mspire 0.5.0 → 0.6.1

metadata

@@ -1,88 +1,205 @@
 --- !ruby/object:Gem::Specification 
 name: mspire
 version: !ruby/object:Gem::Version 
-  version: 0.5.0
+  prerelease: 
+  version: 0.6.1
 platform: ruby
 authors: 
-- John Prince
+- John T. Prince
 - Simon Chiang
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2008-11-20 00:00:00 -07:00
-default_executable: 
+date: 2012-01-25 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: tap
+  name: nokogiri
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: "1.5"
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: "2.6"
   type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: jeweler
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
-    - - ">="
+    - - ~>
       - !ruby/object:Gem::Version 
-        version: 0.11.2
-    version: 
+        version: 1.5.2
+  type: :development
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
-  name: minitest
+  name: rcov
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
   type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  version_requirements: *id004
+- !ruby/object:Gem::Dependency 
+  name: obo
+  prerelease: false
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
-    - - "="
+    - - ">="
       - !ruby/object:Gem::Version 
-        version: 1.3.0
-    version: 
-description: A library for working with mass spectrometry proteomics data.
-email: jprince@icmb.utexas.edu
+        version: 0.1.0
+  type: :development
+  version_requirements: *id005
+description: mass spectrometry proteomics, lipidomics, and tools, a rewrite of mspire, merging of ms-* gems
+email: jtprince@gmail.com
 executables: []
 
 extensions: []
 
