protk 1.3.0 → 1.3.1.pre2

data/lib/protk/protein_to_genome_mapper.rb

@@ -0,0 +1,8 @@
+
+module ProteinToGenomeMapper
+
+	# gene_seq should already have been reverse_complemented if on reverse strand
+
+
+
+end

data/lib/protk/protxml_to_gff_tool.rb

@@ -10,6 +10,8 @@ class ProtXMLToGFFTool < Tool
 
 		add_value_option(:database,nil,['-d filename','--database filename','Database used for ms/ms searches (Fasta Format)'])
 		add_value_option(:genome,nil,['-g filename','--genome filename', 'Nucleotide sequences for scaffolds (Fasta Format)'])
+		add_value_option(:coords_file,nil,['-c filename','--coords-file filename.gff3', 'If genomic coordinates are not encoded in protein db entries look them up from a supplied gff file'])
+		# add_value_option(:contig_regex,nil,['--contig-regex expression','Regular expression with a single capture group to get contig ids from protein ids'])
 		add_value_option(:protein_find,nil,['-f term','--find term', 'Restrict output to proteins whose name matches the specified string'])
 		add_value_option(:nterm_minlen,7,['-n len','--nterm-min-len len', 'Only include inferred N-terminal sequences if longer than len'])
 		add_boolean_option(:skip_fasta_indexing,false,['--skip-index','Don\'t index database (Index should already exist)'])
@@ -317,7 +319,7 @@ class ProtXMLToGFFTool < Tool
 
 	  check_seq = protein_info.strand=='-' ? concat_seq.reverse_complement.translate : concat_seq.translate
 	  if ( check_seq != peptide_seq)
-	    require 'debugger';debugger
+	    # require 'debugger';debugger
 	    puts "Fragment seqs not equal to peptide seqs"
 	  end
 

data/lib/protk/search_tool.rb

@@ -13,15 +13,6 @@ require 'optparse'
 require 'pathname'
 require 'protk/tool'
 
-class FastaDatabase
-  attr :name
-  attr :path
-  def initialize(name,path)
-    @name=name
-    @path=path
-  end
-end
-
 class SearchTool < Tool
 
   # Initializes commandline options common to all search tools.
@@ -30,9 +21,9 @@ class SearchTool < Tool
   def initialize(option_support=[])
     super(option_support)
 
-    if (option_support.include? :database)
-      add_value_option(:database,"sphuman",['-d', '--database dbname', 'Specify the database to use for this search. Can be a named protk database or the path to a fasta file'])        
-    end
+    # if (option_support.include? :database)
+    #   add_value_option(:database,"sphuman",['-d', '--database dbname', 'Specify the database to use for this search. Can be a named protk database or the path to a fasta file'])        
+    # end
     
     if ( option_support.include? :enzyme )
       add_value_option(:enzyme,"Trypsin",['--enzyme enz', 'Enzyme'])
@@ -115,18 +106,6 @@ class SearchTool < Tool
   end
       
 
-  def database_info
-    case
-      when Pathname.new(@options.database).exist? # It's an explicitly named db  
-        db_path=Pathname.new(@options.database).expand_path.to_s
-        db_name=Pathname.new(@options.database).basename.to_s
-      else
-        db_path=Constants.new.current_database_for_name @options.database
-        db_name=@options.database
-    end
-    FastaDatabase.new(db_name,db_path)
-  end
-
 end
 
 

data/lib/protk/swissprot_database.rb

@@ -7,27 +7,18 @@ require 'pathname'
 #
 class SwissprotDatabase 
   
-  def initialize(env=nil,database="swissprot")
-    if ( env!=nil)
-      @genv=env
-    else
-      @genv=Constants.new
-    end
+  def initialize(datfile_path,skip_indexing=false)
 
