bio 1.4.3.0001 → 1.5.0

data/extconf.rb

@@ -1,2 +0,0 @@
-require 'mkmf'
-create_makefile("bioruby")

data/lib/bio/appl/blast/ddbj.rb

@@ -1,131 +0,0 @@
-#
-# = bio/appl/blast/ddbj.rb - Remote BLAST wrapper using DDBJ web service
-# 
-# Copyright::  Copyright (C) 2008       Naohisa Goto <ng@bioruby.org>
-# License::    The Ruby License
-#
-
-require 'bio/io/ddbjrest'
-
-module Bio::Blast::Remote
-
-  # Remote BLAST factory using DDBJ Web API for Biology
-  # (http://xml.nig.ac.jp/).
-  #
-  module DDBJ
-
-    # Creates a remote BLAST factory using DDBJ.
-    # Returns Bio::Blast object.
-    #
-    # Note for future improvement: In the future, it might return
-    # Bio::Blast::Remote::DDBJ or other object. 
-    #
-    def self.new(program, db, options = [])
-      Bio::Blast.new(program, db, options, 'ddbj')
-    end
-
-    # Information about DDBJ BLAST.
-    module Information
-
-      include Bio::Blast::Remote::Information
-
-      # (private) parse database information
-      def _parse_databases
-        if defined? @parse_databases
-          return nil if @parse_databases
-        end
-        drv = Bio::DDBJ::REST::Blast.new
-        str = drv.getSupportDatabaseList
-
-        databases = {}
-        dbdescs = {}
-        keys = [ 'blastn', 'blastp' ]
-        keys.each do |key|
-          databases[key] ||= []
-          dbdescs[key] ||= {}
-        end
-        prefix = ''
-        prefix_count = 0
-        str.each_line do |line|
-          a = line.strip.split(/\s*\-\s*/, 2)
-          case a.size
-          when 1
-            prefix = a[0].to_s.strip
-            prefix += ': ' unless prefix.empty?
-            prefix_count = 0
-            next #each_line
-          when 0
-            prefix = '' if prefix_count > 0
-            next #each_line
-          end
-          name = a[0].to_s.strip.freeze
-          desc = a[1].to_s.strip
-          key = case desc
-                when /\(NT\)\s*$/
-                  'blastn'
-                when /\(AA\)\s*$/
-                  'blastp'
-                else
-                  warn "DDBJ BLAST: could not determine the database is NT or AA: #{line.chomp}" if $VERBOSE
-                  next #each_line
-                end
-          desc = (prefix + desc).freeze
-          prefix_count += 1
-          databases[key].push name
-          dbdescs[key][name] = desc
-        end
-
-        databases['blastp'] ||= []
-        dbdescs['blastp'] ||= []
-
-        databases['blastn'].freeze
-        databases['blastp'].freeze
-
-        databases['blastx']  = databases['blastp']
-        dbdescs['blastx']    = dbdescs['blastp']
-        databases['tblastn'] = databases['blastn']
-        dbdescs['tblastn']   = dbdescs['blastn']
-        databases['tblastx'] = databases['blastn']
-        dbdescs['tblastx']   = dbdescs['blastn']
-
-        @databases = databases
-        @database_descriptions = dbdescs
-        @parse_databases = true
-        true
-      end
-      private :_parse_databases
-
-    end #module Information
-
-    extend Information
-
-    # executes BLAST and returns result as a string
-    def exec_ddbj(query)
-      options = make_command_line_options
-      opt = Bio::Blast::NCBIOptions.new(options)
-
-      # REST objects are cached
-      @ddbj_remote_blast ||= Bio::DDBJ::REST::Blast.new
-      @ddbj_request_manager ||= Bio::DDBJ::REST::RequestManager.new
-
-      program = opt.delete('-p')
-      db = opt.delete('-d')
-      optstr = Bio::Command.make_command_line_unix(opt.options)
-
-      # using searchParamAsync 
-      qid = @ddbj_remote_blast.searchParamAsync(program, db, query, optstr)
-      @output = qid
-
-      result = @ddbj_request_manager.wait_getAsyncResult(qid)
-
-      @output = result
-      return @output
-    end
-
-  end #module DDBJ
-
-  # for lazy load DDBJ module
-  Ddbj = DDBJ
-
-end #module Bio::Blast::Remote
-