 extra_rdoc_files: 
-- changelog.txt
 - LICENSE
-- README
+- README.rdoc
 files: 
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/cv.rb
+- lib/cv/description.rb
+- lib/cv/param.rb
+- lib/io/bookmark.rb
+- lib/merge.rb
 - lib/ms.rb
-- lib/ms/calc.rb
-- lib/ms/data.rb
-- lib/ms/data/interleaved.rb
-- lib/ms/data/transposed.rb
-- lib/ms/data/simple.rb
-- lib/ms/data/lazy_io.rb
-- lib/ms/data/lazy_string.rb
-- lib/ms/format/format_error.rb
-- lib/ms/support/binary_search.rb
+- lib/ms/cvlist.rb
+- lib/ms/digester.rb
+- lib/ms/fasta.rb
+- lib/ms/ident.rb
+- lib/ms/ident/peptide.rb
+- lib/ms/ident/peptide/db.rb
+- lib/ms/ident/peptide_hit.rb
+- lib/ms/ident/peptide_hit/qvalue.rb
+- lib/ms/ident/pepxml.rb
+- lib/ms/ident/pepxml/modifications.rb
+- lib/ms/ident/pepxml/msms_pipeline_analysis.rb
+- lib/ms/ident/pepxml/msms_run_summary.rb
+- lib/ms/ident/pepxml/parameters.rb
+- lib/ms/ident/pepxml/sample_enzyme.rb
+- lib/ms/ident/pepxml/search_database.rb
+- lib/ms/ident/pepxml/search_hit.rb
+- lib/ms/ident/pepxml/search_hit/modification_info.rb
+- lib/ms/ident/pepxml/search_result.rb
+- lib/ms/ident/pepxml/search_summary.rb
+- lib/ms/ident/pepxml/spectrum_query.rb
+- lib/ms/ident/protein.rb
+- lib/ms/ident/protein_group.rb
+- lib/ms/ident/search.rb
+- lib/ms/isotope/aa.rb
+- lib/ms/mascot.rb
+- lib/ms/mass.rb
+- lib/ms/mass/aa.rb
+- lib/ms/mzml.rb
+- lib/ms/mzml/index_list.rb
+- lib/ms/mzml/plms1.rb
+- lib/ms/obo.rb
+- lib/ms/plms1.rb
+- lib/ms/quant/qspec.rb
+- lib/ms/quant/qspec/protein_group_comparison.rb
 - lib/ms/spectrum.rb
-- changelog.txt
-- LICENSE
-- README
-has_rdoc: true
-homepage: http://mspire.rubyforge.org
+- lib/msplat.rb
+- lib/obo/ims.rb
+- lib/obo/ms.rb
+- lib/obo/ontology.rb
+- lib/obo/unit.rb
+- lib/openany.rb
+- lib/write_file_or_string.rb
+- obo/ims.obo
+- obo/ms.obo
+- obo/unit.obo
+- spec/ms/cvlist_spec.rb
+- spec/ms/digester_spec.rb
+- spec/ms/fasta_spec.rb
+- spec/ms/ident/peptide/db_spec.rb
+- spec/ms/ident/pepxml/sample_enzyme_spec.rb
+- spec/ms/ident/pepxml/search_hit/modification_info_spec.rb
+- spec/ms/ident/pepxml_spec.rb
+- spec/ms/ident/protein_group_spec.rb
+- spec/ms/mass_spec.rb
+- spec/ms/mzml/index_list_spec.rb
+- spec/ms/mzml/plms1_spec.rb
+- spec/ms/mzml_spec.rb
+- spec/ms/plms1_spec.rb
+- spec/ms/quant/qspec_spec.rb
+- spec/msplat_spec.rb
+- spec/obo_spec.rb
+- spec/spec_helper.rb
+- spec/testfiles/ms/ident/peptide/db/uni_11_sp_tr.fasta
+- spec/testfiles/ms/ident/peptide/db/uni_11_sp_tr.msd_clvg2.min_aaseq4.yml
+- spec/testfiles/ms/mzml/j24z.idx_comp.3.mzML
+- spec/testfiles/ms/mzml/openms.noidx_nocomp.12.mzML
+- spec/testfiles/ms/quant/kill_extra_tabs.rb
+- spec/testfiles/ms/quant/max_quant_output.provenance.txt
+- spec/testfiles/ms/quant/max_quant_output.txt
+- spec/testfiles/ms/quant/pdcd5_final.killedextratabs.tsv
+- spec/testfiles/ms/quant/pdcd5_final.killedextratabs.tsv_qspecgp
+- spec/testfiles/ms/quant/pdcd5_final.killedextratabs.tsv_qspecgp.csv
+- spec/testfiles/ms/quant/pdcd5_final.txt
+- spec/testfiles/ms/quant/pdcd5_final.txt_qspecgp
+- spec/testfiles/ms/quant/pdcd5_lfq_qspec.CSV.csv
+- spec/testfiles/ms/quant/pdcd5_lfq_qspec.csv
+- spec/testfiles/ms/quant/pdcd5_lfq_qspec.oneprot.csv
+- spec/testfiles/ms/quant/pdcd5_lfq_qspec.oneprot.tsv
+- spec/testfiles/ms/quant/pdcd5_lfq_qspec.oneprot.tsv_qspecgp
+- spec/testfiles/ms/quant/pdcd5_lfq_qspec.oneprot.tsv_qspecgp.csv
+- spec/testfiles/ms/quant/pdcd5_lfq_qspec.txt
+- spec/testfiles/ms/quant/pdcd5_lfq_tabdel.txt
+- spec/testfiles/ms/quant/pdcd5_lfq_tabdel.txt_qspecgp
+- spec/testfiles/ms/quant/remove_rest_of_proteins.rb
+- spec/testfiles/ms/quant/unlog_transform.rb
+- spec/testfiles/plms1/output.key
+homepage: http://github.com/princelab/mspire
+licenses: 
+- MIT
 post_install_message: 
 rdoc_options: []
 
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
       version: "0"
-  version: 
 requirements: []
 
-rubyforge_project: mspire
-rubygems_version: 1.3.0
+rubyforge_project: 
+rubygems_version: 1.8.10
 signing_key: 
-specification_version: 2
-summary: Mass Spectrometry Proteomics Objects, Scripts, and Executables
+specification_version: 3
+summary: mass spectrometry proteomics, lipidomics, and tools
 test_files: []
 

