as a Param object (using MS::CV::Param[]),
+      # casts each string or array as a Param object (using Mspire::CV::Param[]),
       # pushes it onto the params attribute and returns the growing params object
       def describe!(*args)
         @params ||= []
         as_params = args.map do |arg|
           if arg.is_a?(Array)
-            MS::CV::Param[ *arg ]
+            Mspire::CV::Param[ *arg ]
           elsif arg.is_a?(String)
-            MS::CV::Param[ arg ]
+            Mspire::CV::Param[ arg ]
           else
             arg
           end

data/lib/{ms → mspire}/digester.rb

@@ -1,10 +1,10 @@
 require 'strscan'
 
-module MS
+module Mspire
 
   # A Digester splits a protein sequence into peptides at specified sites.
   #
-  #     trypsin = MS::Digester[:trypsin]
+  #     trypsin = Mspire::Digester[:trypsin]
   #
   #     trypsin.digest('MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG')
   #     # => ['MIVIGR', 'SIVHPYITNEYEPFAAEK', 'QQILSIMAG']

data/lib/{ms → mspire}/error_rate/decoy.rb

@@ -1,5 +1,5 @@
 
-module MS
+module Mspire
   module ErrorRate
     module Decoy
       module_function

data/lib/{ms → mspire}/error_rate/qvalue.rb

@@ -1,7 +1,7 @@
 require 'set'
-require 'ms/error_rate/decoy'
+require 'mspire/error_rate/decoy'
 
-module MS
+module Mspire
 
   module ErrorRate
     # For generating and working with q-value calculations.  The q-value is the global false discovery rate when accepting that particular ID.  We do not necessarily distinguish here between *how* the FDR is generated (i.e., Storey's pFDR "the occurrence of false positives" vs. Benjamini-Hochberg's FDR "the rate of false positives" [except to prefer Storey when possible] ).  The main point is that we sort and threshold based on a global FDR.
@@ -22,7 +22,7 @@ module MS
         # Proc.new doesn't do arity checking
         hit_with_qvalue_pairs = Proc.new do |hits|
           sorted_best_to_worst = (hits.sort_by(&sorting)).reverse
-          (target_hits, qvalues) = MS::ErrorRate::Qvalue.mixed_target_decoy(sorted_best_to_worst, target_set, opts)
+          (target_hits, qvalues) = Mspire::ErrorRate::Qvalue.mixed_target_decoy(sorted_best_to_worst, target_set, opts)
           target_hits.zip(qvalues)
         end
 
@@ -54,7 +54,7 @@ module MS
         best_to_worst.each do |hit|
           if target_setlike.include?(hit) 
             num_target += 1
-            precision = MS::ErrorRate::Decoy.precision(num_target, num_decoy)
+            precision = Mspire::ErrorRate::Decoy.precision(num_target, num_decoy)
             target_hits << hit
             qvalues << (1.0 - precision)
           else

data/lib/{ms → mspire}/fasta.rb

@@ -10,12 +10,12 @@ class Bio::FastaFormat
   alias_method :sequence, :seq
 end
 
-module MS
+module Mspire
   # A convenience class for working with fasta formatted sequence databases.
   # the file which includes this class also includes Enumerable with
   # Bio::FlatFile so you can do things like this:
   #
-  #     accessions = MS::Fasta.open("file.fasta") do |fasta| 
+  #     accessions = Mspire::Fasta.open("file.fasta") do |fasta| 
   #       fasta.map(&:accession)
   #     end
   # 
@@ -24,17 +24,17 @@ module MS
   #     entry.header == entry.definition
   #     entry.sequence == entry.seq
   #
-  # MS::Fasta.new accepts both an IO object or a String (a fasta formatted
+  # Mspire::Fasta.new accepts both an IO object or a String (a fasta formatted
   # string itself)
   #
   #     # taking an io object:
   #     File.open("file.fasta") do |io| 
-  #       fasta = MS::Fasta.new(io)
+  #       fasta = Mspire::Fasta.new(io)
   #       ... do something with it
   #     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/ }
   module Fasta
 

data/lib/{ms → mspire}/ident.rb

@@ -1,30 +1,30 @@
 
-require 'ms/ident/protein_group'
-require 'ms/ident/protein'
-require 'ms/ident/peptide_hit'
+require 'mspire/ident/protein_group'
+require 'mspire/ident/protein'
+require 'mspire/ident/peptide_hit'
 
