divvy_proteomics 0.0.1

data/spec/divvy_proteomics_spec.rb

@@ -0,0 +1,106 @@
+require 'systemu'
+require 'pp'
+require 'open3'
+require 'tempfile'
+
+# To run this test:
+# $ rspec /path/to/test_script_being_tested.rb
+
+# Assumes that the name of the file being tested is ../something.rb, and the name of this script is test_something.rb
+$:.unshift File.join(File.dirname(__FILE__),'..')
+script_under_test = File.basename(__FILE__).gsub(/^test_/,'')
+path_to_script = File.join(File.dirname(__FILE__),'..','bin','divvy_spectra')
+
+TEST_DATA_DIR = File.join(File.dirname(__FILE__),'data')
+
+describe script_under_test do
+  let(:header){"ID\tUnique spectra\tNon-unique spectra\tEstimated total spectra\tNormalised spectral count\tDescription\tProteins sharing spectra\n"}
+  it 'should do 1 protein hit' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/single_protein.csv --trace error"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['Mstor_v4.3.2:1344','188','0','188.0','1.0','Methanoflorens_stordalmirensis_v4.3.2_01361 Methyl-coenzyme M reductase I subunit gamma ',''].join("\t")+"\n"
+    stdout.should eq(answer)
+  end
+
+  it 'should do peptides that hit 2 proteins' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/three_proteins.csv --trace error"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['Mstor_v4.3.2:1344','37','151','89.7075471698113','0.29509061569016876','Methanoflorens_stordalmirensis_v4.3.2_01361 Methyl-coenzyme M reductase I subunit gamma ','eDeep20120820:eD1_8237_2'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_8237_2','69','151','167.29245283018867','0.5503041211519364','methyl-coenzyme M reductase gamma subunit # pI:8.94 MW:27683 ','Mstor_v4.3.2:1344'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_1639_1','47','0','47.0','0.15460526315789475','chaperonin GroEL # pI:9.22 MW:10181 ',''+"\n"].join("\t")
+    stdout.should eq(answer)
+  end
+
+  it 'should do peptides that hit more than 2 proteins' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/multiply_mapped_spectra.csv --trace error"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['Mstor_v4.3.2:1344','37','151','89.7075471698113','0.24781090378400913','Methanoflorens_stordalmirensis_v4.3.2_01361 Methyl-coenzyme M reductase I subunit gamma ','eDeep20120820:eD1_8237_2'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_8237_2','69','151','167.29245283018867','0.46213384759720627','methyl-coenzyme M reductase gamma subunit # pI:8.94 MW:27683 ','Mstor_v4.3.2:1344'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_1639_1','47','0','47.0','0.1298342541436464','chaperonin GroEL # pI:9.22 MW:10181 ',''+"\n"].join("\t")+
+    ['eDeep20120820:eD1_13975_5','9','1','9.157894736842106','0.02529805175923234','chaperonin GroEL # pI:6.58 MW:12040 ','eDeep20120820:eD1_3396_1,eDeep20120820:eD1_1494_8'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_3396_1','38','1','38.666666666666664','0.10681399631675874','TGroEL # pI:9.70 MW:6451 ','eDeep20120820:eD1_13975_5,eDeep20120820:eD1_1494_8'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_1494_8','10','1','10.175438596491228','0.028108946399147038','chaperonin GroEL # pI:4.93 MW:54101 ','eDeep20120820:eD1_13975_5,eDeep20120820:eD1_3396_1'+"\n"].join("\t")
+
+    stdout.should eq(answer)
+  end
+
+  it 'should ignore contaminants' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/three_proteins_with_contaminant.csv --trace error"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['Mstor_v4.3.2:1344','37','151','89.7075471698113','0.29509061569016876','Methanoflorens_stordalmirensis_v4.3.2_01361 Methyl-coenzyme M reductase I subunit gamma ','eDeep20120820:eD1_8237_2'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_8237_2','69','151','167.29245283018867','0.5503041211519364','methyl-coenzyme M reductase gamma subunit # pI:8.94 MW:27683 ','Mstor_v4.3.2:1344'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_1639_1','47','0','47.0','0.15460526315789475','chaperonin GroEL # pI:9.22 MW:10181 ',''+"\n"].join("\t")
+    stdout.should eq(answer)
+  end
+
