divvy_proteomics 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f930bb8ef783e793512f0d50bd579055ba475476
-  data.tar.gz: a445f2ef2ea22f7453b4e5b08fb66775797ea9bc
+  metadata.gz: 05ddf71aecd113201c370185104006af9705a525
+  data.tar.gz: b450d8ecd60717f7286f234aed29beaf455aa4eb
 SHA512:
-  metadata.gz: 9020c67860e40394138a02cfcf53a85665cc731292650f1c71b46990d3800de2fe9c2643597a277fe09ca17eede493ec7268496e529bb1a625efdd5f0347c7a9
-  data.tar.gz: 462c1c66db781653937b156023dc404804d8002f661872dab7b74c8a79d8576cf2110262049e0d6964cfa8162c0bb59d503a6a89841bf4d783eac887dfb14190
+  metadata.gz: a0b9e987dd54239a0da817becc9755c42d0f375e89fc16ff7c9f442830b34379de98c89f3bad0d74286567c5cbaafdc6a97656f766f2e63da02ccd113004019e
+  data.tar.gz: 2347260e7dba1a6bb08c91cc2183b445d534b36e1296e6d3338076ed3729073276df516dbfa83bce87e18af4e51721df744fc694eee3a60a096f27d9ecf0f666

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.2.0

data/bin/divvy_spectra

@@ -15,7 +15,7 @@ require 'dta_select_output'
 options = {
   :logger => 'stderr',
   :log_level => 'info',
-  :contaminant_prefix => /^CNTM:/,
+  :contaminant_regexes => [/^CNTM:/],
 }
 o = OptionParser.new do |opts|
   opts.banner = "
@@ -29,6 +29,10 @@ o = OptionParser.new do |opts|
   opts.on("--whitelist FILE_OF_PROTEINS_TO_REPORT", "Only report proteins that are in this whitelist, after divvying with everything") do |file|
     options[:whitelist_file] = file
   end
+  opts.on("--contaminant-regexes REGEXES", "Comma-separated list of regular expressions to apply to protein names. If the protein name matches then all spectra assigned to that protein are considered contaminants. [default: #{options[:contaminant_prefixes]}]") do |str|
+    options[:contaminant_regexes] = str.split(/,/).collect{|s| /#{s}/}
+  end
+
 
   # logger options
   opts.separator "\nVerbosity:\n\n"
@@ -42,8 +46,7 @@ if ARGV.length > 1
 end
 # Setup logging
 Bio::Log::CLI.logger(options[:logger]); Bio::Log::CLI.trace(options[:log_level]); log = Bio::Log::LoggerPlus.new(LOG_NAME); Bio::Log::CLI.configure(LOG_NAME)
-
-
+#$stderr.puts options[:contaminant_prefixes].inspect
 
 # Read in merges, if required
 mergers = {}
@@ -130,12 +133,22 @@ mergers.each do |secondary_id, primary_id|
   end #The other two cases do not require any intervention,
 end
 
+id_is_contaminating = lambda do |protein_id|
+  selected = false
+  options[:contaminant_regexes].each do |regex|
+    if protein_id.match(regex)
+      selected = true
+    end
+  end
+  selected
+end
+
 
 # Total spectra shouldn't count contaminants, but shared spectra should still be divvied up with
 # Annoying thing here is when contaminating proteins share spectra
 total_contaminating_peptides = hits.collect do |ident, peptide|
   num_contaminating_parents = peptide.parent_proteins.select do |prot|
-    prot.identifier.match(options[:contaminant_prefix])
+    id_is_contaminating.call prot.identifier
   end.length
 
   if num_contaminating_parents > 0
@@ -145,7 +158,7 @@ total_contaminating_peptides = hits.collect do |ident, peptide|
   end
 end
 total_contaminating_spectra = total_contaminating_peptides.reduce :+
-total_contaminating_spectra ||= []
+total_contaminating_spectra ||= 0
 log.info "Found #{total_contaminating_spectra} contaminating spectral counts"
 
