ms-core 0.0.1 → 0.0.2

data/History

@@ -0,0 +1,7 @@
+
+== version 0.0.1
+
+* copy overed from simon's mspire.
+* added functionality to Ms::Spectrum
+
+

data/lib/ms/calc.rb

@@ -19,14 +19,12 @@ module Ms
         mz = mz.to_f
         tol = ppm_tol_at(mz, ppm)
         mz-tol...mz+tol
-      end
-      
+      end
 
       # Rounds n to the specified precision (ie number of decimal places)
-      # def round(n, precision)
-      #   factor = 10**precision.to_i
-      #   (n * factor).round.to_f / factor
-      # end
-      
+      def round(n, precision)
+        factor = 10**precision.to_i
+        (n * factor).round.to_f / factor
+      end
   end
 end

data/lib/ms/data.rb

@@ -1,5 +1,6 @@
 require 'ms/data/interleaved'
 require 'ms/data/transposed'
+require 'ms/data/lazy_string'
 
 module Ms
   
@@ -54,4 +55,4 @@ module Ms
       send("new_#{type}", data)  
     end
   end
-end
+end

data/lib/ms/id/peptide.rb

@@ -28,7 +28,7 @@ module Ms::Id::Peptide
       when 1  ## this must be a parse error!
         pieces[0] ## which is the peptide itself  
       else
-        abort "bad peptide sequence: #{sequence}"
+        abort "bad peptide sequence: #{sequence.inspect}"
       end
     end
 

data/lib/ms/mass/aa.rb

@@ -1,3 +1,4 @@
+require 'molecules'
 require 'ms/mass'
 
 module Ms
@@ -14,16 +15,10 @@ module Ms
     #     # or use symbols
     #     MONO[:A]  # => 71.0371137878
     #
-    # This module is built on masses generated from the excellent {'molecules'
+    # This module is built on the excellent {'molecules'
     # library}[http://github.com/bahuvrihi/molecules/tree/master].  See that
-    # library for more serious work with masses:
-    #
-    #     gem install molecules
+    # library for more serious work with masses.
     module AA
-      Ms::Mass.constants.reject {|v| v == 'AA' }.each do |const|
-        const_set(const, Ms::Mass.const_get(const)) 
-      end
-
       # These are included here to offer maximum functionality
       MOLECULES_MONO_UNSUPPORTED = {
         :B => 172.048405, # average of aspartic acid and asparagine
@@ -40,70 +35,10 @@ module Ms
         #:J => nil,
       }
 
-      # generated from molecules version 0.1.3:
-      MOLECULES_MONO = {
-        :A => 71.0371137878,
-        :C => 103.0091844778,
-        :D => 115.026943032,
-        :E => 129.0425930962,
-        :F => 147.0684139162,
-        :G => 57.0214637236,
-        :H => 137.0589118624,
-        :I => 113.0840639804,
-        :K => 128.0949630177,
-        :L => 113.0840639804,
-        :M => 131.0404846062,
-        :N => 114.0429274472,
-        :O => 211.1446528645,
-        :P => 97.052763852,
-        :Q => 128.0585775114,
-        :R => 156.1011110281,
-        :S => 87.0320284099,
-        :T => 101.0476784741,
-        :U => 150.9536355878,
-        :V => 99.0684139162,
-        :W => 186.0793129535,
-        :Y => 163.0633285383,
-      }
-
-      MONO = MOLECULES_MONO_UNSUPPORTED.merge MOLECULES_MONO
-
-      # generated from molecules version 0.1.3:
-      MOLECULES_AVG = {
-        :A => 71.0779,
-        :C => 103.1429,
-        :D => 115.0874,
-        :E => 129.11398,
-        :F => 147.17386,
-        :G => 57.05132,
-        :H => 137.13928,
-        :I => 113.15764,
-        :K => 128.17228,
-        :L => 113.15764,
-        :M => 131.19606,
-        :N => 114.10264,
-        :O => 211.28076,
-        :P => 97.11518,
-        :Q => 128.12922,
-        :R => 156.18568,
-        :S => 87.0773,
-        :T => 101.10388,
-        :U => 150.0379,
-        :V => 99.13106,
-        :W => 186.2099,
-        :Y => 163.17326,
-      }
-
-      AVG = MOLECULES_AVG_UNSUPPORTED.merge MOLECULES_AVG
-
-      [AVG, MONO].each do |hash|
-        hash.each {|k,v| hash[k.to_s] = v }
-      end
 