data/lib/bio/db/kegg/taxonomy.rb

@@ -1,280 +0,0 @@
-#
-# = bio/db/kegg/taxonomy.rb - KEGG taxonomy parser class
-#
-# Copyright::  Copyright (C) 2007 Toshiaki Katayama <k@bioruby.org>
-# License::    The Ruby License
-#
-#  $Id:$
-#
-
-module Bio
-class KEGG
-
-# == Description
-#
-# Parse the KEGG 'taxonomy' file which describes taxonomic classification
-# of organisms.
-#
-# == References
-#
-# The KEGG 'taxonomy' file is available at
-#
-# * ftp://ftp.genome.jp/pub/kegg/genes/taxonomy
-#
-class Taxonomy
-
-  def initialize(filename, orgs = [])
-    # Stores the taxonomic tree as a linked list (implemented in Hash), so
-    # every node need to have unique name (key) to work correctly
-    @tree = Hash.new
-
-    # Also stores the taxonomic tree as a list of arrays (full path)
-    @path = Array.new
-
-    # Also stores all leaf nodes (organism codes) of every intermediate nodes
-    @leaves = Hash.new
-
-    # tentative name for the root node (use accessor to change)
-    @root = 'Genes'
-
-    hier = Array.new
-    level = 0
-    label = nil
-
-    File.open(filename).each do |line|
-      next if line.strip.empty?
-
-      # line for taxonomic hierarchy (indent according to the number of # marks)
-      if line[/^#/]
-	level = line[/^#+/].length
-	label = line[/[A-z].*/]
-	hier[level] = sanitize(label)
-
-      # line for organims name (unify different strains of a species)
-      else
-	tax, org, name, desc = line.chomp.split("\t")
-        if orgs.nil? or orgs.empty? or orgs.include?(org)
-          species, strain, = name.split('_')
-          # (0) Grouping of the strains of the same species.
-          #  If the name of species is the same as the previous line,
-          #  add the species to the same species group.
-          #   ex. Gamma/enterobacteria has a large number of organisms,
-          #       so sub grouping of strains is needed for E.coli strains etc.
-          #
-          # However, if the species name is already used, need to avoid
-          # collision of species name as the current implementation stores
-          # the tree as a Hash, which may cause the infinite loop.
-          #
-          # (1) If species name == the intermediate node of other lineage
-          #  Add '_sp' to the species name to avoid the conflict (1-1), and if
-          #  'species_sp' is already taken, use 'species_strain' instead (1-2).
-          #   ex. Bacteria/Proteobacteria/Beta/T.denitrificans/tbd
-          #       Bacteria/Proteobacteria/Epsilon/T.denitrificans_ATCC33889/tdn
-          #    -> Bacteria/Proteobacteria/Beta/T.denitrificans/tbd
-          #       Bacteria/Proteobacteria/Epsilon/T.denitrificans_sp/tdn
-          #
-          # (2) If species name == the intermediate node of the same lineage
-          #  Add '_sp' to the species name to avoid the conflict.
-          #   ex. Bacteria/Cyanobacgteria/Cyanobacteria_CYA/cya
-          #       Bacteria/Cyanobacgteria/Cyanobacteria_CYB/cya
-          #       Bacteria/Proteobacteria/Magnetococcus/Magnetococcus_MC1/mgm
-          #    -> Bacteria/Cyanobacgteria/Cyanobacteria_sp/cya
-          #       Bacteria/Cyanobacgteria/Cyanobacteria_sp/cya
-          #       Bacteria/Proteobacteria/Magnetococcus/Magnetococcus_sp/mgm
-          sp_group = "#{species}_sp"
-          if @tree[species]
-            if hier[level+1] == species
-              # case (0)
-            else
-              # case (1-1)
-              species = sp_group
-              # case (1-2)
-              if @tree[sp_group] and hier[level+1] != species
-                species = name
-              end
-            end
-          else
-            if hier[level] == species
-              # case (2)
-              species = sp_group
-            end
-          end
-          # 'hier' is an array of the taxonomic tree + species and strain name.
-          #  ex. [nil, Eukaryotes, Fungi, Ascomycetes, Saccharomycetes] +
-          #      [S_cerevisiae, sce]
-          hier[level+1] = species	# sanitize(species)
-          hier[level+2] = org