 total_spectra = hits.collect{|ident, pep| pep.redundancy}.reduce(:+) - total_contaminating_spectra
@@ -177,7 +190,7 @@ puts [
 ].join "\t"
 log.warn "No unique spectra found!" if total_spectra == 0
 proteins.each do |protein_id, protein|
-  next if protein_id.match(options[:contaminant_prefix]) #Don't print contaminants
+  next if id_is_contaminating.call(protein_id) #Don't print contaminants
 
   if options[:whitelist_file].nil? or whitelist.include?(protein_id) # If there's a whitelist, apply it now
     log.debug "Now printing protein #{protein_id}, which has #{protein.peptides.length} associated peptides"

data/divvy_proteomics.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "divvy_proteomics"
-  s.version = "0.1.0"
+  s.version = "0.2.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Ben J Woodcroft"]
-  s.date = "2013-11-05"
+  s.date = "2013-11-06"
   s.description = "divvy up spectra from DTASelect files in a somewhat parsimonious way"
   s.email = "donttrustben@gmail.com"
   s.executables = ["divvy_spectra"]
@@ -32,6 +32,7 @@ Gem::Specification.new do |s|
     "spec/data/merge_definition.csv",
     "spec/data/multiply_mapped_spectra.csv",
     "spec/data/new_format.csv",
+    "spec/data/new_format_some_all_shared_spectra.csv",
     "spec/data/single_protein.csv",
     "spec/data/single_protein_with_aliases.csv",
     "spec/data/three_proteins.csv",

data/spec/data/new_format_some_all_shared_spectra.csv

@@ -0,0 +1,45 @@
+DTASelect v1.9
+/auto/gtl/ms/Abisko_Soils/Field_Sampling_Aug_2010/SurfDeep/Erio_Deep_Aug2010_27Jun_TR1/Frac1/analysis/tryp_edeep_082010_500bp_Wheat/sequest
+/auto/gtl/db/Abisko_Soils/edeep_082010_500bp_Wheat_cntm_psm
+SEQUEST v.27 in SQT format.
+ --DB -p 2 -r 1000
+true	Use criteria
+1.8	Minimum +1 XCorr
+2.5	Minimum +2 XCorr
+3.5	Minimum +3 XCorr
+0.08	Minimum DeltCN
+1	Minimum charge state
+3	Maximum charge state
+0.0	Minimum ion proportion
+1000	Maximum Sp rank
+-1.0	Minimum Sp score
+Include	Modified peptide inclusion
+Any	Tryptic status requirement
+true	Multiple, ambiguous IDs allowed
+Ignore	Peptide validation handling
+XCorr	Purge duplicate peptides by protein
+false	Include only loci with unique peptide
+false	Remove subset proteins
+Ignore	Locus validation handling
+0	Minimum modified peptides per locus
+1000	Minimum redundancy for low coverage loci
+2	Minimum peptides per locus
+
+Locus	Sequence Count	Spectrum Count	Sequence Coverage	Length	MolWt	pI	Validation Status	Descriptive Name
+Unique	FileName	XCorr	DeltCN	Obs_mono_m/z	Calc_mono_m/z	PPM	Delta_amu	TotalIntensity	SpRank	SpScore	IonProportion	Redundancy	Sequence	
+E1D_raw_1__154435_1	3	41	79.3%	58	6132	7.3	U	# 3 # 176 # -1 # ID=154435_1;partial=10;start_type=ATG;rbs_motif=AGGAG;rbs_spacer=5-10bp 
+aliaese	3	41	79.3%	58	6132	7.3	U	# 3 # 176 # -1 # ID=154435_1;partial=10;start_type=ATG;rbs_motif=AGGAG;rbs_spacer=5-10bp 
+	20120806_Erio_Deep_Aug2010_27Jun_TR1_04.22361.22361.3	5.8526	0.4034	2772.4479	2772.4445	1.2211	0.0034	6048.2	1	1349.0	40.0	30	-.MLSIQTNIAALSAQNALTTTNNNLQK.S	
+	20120806_Erio_Deep_Aug2010_27Jun_TR1_10.22784.22784.3	4.5965	0.4101	3275.6674	3275.6608	2.0124	0.0066	5944.2	1	884.7	28.4	7	-.MLSIQTNIAALSAQNALTTTNNNLQKSMER.L	
+	20120806_Erio_Deep_Aug2010_27Jun_TR1_03.06010.06010.2	4.5641	0.462	1594.7954	1594.7956	-0.1435	-0.0002	4981.9	1	1347.9	76.7	4	R.INHAADDAAGLAISEK.M	
+E1D_raw_1__40591_2	3	8	74.5%	51	5250	8.6	U	# 705 # 857 # 1 # ID=40591_2;partial=01;start_type=ATG;rbs_motif=None;rbs_spacer=None 
+*	20120806_Erio_Deep_Aug2010_27Jun_TR1_01.18475.18475.2	4.3739	0.5173	2140.0658	2140.0653	0.2192	0.0005	7636.1	1	1642.9	65.0	1	K.TSDVAGDGTTTATILAQSIYR.E	
+*	20120806_Erio_Deep_Aug2010_27Jun_TR1_02.21883.21883.2	3.4843	0.1996	2553.2977	2553.2928	1.9293	0.0049	6903.6	1	903.4	47.9	3	K.TSDVAGDGTTTATILAQSIYREGVK.A	
+*	20120806_Erio_Deep_Aug2010_27Jun_TR1_08.06194.06194.2	2.7604	0.1784	1326.7055	1326.7083	-2.1145	-0.0028	6041.5	1	860.0	66.7	4	K.AVAAGANPMELKR.G	
+	Proteins	Peptide IDs	Copies
+Unfiltered	318515	400116	506301
+Redundant	1575	3555	18759
+Nonredundant	1211	2557	12384
+
+Classification	Nonredundant Proteins	Redundant Proteins
+Unclassified	0	0

