mspire 0.8.0 → 0.8.1

data/README.md

@@ -0,0 +1,60 @@
+# mspire
+
+Mspire is a full featured library for working with mass spectrometry data,
+particularly proteomic, metabolomic and lipidomic data sets.  It aims to be
+fast, robust, and beautiful.
+
+## Cite
+
+Prince JT, Marcotte EM. <b>mspire: mass spectrometry proteomics in Ruby.</b> *Bioinformatics.* 2008 Dec 1;24(23):2796-7. ([pubmed](http://www.ncbi.nlm.nih.gov/pubmed/18930952))
+
+## Features
+
+### mzml
+
+* Reading *and* writing
+* True random access to spectra or chromatograms
+* Complete object model with implicit object link resolution (even with random access)
+* Simplified creation of and full support for CV params and referenceable param groups
+
+### imzml
+
+Mspire is the *only* converter from mzml into imzml.  
+
+* handles both processed and continuous modes
+* gracefully handles SIM data
+
+### Other Feature Highlights
+
+* isotope distribution prediction: uses fastest method known (FFT convolution)
+* protein digestion: Support for 32 enzymes/variants by name
+* pepxml: full object model and complete write support
+* fasta files: complete programmatic access to description lines (via bio-ruby)
+* peak lists: merging/summing and splitting algorithms
+* obo: ontology hash access
+* molecular formulas: can do arithmetic with formulas
+* calculates q-values
+
+## Examples
+
+### mzml
+
+    require 'ms/mzml'
+
+    MS::Mzml.open("somefile.mzml") do |mzml|
+      spectrum = mzml[0]   # the first spectrum ( same as mzml.spectrum(0) )
+      spectrum = mzml["controllerType=0 controllerNumber=1 scan=2"]  # query by id string
+      mzml.spectrum_from_scan_num(23) # raises ScanNumbersNotFound or ScanNumbersNotUnique errors if problems
+    end
+
+    require 'ms/mass/aa'
+
+    MS::Mass::AA::MONO['A'] # or access by symbol
+
+## Acronym
+
+<i>M</i>ass <i>SP</i>ectrometry <i>I</i>n <i>R</i>uby.  Mspire originally stood for <i>M</i>ass <i>S</i>pectrometry <i>P</i>roteomics <i>I</i>n <i>R</i>uby but the library has since proven useful for all kinds of mass spectrometry projects, hence the more inclusive form.  The <i>e</i> was originally included for aesthetic reasons, but it also provides the user/developer the ability to attach whatever <i>E</i>xclamation or <i>E</i>pithet they choose to the acronym (the best ones will begin with <i>e</i> of course).
+
+## Copyright
+
+MIT license.  See LICENSE for details.

data/Rakefile

@@ -1,6 +1,7 @@
 require 'rubygems'
 require 'rake'
 require 'rspec/core/rake_task'
+require 'yard'
 
 require 'jeweler'
 Jeweler::Tasks.new do |gem|
@@ -35,6 +36,11 @@ RSpec::Core::RakeTask.new(:spec) do |spec|
   spec.pattern = FileList['spec/**/*_spec.rb']
 end
 
+YARD::Rake::YardocTask.new do |t|
+  t.files   = ['lib/**/*.rb', 'obo/**/*', 'README.md', 'script/**/*']   # optional
+  #t.options = ['--any', '--extra', '--opts'] # optional
+end
+
 RSpec::Core::RakeTask.new(:rcov) do |spec|
   spec.pattern = 'spec/**/*_spec.rb'
   spec.rcov = true
@@ -59,7 +65,13 @@ Rake::RDocTask.new do |rdoc|
   rdoc.rdoc_files.include('lib/**/*.rb')
 end
 