       # returns a hash based on the molecules library of amino acid residues.
       # type is :mono or :avg
       def self.mass_index(type=:mono)
-        require 'molecules'
         hash = {}
         ('A'..'Z').each do |letter|
           if res = Molecules::Libraries::Residue[letter]
@@ -120,14 +55,10 @@ module Ms
         hash
       end
 
-      # prints a MONO or AVG hash for inclusion in ruby code
-      # type can be :mono or :avg
-      def self.print_mass_index(type=:mono)
-        puts "#{type.to_s.upcase} = {"
-        mass_index(type).sort.each do |k,v|
-          puts ":#{k} => #{v},"
-        end
-        puts "}"
+      MONO = MOLECULES_MONO_UNSUPPORTED.merge( self.mass_index(:mono) )
+      AVG = MOLECULES_AVG_UNSUPPORTED.merge( self.mass_index(:avg) )
+      [AVG, MONO].each do |hash|
+        hash.each {|k,v| hash[k.to_s] = v }
       end
 
     end

data/lib/ms/spectrum.rb

@@ -1,5 +1,7 @@
 module Ms
   class Spectrum
+    include Enumerable
+
     # The underlying data store.
     attr_reader :data
     
@@ -60,97 +62,99 @@ module Ms
       Ms::Spectrum.new([self.mzs, self.intensities.map {|v| v / tic }])
     end
 
-    # uses index function and returns the intensity at that value
-    def intensity_at_mz(mz)
-      if x = index(mz)
-        intensities[x]
-      else
-        nil
-      end
-    end
+    ## uses index function and returns the intensity at that value
+    #def intensity_at_mz(mz)
+      #if x = index(mz)
+        #intensities[x]
+      #else
+        #nil
+      #end
+    #end
 
-    # returns the index of the first value matching that m/z.  the argument m/z
-    # may be less precise than the actual m/z (rounding to the same precision
-    # given) but must be at least integer precision (after rounding)
-    # implemented as binary search (bsearch from the web)
-    def index(mz)
-      mz_ar = mzs
-      return_val = nil
-      ind = mz_ar.bsearch_lower_boundary{|x| x <=> mz }
-      if mz_ar[ind] == mz
-        return_val = ind
-      else 
-        # do a rounding game to see which one is it, or nil
-        # find all the values rounding to the same integer in the locale
-        # test each one fully in turn
-        mz = mz.to_f
-        mz_size = mz_ar.size
-        if ((ind < mz_size) and equal_after_rounding?(mz_ar[ind], mz))
-          return_val = ind
-        else # run the loop
-          up = ind
-          loop do
-            up += 1
-            if up >= mz_size
-              break
-            end
-            mz_up = mz_ar[up]
-            if (mz_up.ceil  - mz.ceil >= 2)
-              break
-            else
-              if equal_after_rounding?(mz_up, mz)
-                return_val = up
-                return return_val
-              end
-            end
-          end
-          dn= ind
-          loop do
-            dn -= 1
-            if dn < 0
-              break
-            end
-            mz_dn = mz_ar[dn]
-            if (mz.floor - mz_dn.floor >= 2)
-              break
-            else
-              if equal_after_rounding?(mz_dn, mz)
-                return_val = dn
-                return return_val
-              end
-            end
-          end
-        end
-      end
-      return_val
-    end
+    ## index mz, tolerance = :nearest(1), Float, :nearest_within_integer
 