-module MS
+module Mspire
 
-  # An MS::Ident::ProteinGroup is an array of proteins that responds to
+  # An Mspire::Ident::ProteinGroup is an array of proteins that responds to
   # :peptide_hits.  All protein level identifications should be stored in a
   # proteingroup object.
   #
-  # An MS::Ident::Protein is an object representing a protein (:id,
+  # An Mspire::Ident::Protein is an object representing a protein (:id,
   # :sequence, :description).  Note, it is not a protein hit (use a
   # ProteinGroup)
   #  
-  # An MS::Ident::PeptideHit is an object representing a match between an
+  # An Mspire::Ident::PeptideHit is an object representing a match between an
   # amino acid sequence and a spectrum.
   #
   # Typical usage:
   #
-  #     require 'ms/ident'
+  #     require 'mspire/ident'
   #
   #     hit1 = PeptideHit.new(:id => 1, :aaseq => 'PEPTIDE', :search =>
-  #     MS::Ident::Search.new, etc...)
+  #     Mspire::Ident::Search.new, etc...)
   #     peptide_hits = [hit1, hit2, ...]
   #
-  #     protein_groups = MS::Ident::ProteinGroup.peptide_hits_to_protein_groups(peptide_hits)
+  #     protein_groups = Mspire::Ident::ProteinGroup.peptide_hits_to_protein_groups(peptide_hits)
   #     protein_groups.first.peptide_hits  # => the peptide hits in that group
   module Ident
     # returns the filetype (if possible)

data/lib/{ms → mspire}/ident/peptide.rb

@@ -1,5 +1,5 @@
-module MS ; end
-module MS::Ident ; end
+module Mspire ; end
+module Mspire::Ident ; end
 
 # A 'sequence' is a notation of a peptide that includes the leading and
 # trailing amino acid after cleavage (e.g., K.PEPTIDER.E or -.STARTK.L )
@@ -7,7 +7,7 @@ module MS::Ident ; end
 #
 # 'aaseq' is the amino acid sequence of just the peptide with no leading or
 # trailing notation (e.g., PEPTIDER or LAKKLY)
-module MS::Ident::Peptide
+module Mspire::Ident::Peptide
   Nonstandard_AA_re = /[^A-Z\.\-]/
   
   class << self

data/lib/{ms → mspire}/ident/peptide/db.rb

@@ -1,22 +1,22 @@
-require 'ms/digester'
-require 'ms/fasta'
+require 'mspire/digester'
+require 'mspire/fasta'
 require 'optparse'
 
-module MS ; end
-module MS::Ident ; end
-module MS::Ident::Peptide ; end
+module Mspire ; end
+module Mspire::Ident ; end
+module Mspire::Ident::Peptide ; end
 
 # the object itself is a modified Hash.
 # It is initialized with the database file and a protein array can be
 # retrieved with the #[] method given an amino acid sequence.  All other
 # methods are untested at this time and should be avoided!
-class MS::Ident::Peptide::Db < Hash
+class Mspire::Ident::Peptide::Db < Hash
   MAX_NUM_AA_EXPANSION = 3
 
   # the twenty standard amino acids
   STANDARD_AA = %w(A C D E F G H I K L M N P Q R S T V W Y)
 
-  DEFAULT_PEPTIDE_CENTRIC_DB = {:missed_cleavages => 2, :min_length => 4, :enzyme => MS::Digester[:trypsin], :id_regexp => nil, :remove_digestion_file => true, :cleave_initiator_methionine => true, :expand_aa => {'X' => STANDARD_AA}}
+  DEFAULT_PEPTIDE_CENTRIC_DB = {:missed_cleavages => 2, :min_length => 4, :enzyme => Mspire::Digester[:trypsin], :id_regexp => nil, :remove_digestion_file => true, :cleave_initiator_methionine => true, :expand_aa => {'X' => STANDARD_AA}}
 
   PROTEIN_DELIMITER = "\t"
   KEY_VALUE_DELIMITER = ": "
@@ -25,7 +25,7 @@ class MS::Ident::Peptide::Db < Hash
 