+  it 'should do ok merging spectra' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/three_proteins_meant_for_merge.csv --merge-proteins #{File.join(TEST_DATA_DIR,'merge_definition.csv')} --trace error"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['Mstor_v4.3.2:1344','37','151','89.7075471698113','0.29509061569016876','Methanoflorens_stordalmirensis_v4.3.2_01361 Methyl-coenzyme M reductase I subunit gamma ','eDeep20120820:eD1_8237_2'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_8237_2','69','151','167.29245283018867','0.5503041211519364','methyl-coenzyme M reductase gamma subunit # pI:8.94 MW:27683 ','Mstor_v4.3.2:1344'+"\n"].join("\t")+
+    ['eDeep20120820:eD1_1639_1','47','0','47.0','0.15460526315789475','chaperonin GroEL # pI:9.22 MW:10181 ',''+"\n"].join("\t")
+    stdout.should eq(answer)
+  end
+
+  it 'should do 1 protein with an alias' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/single_protein_with_aliases.csv --trace error"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['Mstor_v4.3.2:1344','0','188','94.0','0.5','Methanoflorens_stordalmirensis_v4.3.2_01361 Methyl-coenzyme M reductase I subunit gamma ','alias1'+"\n"].join("\t")+
+    ['alias1','0','188','94.0','0.5','alias1 Methyl-coenzyme M reductase I subunit gamma ','Mstor_v4.3.2:1344'+"\n"].join("\t")
+    stdout.should eq(answer), test_file
+  end
+
+  it 'should do a whitelist correctly' do
+    Tempfile.open('test_divvy_spectra') do |tempfile|
+      %w(eDeep20120820:eD1_8237_2 eDeep20120820:eD1_1639_1).each {|i| tempfile.puts i}
+      tempfile.close
+
+      test_file = "#{path_to_script} --whitelist #{tempfile.path} #{TEST_DATA_DIR}/three_proteins.csv --trace error"
+      status, stdout, stderr = systemu test_file
+
+      stderr.should eq("")
+      answer = header+
+      ['eDeep20120820:eD1_8237_2','69','151','167.29245283018867','0.5503041211519364','methyl-coenzyme M reductase gamma subunit # pI:8.94 MW:27683 ','Mstor_v4.3.2:1344'+"\n"].join("\t")+
+      ['eDeep20120820:eD1_1639_1','47','0','47.0','0.15460526315789475','chaperonin GroEL # pI:9.22 MW:10181 ',''+"\n"].join("\t")
+      stdout.should eq(answer)
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,12 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'rspec'
+require 'divvy_proteomics'
+
+# Requires supporting files with custom matchers and macros, etc,
+# in ./support/ and its subdirectories.
+Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
+
+RSpec.configure do |config|
+  
+end

metadata

@@ -0,0 +1,166 @@
+--- !ruby/object:Gem::Specification
+name: divvy_proteomics
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Ben J Woodcroft
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-04-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bio-logger
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: systemu
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 2.8.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 2.8.0
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '3.12'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+description: divvy up spectra from DTASelect files in a somewhat parsimonious way
+email: donttrustben@gmail.com
+executables:
+- divvy_spectra
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.md
+files:
+- .document
+- .rspec
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- VERSION
+- bin/divvy_spectra
+- divvy_proteomics.gemspec
+- lib/divvy_proteomics.rb
+- spec/data/merge_definition.csv
+- spec/data/multiply_mapped_spectra.csv
+- spec/data/single_protein.csv
+- spec/data/single_protein_with_aliases.csv
+- spec/data/three_proteins.csv
+- spec/data/three_proteins_meant_for_merge.csv
+- spec/data/three_proteins_with_contaminant.csv
+- spec/divvy_proteomics_spec.rb
+- spec/spec_helper.rb
+homepage: http://github.com/wwood/divvy_proteomics
+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'
+      segments:
+      - 0
+      hash: -659530255
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: divvy up spectra from DTASelect files in a parsimonious way
+test_files: []