-    # less_precise should be a float
-    # precise should be a float
-    def equal_after_rounding?(precise, less_precise) # :nodoc:
-      # determine the precision of less_precise
-      exp10 = precision_as_neg_int(less_precise)
-      #puts "EXP10: #{exp10}"
-      answ = ((precise*exp10).round == (less_precise*exp10).round)
-      #puts "TESTING FOR EQUAL: #{precise} #{less_precise}"
-      #puts answ
-      (precise*exp10).round == (less_precise*exp10).round
-    end
+    ## returns the index of the first value matching that m/z.  the argument m/z
+    ## may be less precise than the actual m/z (rounding to the same precision
+    ## given) but must be at least integer precision (after rounding)
+    ## implemented as binary search (bsearch from the web)
+    #def index(mz)
+      #mz_ar = mzs
+      #return_val = nil
+      #ind = mz_ar.bsearch_lower_boundary{|x| x <=> mz }
+      #if mz_ar[ind] == mz
+        #return_val = ind
+      #else 
+        ## do a rounding game to see which one is it, or nil
+        ## find all the values rounding to the same integer in the locale
+        ## test each one fully in turn
+        #mz = mz.to_f
+        #mz_size = mz_ar.size
+        #if ((ind < mz_size) and equal_after_rounding?(mz_ar[ind], mz))
+          #return_val = ind
+        #else # run the loop
+          #up = ind
+          #loop do
+            #up += 1
+            #if up >= mz_size
+              #break
+            #end
+            #mz_up = mz_ar[up]
+            #if (mz_up.ceil  - mz.ceil >= 2)
+              #break
+            #else
+              #if equal_after_rounding?(mz_up, mz)
+                #return_val = up
+                #return return_val
+              #end
+            #end
+          #end
+          #dn= ind
+          #loop do
+            #dn -= 1
+            #if dn < 0
+              #break
+            #end
+            #mz_dn = mz_ar[dn]
+            #if (mz.floor - mz_dn.floor >= 2)
+              #break
+            #else
+              #if equal_after_rounding?(mz_dn, mz)
+                #return_val = dn
+                #return return_val
+              #end
+            #end
+          #end
+        #end
+      #end
+      #return_val
+    #end
 
-    # returns 1 for ones place, 10 for tenths, 100 for hundredths
-    # to a precision exceeding 1e-6
-    def precision_as_neg_int(float) # :nodoc:
-      neg_exp10 = 1
-      loop do
-        over = float * neg_exp10
-        rounded = over.round
-        if (over - rounded).abs <= 1e-6
-          break
-        end
-        neg_exp10 *= 10
-      end
-      neg_exp10
-    end
+    ## less_precise should be a float
+    ## precise should be a float
+    #def equal_after_rounding?(precise, less_precise) # :nodoc:
+      ## determine the precision of less_precise
+      #exp10 = precision_as_neg_int(less_precise)
+      ##puts "EXP10: #{exp10}"
+      #answ = ((precise*exp10).round == (less_precise*exp10).round)
+      ##puts "TESTING FOR EQUAL: #{precise} #{less_precise}"
+      ##puts answ
+      #(precise*exp10).round == (less_precise*exp10).round
+    #end
+
+    ## returns 1 for ones place, 10 for tenths, 100 for hundredths
+    ## to a precision exceeding 1e-6
+    #def precision_as_neg_int(float) # :nodoc:
+      #neg_exp10 = 1
+      #loop do
+        #over = float * neg_exp10
+        #rounded = over.round
+        #if (over - rounded).abs <= 1e-6
+          #break
+        #end
+        #neg_exp10 *= 10
+      #end
+      #neg_exp10
+    #end
 
 
   end

metadata

@@ -1,18 +1,28 @@
 --- !ruby/object:Gem::Specification 
 name: ms-core
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors: 
-- John Prince
 - Simon Chiang
+- John Prince
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2009-05-22 00:00:00 -06:00
+date: 2009-09-08 00:00:00 -06:00
 default_executable: 
 dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: molecules
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.2.0
+    version: 
 - !ruby/object:Gem::Dependency 
   name: tap
   type: :development
@@ -29,42 +39,43 @@ dependencies:
   version_requirement: 
   version_requirements: !ruby/object:Gem::Requirement 
     requirements: 
-    - - "="
+    - - ">="
       - !ruby/object:Gem::Version 
         version: 1.3.0
     version: 
 description: 
-email: jtprince@gmail.com
+email: 
+- jtprince@gmail.com
 executables: []
 
 extensions: []
 