-# need to write updaters to get latest obo
-#task 'update-obo' do
-#  "http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo"
-#end
+desc "downloads the latest obo to appropriate spot"
+task 'obo-update' do
+  require 'mspire/mzml/cv'
+  require 'open-uri'
+  Mspire::Mzml::CV::DEFAULT_CVS.each do |const|
+    obo_fn = File.dirname(__FILE__) + "/obo/#{const.id.downcase}.obo"
+    File.write(obo_fn, open(const.uri, &:read).gsub(/\r\n?/, "\n"))
+    puts "NOTE: if a file changed (git status), then update lib/mspire/mzml/cv.rb with correct version !!!"
+  end
+end

data/VERSION

@@ -1 +1 @@
-0.8.0
+0.8.1

data/lib/mspire/imzml/writer/commandline.rb

@@ -83,7 +83,7 @@ output: <file>.imzML and <file>.ibd
     end
   end
 
-  def self.run(argv, globalopts)
+  def self.run(argv, globalopts=[])
     begin
       opts = parser.parse(argv)
     rescue Trollop::HelpNeeded

data/lib/mspire/imzml/writer.rb

@@ -4,6 +4,7 @@ require 'uuid'
 require 'cv'
 require 'mspire/mzml'
 require 'mspire/mzml/spectrum'
+require 'mspire/spectrum'
 require 'pathname'
 require 'digest/sha1'
 
@@ -325,7 +326,25 @@ module Mspire::Imzml
           sourcefile_id = "source_file_#{i}"
           sourcefile_ids << sourcefile_id
           Mspire::Mzml.open(mzml_filename) do |mzml|
-            mzml.each_with_index do |spec,i| 
+            enumerates_spectra = 
+              # handle SIM files "MS:1001472", "selected ion monitoring chromatogram"
+              if mzml.file_description.file_content.fetch_by_acc('MS:1001472')
+                # handle normal mzml files
+                mz_ars = []
+                its_ars = []
+                mzml.each_chromatogram.each do |chromatogram,i| 
+                  next unless chromatogram.fetch_by_acc('MS:1001472')
+                  target_mz = chromatogram.precursor.isolation_window.fetch_by_acc('MS:1000827').to_f
+                  its = chromatogram.intensities
+                  mz_ars << Array.new(its.size, target_mz)
+                  its_ars << its
+                end
+                mz_ars.transpose.zip(its_ars.transpose).map {|mzs, its| Mspire::Spectrum.new([mzs, its]) }
+              else
+                # normal mzml file with spectra
+                mzml
+              end
+            enumerates_spectra.each_with_index do |spec,i| 
               break if config[:trim_to] && (i >= config[:trim_to])
               sourcefile_id_parallel_to_spectra << sourcefile_id 
               yielder << spec

data/lib/mspire/mzml/cv.rb

@@ -38,12 +38,11 @@ module Mspire
         self.new(xml[:id], xml[:fullName], xml[:URI], xml[:version])
       end
 
-      # These are derived by looking in the obo folder at the top of mspire
       IMS = self.new("IMS",  "Imaging MS Ontology", "http://www.maldi-msi.org/download/imzml/imagingMS.obo", "0.9.1")
-      MS = self.new('MS', "Proteomics Standards Initiative Mass Spectrometry Ontology", "http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo", "3.18.0")
+      MS = self.new('MS', "Proteomics Standards Initiative Mass Spectrometry Ontology", "http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo", "3.29.0")
       # the version for UO doesn't really exist: seen files where they use the
-      # download date: DD:MM:YYY
-      UO = self.new("UO", "Unit Ontology", "http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/unit.obo", "16:02:2012")
+      # download date: DD:MM:YYY.  I'm going to use the save date in the header.
+      UO = self.new("UO", "Unit Ontology", "http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/unit.obo", "12:10:2011")
 
       DEFAULT_CVS = [MS, UO, IMS]
 

data/obo/ims.obo

@@ -1,4 +1,3 @@
-
 format-version: 1.2
 date: 08:09:2008 13:53
 saved-by: Thorsten Schramm
@@ -377,7 +376,7 @@ relationship: is_a IMS:1000002 ! Sample Stage
 relationship: has_units UO:0000017 ! Micrometer
 
 [Term]
-id: IMS:10000202
+id: IMS:1000202
 name: target material
 def: "Describes the material the target is made of." [COMPUTIS:IMS]
 xref: value-type:xsd\:string "The allowed value-type for this CV term."
@@ -558,5 +557,4 @@ name: solvent flowrate
 def: "Rate with which the solvent is flowing on the surface of the imaging object" [COMPUTIS:IMS]
 xref: value-type:xsd\:float "The allowed value-type for this CV term."
 relationship: is_a IMS:1000121 ! DESI
-relationship: has_units IMS:1000131 ! milliliter per minute
-
+relationship: has_units IMS:1000131 ! milliliter per minute