+    dbpath=Pathname.new(datfile_path)
+    dbclass=Bio::SPTR
 
-    dbpath=Pathname.new(database)
-
-    if ( dbpath.exist? )
-#      require 'debugger';debugger
-      dbclass=Bio::SPTR
+    unless skip_indexing
       parser = Bio::FlatFileIndex::Indexer::Parser.new(dbclass, nil, nil)
-      Bio::FlatFileIndex::Indexer::makeindexFlat(dbpath.realpath.dirname.to_s, parser, {}, dbpath.realpath.to_s)
-      @db_object=Bio::FlatFileIndex.new("#{dbpath.realpath.dirname.to_s}")
-    elsif ( database=="swissprot")
-      @db_object=Bio::FlatFileIndex.new("#{@genv.protein_database_root}/#{@genv.uniprot_sprot_annotation_database}")
-    else
-      @db_object=Bio::FlatFileIndex.new("#{@genv.protein_database_root}/#{@genv.uniprot_trembl_annotation_database}")
+      Bio::FlatFileIndex::Indexer::makeindexFlat(dbpath.realpath.dirname.to_s, parser, {}, \
+        dbpath.realpath.to_s)
     end
+      
+    @db_object=Bio::FlatFileIndex.new("#{dbpath.realpath.dirname.to_s}")
     
     @db_object.always_check_consistency=false
   end
@@ -36,9 +27,6 @@ class SwissprotDatabase
   def get_entry_for_name(name)
     result=@db_object.get_by_id(name)
     if result==""
-      if ( @genv!=nil)
-        @genv.log("Failed to find UniProt entry for protein named #{name} in database",:warn)
-      end
       return nil
     else
       Bio::SPTR.new(result)

data/lib/protk/tool.rb

@@ -10,6 +10,17 @@ require 'optparse'
 require 'pathname'
 require 'protk/command_runner'
 
+
+class FastaDatabase
+  attr :name
+  attr :path
+  def initialize(name,path)
+    @name=name
+    @path=path
+  end
+end
+
+
 class Tool
 
   # Options set from the command-line
@@ -108,7 +119,13 @@ class Tool
       add_value_option(:threads,1,['-n','--threads num','Number of processing threads to use. Set to 0 to autodetect an appropriate value'])
     end
 
+    if ( option_support.include? :database)
+      add_value_option(:database,"sphuman",['-d', '--database dbname', 'Specify the database to use for this search. Can be a named protk database or the path to a fasta file'])        
+    end
 
+    if (option_support.include? :debug)
+      add_boolean_option(:debug,false,['--debug','Run in debug mode'])
+    end
 
   end
 
@@ -147,6 +164,10 @@ class Tool
     # Checking for required options
     begin
       self.option_parser.parse!
+
+      if has_override
+        return true
+      end
       missing = mandatory.select{ |param| self.send(param).nil? }
       if not missing.empty?                                            
         puts "Missing options: #{missing.join(', ')}"                  
@@ -175,5 +196,19 @@ class Tool
     cmd_runner.run_local(cmd)
    end
    