data/spec/divvy_proteomics_spec.rb

@@ -88,6 +88,17 @@ describe script_under_test do
     stdout.should eq(answer), test_file
   end
 
+  it 'should handle arbitrary contaminant prefixes' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/single_protein_with_aliases.csv --trace error --contaminant-regexes alias"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['Mstor_v4.3.2:1344','0','188','0','NaN','Methanoflorens_stordalmirensis_v4.3.2_01361 Methyl-coenzyme M reductase I subunit gamma ','alias1'+"\n"].join("\t")
+    #['alias1','0','188','0','0.0','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}
@@ -115,4 +126,16 @@ describe script_under_test do
     ['E1D_raw_1__40591_2','8','0','8.0','0.12121212121212122','# 705 # 857 # 1 # ID=40591_2;partial=01;start_type=ATG;rbs_motif=None;rbs_spacer=None ',"\n"].join("\t")
     stdout.should eq(answer)
   end
+
+  it 'should include spectra shared between unresolvable proteins in calculations' do
+    test_file = "#{path_to_script} #{TEST_DATA_DIR}/new_format_some_all_shared_spectra.csv --trace error"
+    status, stdout, stderr = systemu test_file
+
+    stderr.should eq("")
+    answer = header+
+    ['E1D_raw_1__154435_1','0','41','0','0.0','# 3 # 176 # -1 # ID=154435_1;partial=10;start_type=ATG;rbs_motif=AGGAG;rbs_spacer=5-10bp ','aliaese'+"\n"].join("\t")+
+    ['aliaese','0','41','0','0.0','# 3 # 176 # -1 # ID=154435_1;partial=10;start_type=ATG;rbs_motif=AGGAG;rbs_spacer=5-10bp ','E1D_raw_1__154435_1'+"\n"].join("\t")+
+    ['E1D_raw_1__40591_2','8','0','8.0','0.16326530612244897','# 705 # 857 # 1 # ID=40591_2;partial=01;start_type=ATG;rbs_motif=None;rbs_spacer=None ',''+"\n"].join("\t")
+    stdout.should eq(answer)
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: divvy_proteomics
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Ben J Woodcroft
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-05 00:00:00.000000000 Z
+date: 2013-11-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-logger
@@ -117,6 +117,7 @@ files:
 - spec/data/merge_definition.csv
 - spec/data/multiply_mapped_spectra.csv
 - spec/data/new_format.csv
+- spec/data/new_format_some_all_shared_spectra.csv
 - spec/data/single_protein.csv
 - spec/data/single_protein_with_aliases.csv
 - spec/data/three_proteins.csv