     opt = {
       :remove_digestion_file => true,
-      :enzyme => MS::Digester[:trypsin]
+      :enzyme => Mspire::Digester[:trypsin]
     }
     opts = OptionParser.new do |op|
       op.banner = "usage: #{File.basename($0)} <file>.fasta ..."
@@ -42,9 +42,9 @@ class MS::Ident::Peptide::Db < Hash
       op.on("--min-length <#{opt[:min_length]}>", Integer, "the minimum peptide aaseq length") {|v| opt[:min_length] = v }
       op.on("--no-cleaved-methionine", "does not cleave off initiator methionine") { opt[:cleave_initiator_methionine] = false }
       op.on("--no-expand-x", "don't enumerate aa 'X' possibilities") { opt[:expand_aa] = nil }
-      op.on("-e", "--enzyme <name>", "enzyme for digestion") {|v| opt[:enzyme] = MS::Insilico::Digester.const_get(v.upcase) }
+      op.on("-e", "--enzyme <name>", "enzyme for digestion") {|v| opt[:enzyme] = Mspire::Insilico::Digester.const_get(v.upcase) }
       op.on("--list-enzymes", "lists approved enzymes and exits") do
-        puts MS::Digester::ENZYMES.keys.join("\n")
+        puts Mspire::Digester::ENZYMES.keys.join("\n")
         exit
       end
     end
@@ -56,7 +56,7 @@ class MS::Ident::Peptide::Db < Hash
     end
 
     argv.map do |file|
-      MS::Ident::Peptide::Db.peptide_centric_db(file, opt)
+      Mspire::Ident::Peptide::Db.peptide_centric_db(file, opt)
     end
   end
 
@@ -79,7 +79,7 @@ class MS::Ident::Peptide::Db < Hash
     base = fasta_file.chomp(File.extname(fasta_file))
     digestion_file = base + ".msd_clvg#{missed_cleavages}.peptides"
     File.open(digestion_file, "w") do |fh|
-      MS::Fasta.open(fasta_file) do |fasta|
+      Mspire::Fasta.open(fasta_file) do |fasta|
         fasta.each do |prot|
           peptides = enzyme.digest(prot.sequence, missed_cleavages)
           if (cleave_initiator_methionine && (prot.sequence[0,1] == "M"))

data/lib/{ms → mspire}/ident/peptide_hit.rb

@@ -1,22 +1,22 @@
 require 'merge'
 
-module MS ; end
-module MS::Ident ; end
+module Mspire ; end
+module Mspire::Ident ; end
 
-module MS::Ident::PeptideHitLike
+module Mspire::Ident::PeptideHitLike
   attr_accessor :id
   attr_accessor :search
   attr_accessor :missed_cleavages
   attr_accessor :aaseq
   attr_accessor :charge
-  # an array of MS::Ident::ProteinLike objects
+  # an array of Mspire::Ident::ProteinLike objects
   attr_accessor :proteins
   # relative to the set the hit is contained in!
   attr_accessor :qvalue
 end
 
-class MS::Ident::PeptideHit
-  include MS::Ident::PeptideHitLike
+class Mspire::Ident::PeptideHit
+  include Mspire::Ident::PeptideHitLike
   include Merge
 
   def initialize(hash)

data/lib/{ms → mspire}/ident/peptide_hit/qvalue.rb

@@ -1,10 +1,10 @@
-require 'ms/ident/search'
-require 'ms/ident/peptide_hit'
+require 'mspire/ident/search'
+require 'mspire/ident/peptide_hit'
 
-module MS ; end
-module MS::Ident ; end
+module Mspire ; end
+module Mspire::Ident ; end
 
-class MS::Ident::PeptideHit
+class Mspire::Ident::PeptideHit
   module Qvalue
     FILE_EXTENSION = '.phq.tsv'
     FILE_DELIMITER = "\t"
@@ -32,7 +32,7 @@ class MS::Ident::PeptideHit
 
       # returns an array of PeptideHit objects from a phq.tsv
       def from_file(filename)
-        searches = Hash.new {|h,id|  h[id] = MS::Ident::Search.new(id) }
+        searches = Hash.new {|h,id|  h[id] = Mspire::Ident::Search.new(id) }
         peptide_hits = []
         File.open(filename) do |io|
           header = io.readline.chomp.split(FILE_DELIMITER)
@@ -40,7 +40,7 @@ class MS::Ident::PeptideHit
           io.each do |line|
             line.chomp!
             (run_id, id, aaseq, charge, qvalue) = line.split(FILE_DELIMITER)
-            ph = MS::Ident::PeptideHit.new
+            ph = Mspire::Ident::PeptideHit.new
             ph.search = searches[run_id]
             ph.id = id; ph.aaseq = aaseq ; ph.charge = charge.to_i ; ph.qvalue = qvalue.to_f
             peptide_hits << ph

data/lib/{ms → mspire}/ident/pepxml.rb

@@ -1,10 +1,10 @@
 require 'nokogiri'
-require 'ms/ident'
-require 'ms/ident/pepxml/msms_pipeline_analysis'
+require 'mspire/ident'
+require 'mspire/ident/pepxml/msms_pipeline_analysis'
 
 require 'ostruct'
 