 extra_rdoc_files: 
-- changelog.txt
-- LICENSE
-- README
+- README.rdoc
+- MIT-LICENSE
+- History
 files: 
+- MIT-LICENSE
+- README.rdoc
+- History
+- lib/ms.rb
+- lib/ms/calc.rb
+- lib/ms/data.rb
+- lib/ms/data/interleaved.rb
+- lib/ms/data/lazy_io.rb
+- lib/ms/data/lazy_string.rb
+- lib/ms/data/simple.rb
+- lib/ms/data/transposed.rb
 - lib/ms/format/format_error.rb
-- lib/ms/id/search.rb
 - lib/ms/id/peptide.rb
 - lib/ms/id/protein.rb
+- lib/ms/id/search.rb
+- lib/ms/mass.rb
 - lib/ms/mass/aa.rb
-- lib/ms/data.rb
 - lib/ms/spectrum.rb
 - lib/ms/support/binary_search.rb
-- lib/ms/mass.rb
-- lib/ms/calc.rb
-- lib/ms/data/interleaved.rb
-- lib/ms/data/simple.rb
-- lib/ms/data/lazy_string.rb
-- lib/ms/data/transposed.rb
-- lib/ms/data/lazy_io.rb
-- lib/ms.rb
-- changelog.txt
-- LICENSE
-- README
 has_rdoc: true
-homepage: http://mspire.rubyforge.org/projects/ms-core/
+homepage: http://mspire.rubyforge.org/ms-core/
 licenses: []
 
 post_install_message: 
@@ -90,6 +101,6 @@ rubyforge_project: mspire
 rubygems_version: 1.3.2
 signing_key: 
 specification_version: 3
-summary: the core, shared library for mspire
+summary: basic, shared functionality for mspire libraries
 test_files: []
 

