reubypathdb 0.3.0 → 0.3.1

data/VERSION

@@ -1 +1 @@
-0.3.0
+0.3.1

data/lib/eupathdb_fasta.rb

@@ -0,0 +1,70 @@
+
+
+module Bio
+  class EuPathDB
+    # Looks like EuPathDB databases have settled on something like
+    # >gb|TGME49_000380 | organism=Toxoplasma_gondii_ME49 | product=myb-like DNA binding domain-containing protein | location=TGME49_chrVIII:6835359-6840923(-) | length=1528
+    # where the species name differs but the rest is mostly constant
+    class FastaParser
+      attr_accessor :species_name
+      
+      # The species name is what should show up in the 2nd bracket, so something
+      # like 'Toxoplasma_gondii_ME49' for
+      # >gb|TGME49_000380 | organism=Toxoplasma_gondii_ME49 | product=myb-like DNA binding domain-containing protein | location=TGME49_chrVIII:6835359-6840923(-) | length=1528
+      # for instance
+      def initialize(species_name, filename)
+        @species_name = species_name
+        @filename = filename
+      end
+      
+      # Enumerate through fasta file entries
+      def each
+        @flat = Bio::FlatFile.open(Bio::FastaFormat, @filename)
+        n = next_entry
+        while !n.nil?
+          yield n
+          n = next_entry
+        end
+      end
+
+      # Return the entry in the fasta file, or nil if there is no more or the
+      # fasta file could not be opened correctly.
+      def next_entry
+        return nil if !@flat
+        n = @flat.next_entry
+        return nil if !n
+        
+        s = parse_name(n.definition)
+        s.sequence = n.seq
+        return s
+      end
+      
+      def parse_name(definition)
+        s = FastaAnnotation.new
+        
+        regex = /^(\S+)\|(.*?) \| organism=#{@species_name} \| product=(.*?) \| location=(.*) \| length=\d+$/
+        matches = definition.match(regex)
+        
+        if !matches
+          raise Exception, "Definition line has unexpected format: `#{definition}'. Trying to match this line to the regular expression `#{regex.inspect}'"
+        end
+        
+        matches2 = matches[4].match(/^(.+?)\:/)
+        if !matches2
+          raise ParseException, "Definition line has unexpected scaffold format: #{matches[4]}"
+        end
+        s.sequencing_centre = matches[1]
+        s.scaffold = matches2[1]
+        s.gene_id = matches[2]
+        s.annotation = matches[3]
+        return s
+      end
+    end
+    
+    class FastaAnnotation
+      attr_accessor :gene_id, :sequence, :annotation, :scaffold, :sequencing_centre
+    end
+    
+    class ParseException < Exception; end
+  end
+end

data/lib/eupathdb_species_data.rb

@@ -76,6 +76,7 @@ class EuPathDBSpeciesData
       :source => 'ToxoDB',
       :database_download_folder => 'EtenellaHoughton',
       :behind_usage_policy => true,
+      :fasta_file_species_name => 'Eimeria_tenella_str._Houghton',
     },
     'Toxoplasma gondii' => {
       :name => 'Toxoplasma gondii',
@@ -170,12 +171,12 @@ class EuPathDBSpeciesData
   end
   
   SOURCE_VERSIONS = {
-    'PlasmoDB' => '7.2',#
-    'ToxoDB' => '6.4',#'7.0',#
-    'CryptoDB' => '4.4',#'4.5',#
-    'PiroplasmaDB' => '1.0',#'1.1',#
+    'PlasmoDB' => '8.2',
+    'ToxoDB' => '7.2',
+    'CryptoDB' => '4.6',
+    'PiroplasmaDB' => '1.1',
     'FungiDB' => '1.0',
-    'TriTrypDB' => '3.2',
+    'TriTrypDB' => '4.0',
   }
   DATABASES = SOURCE_VERSIONS.keys
   
@@ -186,7 +187,7 @@ class EuPathDBSpeciesData
   #
   # base_data_directory is the directory where locally cached version of the downloaded
   # files are stored.
-  def initialize(nickname, base_data_directory=nil)
+  def initialize(nickname, base_data_directory=nil, database_version=nil)
     @species_data = @@data[nickname] # try the full name
     @species_data ||= @@data[nickname.capitalize.gsub('_',' ')] #try replacing underscores
     if @species_data.nil? # try using just the second word
@@ -195,10 +196,13 @@ class EuPathDBSpeciesData
         @species_data = @@data[splits[1]]
       end
     end
+    raise Exception, "Couldn't find species data for #{nickname}" unless @species_data
     