-  
+
+   def database_info
+     case
+       when Pathname.new(@options.database).exist? # It's an explicitly named db  
+         db_path=Pathname.new(@options.database).expand_path.to_s
+         db_name=Pathname.new(@options.database).basename.to_s
+       else
+         db_path=Constants.new.current_database_for_name @options.database
+         db_name=@options.database
+     end
+     FastaDatabase.new(db_name,db_path)
+   end
+
+
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.3.1.pre2
 platform: ruby
 authors:
 - Ira Cooke
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-24 00:00:00.000000000 Z
+date: 2014-10-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: open4
@@ -152,6 +152,26 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: debugger
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.6.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.6.0
 - !ruby/object:Gem::Dependency
   name: sqlite3
   requirement: !ruby/object:Gem::Requirement
@@ -190,11 +210,44 @@ executables:
 - augustus_to_proteindb.rb
 - protxml_to_gff.rb
 - protxml_to_table.rb
+- swissprot_to_table.rb
+- protxml_to_psql.rb
 extensions:
 - ext/decoymaker/extconf.rb
 extra_rdoc_files: []
 files:
-- README.md
+- lib/protk/bio_gff3_extensions.rb
+- lib/protk/bio_sptr_extensions.rb
+- lib/protk/command_runner.rb
+- lib/protk/constants.rb
+- lib/protk/convert_util.rb
+- lib/protk/data/make_uniprot_table.rb
+- lib/protk/fastadb.rb
+- lib/protk/galaxy_stager.rb
+- lib/protk/galaxy_util.rb
+- lib/protk/gffdb.rb
+- lib/protk/manage_db_tool.rb
+- lib/protk/mascot_util.rb
+- lib/protk/mzml_parser.rb
+- lib/protk/omssa_util.rb
+- lib/protk/openms_defaults.rb
+- lib/protk/peptide.rb
+- lib/protk/pepxml.rb
+- lib/protk/plasmodb.rb
+- lib/protk/prophet_tool.rb
+- lib/protk/protein.rb
+- lib/protk/protein_to_genome_mapper.rb
+- lib/protk/protxml_to_gff_tool.rb
+- lib/protk/randomize.rb
+- lib/protk/search_tool.rb
+- lib/protk/setup_tool.rb
+- lib/protk/swissprot_database.rb
+- lib/protk/tandem_search_tool.rb
+- lib/protk/tool.rb
+- lib/protk/uniprot_mapper.rb
+- lib/protk.rb
+- lib/protk/manage_db_rakefile.rake
+- lib/protk/setup_rakefile.rake
 - bin/add_retention_times.rb
 - bin/augustus_to_proteindb.rb
 - bin/interprophet.rb
@@ -213,25 +266,19 @@ files:
 - bin/protxml_to_table.rb
 - bin/repair_run_summary.rb
 - bin/sixframe.rb
+- bin/swissprot_to_table.rb
 - bin/tandem_search.rb
 - bin/tandem_to_pepxml.rb
 - bin/unimod_to_loc.rb
 - bin/uniprot_mapper.rb
-- ext/decoymaker/decoymaker.c
-- ext/decoymaker/extconf.rb
-- lib/protk.rb
-- lib/protk/bio_sptr_extensions.rb
-- lib/protk/command_runner.rb
-- lib/protk/constants.rb
-- lib/protk/convert_util.rb
-- lib/protk/data/ExecutePipeline.trf
-- lib/protk/data/FeatureFinderCentroided.ini
-- lib/protk/data/FeatureFinderIsotopeWavelet.ini
+- README.md
 - lib/protk/data/apt-get_packages.yaml
 - lib/protk/data/brew_packages.yaml
 - lib/protk/data/default_config.yml
+- lib/protk/data/ExecutePipeline.trf
+- lib/protk/data/FeatureFinderCentroided.ini
+- lib/protk/data/FeatureFinderIsotopeWavelet.ini
 - lib/protk/data/galaxyenv.sh
-- lib/protk/data/make_uniprot_table.rb
 - lib/protk/data/predefined_db.crap.yaml
 - lib/protk/data/predefined_db.sphuman.yaml
 - lib/protk/data/predefined_db.swissprot_annotation.yaml
@@ -246,30 +293,11 @@ files:
 - lib/protk/data/uniprot_accessions_table.txt
 - lib/protk/data/uniprot_input_accessions.loc
 - lib/protk/data/yum_packages.yaml
-- lib/protk/fastadb.rb
-- lib/protk/galaxy_stager.rb
-- lib/protk/galaxy_util.rb
-- lib/protk/manage_db_rakefile.rake
-- lib/protk/manage_db_tool.rb
-- lib/protk/mascot_util.rb
-- lib/protk/mzml_parser.rb
-- lib/protk/omssa_util.rb
-- lib/protk/openms_defaults.rb
-- lib/protk/pepxml.rb
-- lib/protk/plasmodb.rb
-- lib/protk/prophet_tool.rb
-- lib/protk/protxml.rb
-- lib/protk/protxml_to_gff_tool.rb
-- lib/protk/randomize.rb
-- lib/protk/search_tool.rb
-- lib/protk/setup_rakefile.rake
-- lib/protk/setup_tool.rb
-- lib/protk/swissprot_database.rb
-- lib/protk/tandem_search_tool.rb
-- lib/protk/tool.rb
-- lib/protk/uniprot_mapper.rb
+- ext/decoymaker/decoymaker.c
+- ext/decoymaker/extconf.rb
 homepage: http://rubygems.org/gems/protk
-licenses: []
+licenses:
+- LGPL-2.1
 metadata: {}
 post_install_message: Now run protk_setup.rb to install third party tools
 rdoc_options: []
@@ -282,14 +310,13 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - '>'
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.1
+rubygems_version: 2.0.14
 signing_key: 
 specification_version: 4
 summary: Proteomics Toolkit
 test_files: []
-has_rdoc: 