data/changelog.txt

@@ -1,196 +0,0 @@
-
-== version 0.1.7
-
-1. A couple of scripts and subroutines were hashing peptides but not on the file
-basename.  This would result in slightly incorrect results (any time there
-were overlapping scan numbers in multiple datasets, only the top one would be
-chosen).  The results would be correct for single runs.
-
-Output files that could be affected:
-*.top_per_scan.txt
-*.all_peps_per_scan.txt
-
-Scripts that could be affected:
-script/top_hit_per_scan.rb
-bin/filter_spec_id.rb
-script/filter-peps.rb
-bin/id_precision.rb
-
-Subroutines that were affected:
-spec_id.rb (pep_probs_by_* )
-spec_id.rb (top_peps_prefilter!)
-proph.rb uniq_by_seqcharge
-align.rb called uniq_by_seqcharge
-
-
-2. false_positive_rate.rb and protein_summary.rb (by extension) were using
-number of true positives on the x axis while in reality I was plotting the
-number of hits.  I've updated x axis labels to reflect this change.  In
-addition, since the term 'false positive rate' has such a distinct definition
-in classical ROC plots and binary statistics, I've decided to work primarily
-in terms of precision (TP/(TP+FP)).  I've purged the terms 'False Positive
-Rate' and 'FPR' from the package. It's been suggested that FP/(TP+FP) be
-called the False Positive Predictive Rate (FPPR).  I will probably implement
-this in a future release.
-
-== version 0.2.0
-
-Revamped the way SpecID works (it is now mixed-in).
-Added support for modifications to bioworks_to_pepxml.rb
-Can read .srf files (nearly interchangeable with bioworks files)
-Redid filter.rb
-
-== version 0.2.1
-
-minor bugfix
-
-== version 0.2.2
-
-made compatible with Bioworks fasta file reverser and updated tutorial.
-Killed classify_by_prefix routine in favor of classify_by_false_flag which has
-a prefix option
-
-== version 0.2.3
-
-in protein_summary.rb added handling for proteins with no annotation. (either
-dispaly NA or use gi2annnot to grab them from NCBI)
-
-== version 0.2.5
-
-renamed prep_list in roc (potential breaks in code)
-
-== version 0.2.6
-
-1. Massive refactorization of filtering and validation.  Validation objects are
-created and then can be used to validate just about anything.
-2. Massive redo of the parsing of MS runs.  Can parse mzXML v1, v2.X
-(including readw broken output), and mzData (even Thermo's broken output).
-4. Moved all tests to specs (rspec).
-5. Can read gradient programs off of .meth or .RAW files (both Xcal 1.X and
-2.X)
-
-Bugfixes:
-1. The search_summary 'base_name' in pepxml output was incorrect (this did not
-appear to influence our analyses, however). Fixed.
-2. Enzymes with no exceptions (e.g., cuts at KR) would report one too many
-missed cleavages if the last amino acid was a cut point. Fixed.
-
-== version 0.2.7
-
-1. In conversion from bioworks to pepxml, the default was trypsin (KR/P).
-Now, the sample enzyme is set explicitly from the params file and the option
-is not available.  This can give more accuract pepxml files than from
-previous depending on your enzyme.
-
-== version 0.2.9
-
-1. Added support for phobius transmembrane predictions
-2. have filter_and_validate.rb working well (multiple validators allowed).
-3. Can read bioworks 3.3.1 .srf files (.srf version 3.5 files)
-4. Added a bias validator
-
-== version 0.2.10
-
-1. Fixed --hits_separate flag in spec_id/filter
-
-== version 0.2.11
-
-1. Added prob precision support and reorganized filter_and_validate libs
-
-== version 0.2.12
-
-1. Fixed bug in transmem for prob and others.
-2. Can use axml (XMLParser based) or libxml depending on availability
-
-== version 0.2.13
-
-1. Fixed issue with --hits_separate
-2. filter_and_validate.rb requires decoy validator if decoy proteins
-(refactored code)
-
-== version 0.2.14
-
-1. Can read PeptideProphet files (should be able to read pepxml files, too)
-2. API change: Some slight modifications to the Sequest::PepXML object
-interfaces and implementations (using ArrayClass)
-
-== version 0.2.15
-
-1. can convert srf files to sqt files
-
-== version 0.3.0
-
-1. IMPORTANT BUG FIX: protein reporting in srf files is correct now (proteins after the first protein were being assigned to the last hit in an out file).
-2. SQT export is correct and works at least on 3.2 and 3.3.1.
-
-== version 0.3.1
-
-1. Bug fix in srf filtering (num_hits adjusted)
-
-== version 0.3.2
-
-1. Uses sequest peptide_mass_tolerance filter on srf group files by default
-now.
-
-== version 0.3.3
-
-1. Worked out minor kinks in prob_precision.rb
-
-== version 0.3.4
-
-1. filters >= +3 charged ions now.
-
-== version 0.3.5
-
-1. fixed creation of background distribution in validators (hash_by base_name,
-first_scan, charge now)
-
-== version 0.3.6
-
-1. split off bad_aa_est from bad_aa
-
-== version 0.3.7
-
-1. can deal with No_Enzyme searches now (while still capable of setting
-sample_enzyme)
-
-== version 0.3.8
-
-1. can set a decoy to target ratio for decoy validation
-2. added mass calculator in Mass::Calculator
-
-== version 0.3.9
-
-1. doesn't clobber mzdata filename in ms_to_lmat.rb conversion
-
-== version 0.3.10
-
-1. added run_percolator.rb script which makes running multiple files easy
-
-== version 0.3.11
-
-1. faster sensing of bad scan tags in mzXML v. 2.0 files
-2. implemented lazy evaluation of spectrum in 2 different ways allowing much
-larger files to be parsed
-
-== version 0.4.0
-
-1. ** INTERFACE CHANGE: each scan can only have one precursor (used to be an array)
-2. ** INTERFACE CHANGE: spectrum mz and intensity data accessed with mzs and intensities
-3. lazy eval working on mzData
-4. mzData not necessarily guaranteed to have precursor intensities on lazy
-eval methos (however, the method intensity_at_mz will still work (causing
-evaluation))
-
-== version 0.4.1
-
-1. added support for reading mzXML version 3.0 (may fail in some cases)
-
-== version 0.4.2
-
-1. added MS::MSRun.open method
-2. added method to write dta files from SRF
-
-== version 0.4.3
-
-1. added to_mfg_file from SRF