-module MS ; module Ident ; end ; end
+module Mspire ; module Ident ; end ; end
 
 class Numeric
   # returns a string with a + or - on the front
@@ -17,14 +17,14 @@ class Numeric
   end
 end
 
-class MS::Ident::Pepxml
+class Mspire::Ident::Pepxml
   XML_STYLESHEET_LOCATION = '/tools/bin/TPP/tpp/schema/pepXML_std.xsl'
   DEFAULT_PEPXML_VERSION = MsmsPipelineAnalysis::PEPXML_VERSION
   XML_ENCODING = 'UTF-8'
 
   attr_accessor :msms_pipeline_analysis
 
-  # returns an array of MS::Ident::Pepxml::SearchHit::Simple structs
+  # returns an array of Mspire::Ident::Pepxml::SearchHit::Simple structs
   def self.simple_search_hits(file)
     hit_values = File.open(file) do |io|
       doc = Nokogiri::XML.parse(io, nil, nil, Nokogiri::XML::ParseOptions::DEFAULT_XML | Nokogiri::XML::ParseOptions::NOBLANKS | Nokogiri::XML::ParseOptions::STRICT)
@@ -40,7 +40,7 @@ class MS::Ident::Pepxml
         search_score_nodes.each do |node|
           search_scores[node['name'].to_sym] = node['value'].to_f
         end
-        MS::Ident::Pepxml::SearchHit::Simple.new("hit_#{i}", MS::Ident::Search.new(file.chomp(File.extname(file))), aaseq, charge, search_scores)
+        Mspire::Ident::Pepxml::SearchHit::Simple.new("hit_#{i}", Mspire::Ident::Search.new(file.chomp(File.extname(file))), aaseq, charge, search_scores)
       end
     end
   end
@@ -97,7 +97,7 @@ class MS::Ident::Pepxml
 
     builder = Nokogiri::XML::Builder.new(:encoding => XML_ENCODING)
     msms_pipeline_analysis.to_xml(builder)
-    add_stylesheet(builder.doc, MS::Ident::Pepxml::XML_STYLESHEET_LOCATION)
+    add_stylesheet(builder.doc, Mspire::Ident::Pepxml::XML_STYLESHEET_LOCATION)
     string = builder.doc.to_xml
 
     if outfile 

data/lib/{ms → mspire}/ident/pepxml/modifications.rb

@@ -1,13 +1,13 @@
 require 'merge'
 require 'nokogiri'
 
-module MS ; end
-module MS::Ident ; end
-class MS::Ident::Pepxml ; end
+module Mspire ; end
+module Mspire::Ident ; end
+class Mspire::Ident::Pepxml ; end
 
 # Modified aminoacid, static or variable
 # unless otherwise stated, all attributes can be anything
-class MS::Ident::Pepxml::AminoacidModification
+class Mspire::Ident::Pepxml::AminoacidModification
   include Merge
   # The amino acid (one letter code)
   attr_accessor :aminoacid
@@ -36,7 +36,7 @@ class MS::Ident::Pepxml::AminoacidModification
     xmlb = builder || Nokogiri::XML::Builder.new
     # note massdiff: must begin with either + (nonnegative) or - [e.g.
     # +1.05446 or -2.3342] consider Numeric#to_plus_minus_string in
-    # MS::Ident::Pepxml
+    # Mspire::Ident::Pepxml
     attrs = [:aminoacid, :massdiff, :mass, :variable, :peptide_terminus, :symbol, :binary].map {|at| v=send(at) ; [at,v] if v }.compact
     hash = Hash[attrs]
     hash[:massdiff] = hash[:massdiff].to_plus_minus_string
@@ -46,7 +46,7 @@ class MS::Ident::Pepxml::AminoacidModification
 end
 
 # Modified aminoacid, static or variable
-class MS::Ident::Pepxml::TerminalModification
+class Mspire::Ident::Pepxml::TerminalModification
   include Merge
   # n for N-terminus, c for C-terminus
   attr_accessor :terminus
@@ -57,7 +57,7 @@ class MS::Ident::Pepxml::TerminalModification
   # Y if both modified and unmodified terminus could be present in the
   # dataset, N if only modified terminus can be present
   attr_accessor :variable
-  # MSial symbol used by search engine to designate this modification
+  # symbol used by search engine to designate this modification
   attr_accessor :symbol
   # whether modification can reside only at protein terminus (specified n or
   # c)