data/lib/protk/protxml.rb

@@ -1,141 +0,0 @@
-require 'rubygems'
-require 'rexml/document'
-require 'rexml/xpath'
-
-class ProtXML 
-    
-  attr_accessor :groups
-    
-    
-  def indistinguishable_proteins_from_protein(protein_element)
-    iprots=[]
-    REXML::XPath.each(protein_element,"./indistinguishable_protein") do |ipel|
-      ipel_attributes={}
-      ipel.attributes.each_attribute { |att| ipel_attributes[att.expanded_name.to_sym]=att.value }
-      iprots.push(ipel_attributes[:protein_name])
-    end    
-    iprots
-  end
-
-  def peptides_from_protein(protein_element)
-    peptides=[]
-    REXML::XPath.each(protein_element,"./peptide") do |pel|
-      peptide={}
-
-      pel.attributes.each_attribute { |att| peptide[att.expanded_name.to_sym]=att.value }
-      modifications=pel.get_elements("./modification_info")
-      mods=modifications.collect {|mp| mp.attribute("modified_peptide").value }
-      peptide[:modifications] = mods
-      peptides.push(peptide)
-    end
-    peptides
-  end
-    
-  def proteins_from_group(group_element)
-    proteins=[]
-    REXML::XPath.each(group_element,"./protein") do |pel|
-      protein={}
-      pel.attributes.each_attribute { |att| protein[att.expanded_name.to_sym]=att.value }
-      protein[:peptides]=peptides_from_protein(pel)      
-      protein[:indistinguishable_prots]=indistinguishable_proteins_from_protein(pel)
-      proteins.push(protein)
-    end
-    proteins
-  end
-    
-  def init_groups
-    @groups=[]
-    REXML::XPath.each(@doc.root,"//protein_group") do |gel|
-      group={}
-      group[:group_probability]=gel.attributes["probability"].to_f
-      group[:proteins]=proteins_from_group(gel)
-      groups.push group
-    end
-    @groups
-  end
-
-
-  def initialize(file_name)
-    @doc=REXML::Document.new(File.new(file_name))
-    @groups=self.init_groups
-  end
-
-  def find_pep_xml()
-    header = REXML::XPath.first(@doc, "//protein_summary_header")
-    source_file = header.attributes["source_files"]
-  end
-  
-  def peptide_sequences_from_protein(prot)
-    peptides=prot[:peptides]
-    sequences=[]
-    peptides.each do |pep| 
-      if ( pep[:modifications].length > 0 )
-        pep[:modifications].each {|pmod| 
-          sequences.push(pmod) }
-      else
-        sequences.push(pep[:peptide_sequence])
-      end
-    end
-    sequences
-  end
-  
-  def protein_to_row(prot)
-    protein_row=[]
-    protein_row.push(prot[:protein_name])
-    protein_row.push(prot[:probability])
-    
-    indistinct=prot[:indistinguishable_prots]
-    indist_string="#{prot[:protein_name]};"
-    indistinct.each { |pr| indist_string<<"#{pr};"}
-    indist_string.chop!
-    protein_row.push(indist_string)
-    
-    protein_row.push(prot[:peptides].length)
-    
-    peptide_string=""
-    peptide_sequences_from_protein(prot).each {|pep| peptide_string<<"#{pep};" }
-    peptide_string.chop!
-    
-    protein_row.push(peptide_string)
-    protein_row
-  end
-  
-  # Convert the entire prot.xml document to row format
-  # Returns an array of arrays. Each of the sub-arrays is a row.
-  # Each row should contain a simple summary of the protein.
-  # A separate row should be provided for every protein (including indistinguishable ones)
-  # The first row will be the header
-  # 
-  # Proteins with probabilities below a threshold are excluded
-  #
-  def as_rows(threshold_probability)
-    
-    rows=[]
-    rows.push(["Accession","Probability","Indistinguishable Proteins","Num Peptides","Peptides"])
-    
-    proteins=[]
-    @groups.each do |grp|
-      grp[:proteins].each {|prot| 
-        if ( prot[:probability].to_f >= threshold_probability)
-          proteins.push(prot)
-        end
-      }
-    end
-    
-    proteins.each do |prot|
-      protein_row=protein_to_row(prot)
-      rows.push(protein_row)
-      
-      indistinguishables=prot[:indistinguishable_prots]
-      indistinguishables.each do |indist|
-        indist_row=protein_row.clone
-        indist_row[0]=indist
-        rows.push(indist_row)
-      end
-      
-    end
-    
-    rows
-  end
-  
-end