data/README

@@ -1,77 +0,0 @@
-= {Mspire}[http://mspire.rubyforge.org]
-
-A library for working with mass spectrometry proteomics data.
-
-<em> Mspire is going through a re-write as of version 0.5.0 to support a new
-development model.  Many modules are absent but will gradually be added back.
-Use the 0.4 releases as necessary. </em>
-
-== Description
-
-mspire - 'Mass Spectrometry Proteomics in Ruby' is a collection of tools for
-working with MS proteomics data in ruby.  It seeks to provide support for open
-standards (e.g., parsers for mzData, mzXML, Peptide/Protein Prophet and the
-TPP) and contribute other useful functionality for working with mass
-spectrometry data in ruby.
-
-* Lighthouse[http://bahuvrihi.lighthouseapp.com/projects/16692-mspire/tickets]
-* Github[http://github.com/bahuvrihi/mspire/tree/master]
-* {Google Group}[http://groups.google.com/group/mspire-forum]
-
---
-=== Current Focus
-
-The project is currently focusing on the following:
-
-* SEQUEST data (particularly the output of Bioworks 3.2-3.3.1)
-* mzXML
-* mzData
-* ProteinProphet
-* Preparation of files for [obiwarp](http://obi-warp.sourceforge.net/)
-
-=== Features
-
-* mzXML (version 1, 2, and 3) parsing
-* mzData parsing
-* bioworks .srf (binary files) reader
-* read/write .sqt files
-* bioworks to PeptideProphet input (pepXML files)
-* lightweight APEX values parser
-* histogram protein probabilities
-* protein summary views with custom false ID cutoff values
-* conversion to OBI-Warp input files
-* portable: works across platforms
-
-Validation by:
-  * Various Decoy Database search options: Reverse/Shuffle, concatenated/separate, with various hashing options (e.g., by amino acid sequence + charge)
-  * Amino acid (e.g., search for unblocked cysteines)
-  * Transmembrane prediction (Phobius or TopPred)
-  * Generic sample bias (e.g., low abundance/high abundance proteins)
-  * Defined sample
-
-=== Spectra and Spectra Identification
-
-The [MS](ms/index.html) namespace contains objects for working with mass spectra and associated file formats.
-
-The [SpecID](spec_id/index.html) namespace contains objects for working with spectral identifications.
-
-=== Tutorials
-
-* [Database Searching Tutorial](tutorial/database_searching/index.html) -
-Demonstrates two methods for running and analysing Bioworks output to obtain
-false positive rates using mspire executables.
-++
-
-== Installation
-
-Mspire is available as a gem on RubyForge[http://rubyforge.org/projects/mspire].  Use:
-
-  % gem install mspire
-
-= Warning
-
-This is an experimental package.  As such, all versions prior to version 1.0
-may contain interface changes on minor revisions (major.minor.build) (e.g.,
-0.4.0 may contain interface change from 0.3.9).  Beyond version 1.0, the
-versioning scheme will be strictly adhered to (no interface changes except on
-major revisions).

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

data/lib/ms/calc.rb

@@ -1,32 +0,0 @@
-module Ms
-  module Calc 
-      module_function
-    
-      #
-      # ppm calculations... maybe use RUnit
-      #
-  
-      def ppm_tol_at(mz, ppm)
-        1.0 * mz * ppm / 10**6
-      end
-
-      def ppm_span_at(mz, ppm)
-        tol = ppm_tol_at(mz, ppm)
-        [mz-tol, mz+tol]
-      end
-  
-      def ppm_range_at(mz, ppm)
-        mz = mz.to_f
-        tol = ppm_tol_at(mz, ppm)
-        mz-tol...mz+tol
-      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
-      
-  end
-end