     @base_data_directory = base_data_directory
     
-    raise Exception, "Couldn't find species data for #{nickname}" unless @species_data
+    # record out what version of the db we are looking at, otherwise default
+    @database_version = database_version
+    @database_version ||= SOURCE_VERSIONS[@species_data[:source]]
   end
   
   def method_missing(symbol)
@@ -237,7 +241,7 @@ class EuPathDBSpeciesData
   end
   
   def version
-    SOURCE_VERSIONS[@species_data[:source]]
+    @database_version
   end
   
   def protein_fasta_filename
@@ -294,13 +298,7 @@ class EuPathDBSpeciesData
   end
   
   def eu_path_db_download_directory
-    directories = {}
-    SOURCE_VERSIONS.each do |db, version|
-      # 'PlasmoDB' => "http://plasmodb.org/common/downloads/release-#{SOURCE_VERSIONS['PlasmoDB']}",
-      directories[db] = "http://#{db.downcase}.org/common/downloads/release-#{version}"
-    end
-    raise Exception, "Base URL for database '#{database}' not known" if directories[database].nil?
-    return "#{directories[database]}/#{one_word_name}"
+    "http://#{database.downcase}.org/common/downloads/release-#{@database_version}/#{one_word_name}"
   end
   
   def eu_path_db_fasta_download_directory
@@ -331,7 +329,7 @@ class EuPathDBSpeciesData
   
   def local_download_directory
     s = @species_data
-    "#{@base_data_directory}/#{s[:name]}/genome/#{s[:source]}/#{SOURCE_VERSIONS[s[:source]]}"
+    "#{@base_data_directory}/#{s[:name]}/genome/#{s[:source]}/#{@database_version}"
   end
   
   # an array of directory names. mkdir is called on each of them in order,
@@ -348,7 +346,7 @@ class EuPathDBSpeciesData
     s[:name],
       'genome',
     s[:source],
-    SOURCE_VERSIONS[s[:source]]
+    @database_version,
     ]
     
      (0..components.length-1).collect do |i|
@@ -359,7 +357,8 @@ class EuPathDBSpeciesData
   # Return a list of the species names that are included in the EuPathDB database
   def self.species_data_from_database(database_name, base_download_directory=nil)
     species = @@data.select {|name, info|
-    info[:source].downcase == database_name.downcase
+      info[:source].downcase == database_name.downcase and
+      name == info[:name] #only allow ones that are fully specified - not shortcut ones
     }
     species.collect do |name_info|
       EuPathDBSpeciesData.new(name_info[0], base_download_directory)
@@ -410,4 +409,8 @@ class EuPathDBSpeciesData
       end
     end
   end
+  
+  def protein_fasta_file_iterator
+    Bio::EuPathDB::FastaParser.new(fasta_file_species_name, protein_fasta_path)
+  end
 end

data/lib/reubypathdb.rb

@@ -1,3 +1,4 @@
 require 'eupathdb_gene_information_table'
 require 'eupathdb_gff'
 require 'eupathdb_species_data'
+require 'eupathdb_fasta'

data/reubypathdb.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{reubypathdb}
-  s.version = "0.3.0"
+  s.version = "0.3.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["Ben J Woodcroft"]
-  s.date = %q{2011-08-26}
+  s.authors = [%q{Ben J Woodcroft}]
+  s.date = %q{2012-01-14}
   s.description = %q{Classes to help parsing EuPathDB data files}
   s.email = %q{donttrustben near gmail.com}
   s.extra_rdoc_files = [
@@ -19,11 +19,11 @@ Gem::Specification.new do |s|
   s.files = [
     ".document",
     "Gemfile",
-    "Gemfile.lock",
     "LICENSE",
     "README.rdoc",
     "Rakefile",
     "VERSION",
+    "lib/eupathdb_fasta.rb",
     "lib/eupathdb_gene_information_table.rb",
     "lib/eupathdb_gff.rb",
     "lib/eupathdb_species_data.rb",
@@ -36,9 +36,9 @@ Gem::Specification.new do |s|
     "test/test_eupathdb_species_data.rb"
   ]
   s.homepage = %q{http://github.com/wwood/reubypathdb}
-  s.licenses = ["MIT"]
-  s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.6.1}
+  s.licenses = [%q{MIT}]
+  s.require_paths = [%q{lib}]
+  s.rubygems_version = %q{1.8.6}
   s.summary = %q{Classes to help parsing EuPathDB data files}
 
   if s.respond_to? :specification_version then

data/test/test_eupathdb_species_data.rb

@@ -97,17 +97,32 @@ class EuPathDBSpeciesDataTest < Test::Unit::TestCase
     spd = EuPathDBSpeciesData.new('Plasmodium chabaudi')
     assert_equal "http://plasmodb.org/common/downloads/release-#{EuPathDBSpeciesData::SOURCE_VERSIONS['PlasmoDB']}/Pchabaudi/fasta/data",
     spd.eu_path_db_fasta_download_directory
- end
+  end
  