data/lib/ms/data/interleaved.rb

@@ -1,60 +0,0 @@
-require 'ms/data/simple'
-
-module Ms
-  module Data
-    module_function
-    
-    # Initializes a new interleaved data array.
-    def new_interleaved(unresolved_data, n=2)
-      Interleaved.new(unresolved_data, n=2)
-    end
-    
-    # An Interleaved data array lazily evaluates it's unresolved data as 
-    # an interleaved array of n members.  The unresolved data is evaluated 
-    # into an array using to_a.
-    #
-    #   i = Ms::Data::Interleaved.new([1,4,2,5,3,6])
-    #   i.unresolved_data    # => [1,4,2,5,3,6]
-    #   i.data               # => []
-    #   i[0]                 # => [1,2,3]
-    #   i[1]                 # => [4,5,6]
-    #   i.data               # => [[1,2,3], [4,5,6]]
-    #
-    class Interleaved < Simple
-      attr_reader :n
-      
-      def initialize(unresolved_data, n=2)
-        @n = 2
-        super(unresolved_data)
-      end
-      
-      def [](index)
-        resolve.data[index]
-      end
-      
-      def resolved?
-        !@data.empty?
-      end
-    
-      def resolve
-        return(self) if resolved?
-        
-        unresolved_data = @unresolved_data.to_a
-        
-        unless unresolved_data.length % n == 0
-          raise ArgumentError, "interleaved data must have a number of elements evenly divisible by n (#{n})"
-        end
-        
-        n.times { @data << [] }
-        map = @data * (unresolved_data.length/n)
-        
-        unresolved_data.each_with_index do |item, i|
-          map[i] << item
-        end
-
-        self
-      end
-      
-    end
-  end
-end

data/lib/ms/data/lazy_io.rb

@@ -1,73 +0,0 @@
-module Ms
-  module Data
-    
-    # LazyIO represents data to be lazily read from an IO.  To read the data
-    # from the IO, either string or to_a may be called (to_a unpacks the 
-    # string into an array using the decode_format and unpack_format).
-    #
-    # LazyIO is a suitable unresolved_data source for Ms::Data formats.
-    class LazyIO
-      NETWORK_FLOAT = 'g*'
-      NETWORK_DOUBLE = 'G*'
-      LITTLE_ENDIAN_FLOAT = 'e*'
-      LITTLE_ENDIAN_DOUBLE = 'E*'
-      BASE_64 = 'm'
-      
-      class << self
-        # Returns the unpacking code for the given precision (32 or 64-bit)
-        # and network order (true for big-endian).
-        def unpack_code(precision, network_order)
-          case precision
-          when 32 then network_order ? NETWORK_FLOAT : LITTLE_ENDIAN_FLOAT
-          when 64 then network_order ? NETWORK_DOUBLE : LITTLE_ENDIAN_DOUBLE
-          else raise ArgumentError, "unknown precision (should be 32 or 64): #{precision}"
-          end
-        end
-      end
-    
-      # The IO from which string is read
-      attr_reader :io
-      
-      # The start index for reading string
-      attr_reader :start_index
-      
-      # The number of bytes to be read from io when evaluating string
-      attr_reader :num_bytes
-      
-      # Indicates the unpacking format
-      attr_reader :unpack_format
-      
-      # Indicates a decoding format, may be false to unpack string
-      # without decoding.
-      attr_reader :decode_format
-      
-      def initialize(io, start_index=io.pos, num_bytes=nil, unpack_format=NETWORK_FLOAT, decode_format=BASE_64)
-        @io = io
-        @start_index = start_index
-        @num_bytes = num_bytes
-        @unpack_format = unpack_format
-        @decode_format = decode_format
-      end
-      
-      # Positions io at start_index and reads a string of num_bytes length.
-      # The string is newly read from io each time string is called.
-      def string
-        io.pos = start_index unless io.pos == start_index
-        io.read(num_bytes)
-      end
-      
-      # Resets the cached array (returned by to_a) so that the array will
-      # be re-read from io.
-      def reset
-        @array = nil
-      end
-      
-      # Reads string and unpacks using decode_format and unpack_code.  The
-      # array is cached internally; to re-read the array, use reset.
-      def to_a
-        @array ||= (decode_format ? string.unpack(decode_format)[0] : string).unpack(unpack_format)
-      end
-
-    end
-  end
-end

data/lib/ms/data/lazy_string.rb

@@ -1,15 +0,0 @@
-require 'ms/data/lazy_io'
-require 'stringio'
-
-module Ms
-  module Data
-    
-    # LazyString is a LazyIO initialized from a string, which is converted into
-    # a StringIO.
-    class LazyString < LazyIO
-      def initialize(string, unpack_format=NETWORK_FLOAT, decode_format=BASE_64)
-        super(StringIO.new(string), 0, string.length, unpack_format, decode_format)
-      end
-    end
-  end
-end