- def test_behind_usage_policy
+  def test_behind_usage_policy
     spd = EuPathDBSpeciesData.new('Plasmodium vivax')
     assert_equal "http://plasmodb.org/common/downloads/release-#{EuPathDBSpeciesData::SOURCE_VERSIONS['PlasmoDB']}/Pvivax/fasta",
     spd.eu_path_db_fasta_download_directory
- end
+  end
  
- def test_representative_strain_name
-   spd = EuPathDBSpeciesData.new('Trypanosoma brucei')
-   assert_equal "http://tritrypdb.org/common/downloads/release-#{EuPathDBSpeciesData::SOURCE_VERSIONS['TriTrypDB']}/Tbrucei/fasta/TbruceiTreu927Genomic_TriTrypDB-#{EuPathDBSpeciesData::SOURCE_VERSIONS['TriTrypDB']}.fasta",
+  def test_representative_strain_name
+    spd = EuPathDBSpeciesData.new('Trypanosoma brucei')
+    assert_equal "http://tritrypdb.org/common/downloads/release-#{EuPathDBSpeciesData::SOURCE_VERSIONS['TriTrypDB']}/Tbrucei/fasta/TbruceiTreu927Genomic_TriTrypDB-#{EuPathDBSpeciesData::SOURCE_VERSIONS['TriTrypDB']}.fasta",
     "#{spd.eu_path_db_fasta_download_directory}/#{spd.genomic_fasta_filename}"
- end
+  end
+ 
+  def test_non_default_db_version_of_protein_fasta
+    spd = EuPathDBSpeciesData.new('Plasmodium yoelii', base_dir,'100.9')
+    assert_equal "/home/ben/phd/data/Plasmodium yoelii/genome/PlasmoDB/100.9/PyoeliiAnnotatedProteins_PlasmoDB-100.9.fasta",
+    spd.protein_fasta_path
+  end
+  
+  def test_species_data_from_database
+    plasmos = EuPathDBSpeciesData.species_data_from_database('PlasmoDB')
+    # make sure there is only 1 of each species being produced - there was a bug about that multiple species were being generated at one point
+    bergs = plasmos.select{|s| 
+      EuPathDBSpeciesData.new(s.name).name == 'Plasmodium berghei'
+    }
+    assert_equal ['Plasmodium berghei'], bergs.collect{|d| d.name}
+  end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: reubypathdb
 version: !ruby/object:Gem::Version 
-  hash: 19
+  hash: 17
   prerelease: 
   segments: 
   - 0
   - 3
-  - 0
-  version: 0.3.0
+  - 1
+  version: 0.3.1
 platform: ruby
 authors: 
 - Ben J Woodcroft
@@ -15,8 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-08-26 00:00:00 +10:00
-default_executable: 
+date: 2012-01-14 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   type: :development
@@ -90,11 +89,11 @@ extra_rdoc_files:
 files: 
 - .document
 - Gemfile
-- Gemfile.lock
 - LICENSE
 - README.rdoc
 - Rakefile
 - VERSION
+- lib/eupathdb_fasta.rb
 - lib/eupathdb_gene_information_table.rb
 - lib/eupathdb_gff.rb
 - lib/eupathdb_species_data.rb
@@ -105,7 +104,6 @@ files:
 - test/helper.rb
 - test/test_eupathdb_gene_information_table.rb
 - test/test_eupathdb_species_data.rb
-has_rdoc: true
 homepage: http://github.com/wwood/reubypathdb
 licenses: 
 - MIT
@@ -135,7 +133,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.6.1
+rubygems_version: 1.8.6
 signing_key: 
 specification_version: 3
 summary: Classes to help parsing EuPathDB data files

data/Gemfile.lock

@@ -1,20 +0,0 @@
-GEM
-  remote: http://rubygems.org/
-  specs:
-    git (1.2.5)
-    jeweler (1.6.4)
-      bundler (~> 1.0)
-      git (>= 1.2.5)
-      rake
-    rake (0.9.2)
-    rcov (0.9.10)
-    shoulda (2.11.3)
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  bundler (~> 1.0.0)
-  jeweler (~> 1.6.4)
-  rcov
-  shoulda