-          ary = hier[1, level+2]
-          warn ary.inspect if $DEBUG
-          add_to_tree(ary)
-          add_to_leaves(ary)
-          add_to_path(ary)
-        end
-      end
-    end
-    return tree
-  end
-
-  attr_reader :tree
-  attr_reader :path
-  attr_reader :leaves
-  attr_accessor :root
-
-  def organisms(group)
-    @leaves[group]
-  end
-
-  # Add a new path [node, subnode, subsubnode, ..., leaf] under the root node
-  # and every intermediate nodes stores their child nodes as a Hash.
-  def add_to_tree(ary)
-    parent = @root
-    ary.each do |node|
-      @tree[parent] ||= Hash.new
-      @tree[parent][node] = nil
-      parent = node
-    end
-  end
-
-  # Add a new path [node, subnode, subsubnode, ..., leaf] under the root node
-  # and stores leaf nodes to the every intermediate nodes as an Array.
-  def add_to_leaves(ary)
-    leaf = ary.last
-    ary.each do |node|
-      @leaves[node] ||= Array.new
-      @leaves[node] << leaf
-    end
-  end
-
-  # Add a new path [node, subnode, subsubnode, ..., leaf] under the root node
-  # and stores the path itself in an Array.
-  def add_to_path(ary)
-    @path << ary
-  end
-
-  # Compaction of intermediate nodes of the resulted taxonomic tree.
-  #  - If child node has only one child node (grandchild), make the child of
-  #    grandchild as a grandchild.
-  #  ex.
-  #    Plants / Monocotyledons / grass family / osa
-  #    --> Plants / Monocotyledons / osa
-  #
-  def compact(node = root)
-    # if the node has children
-    if subnodes = @tree[node]
-      # obtain grandchildren for each child
-      subnodes.keys.each do |subnode|
-        if subsubnodes = @tree[subnode]
-          # if the number of grandchild node is 1
-          if subsubnodes.keys.size == 1
-            # obtain the name of the grandchild node
-            subsubnode = subsubnodes.keys.first
-            # obtain the child of the grandchlid node
-            if subsubsubnodes = @tree[subsubnode]
-              # make the child of grandchild node as a chlid of child node
-              @tree[subnode] = subsubsubnodes
-              # delete grandchild node
-              @tree[subnode].delete(subsubnode)
-              warn "--- compact: #{subsubnode} is replaced by #{subsubsubnodes}" if $DEBUG
-              # retry until new grandchild also needed to be compacted.
-              retry
-            end
-          end
-        end
-        # repeat recurseively
-        compact(subnode)
-      end
-    end
-  end
-
-  # Reduction of the leaf node of the resulted taxonomic tree.
-  #  - If the parent node have only one leaf node, replace parent node
-  #    with the leaf node.
-  #  ex.
-  #   Plants / Monocotyledons / osa
-  #   --> Plants / osa
-  #
-  def reduce(node = root)
-    # if the node has children
-    if subnodes = @tree[node]
-      # obtain grandchildren for each child
-      subnodes.keys.each do |subnode|
-        if subsubnodes = @tree[subnode]
-          # if the number of grandchild node is 1
-          if subsubnodes.keys.size == 1
-            # obtain the name of the grandchild node
-            subsubnode = subsubnodes.keys.first
-            # if the grandchild node is a leaf node
-            unless @tree[subsubnode]
-              # make the grandchild node as a child node
-              @tree[node].update(subsubnodes)
-              # delete child node
-              @tree[node].delete(subnode)
-              warn "--- reduce: #{subnode} is replaced by #{subsubnode}" if $DEBUG
-            end
-          end
-        end
-        # repeat recursively
-        reduce(subnode)
-      end
-    end
-  end
-
-  # Traverse the taxonomic tree by the depth first search method
-  # under the given (root or intermediate) node.
-  def dfs(parent, &block)
-    if children = @tree[parent]
-      yield parent, children
-      children.keys.each do |child|
-        dfs(child, &block)
-      end
-    end
-  end
-
-  # Similar to the dfs method but also passes the current level of the nest
-  # to the iterator.
-  def dfs_with_level(parent, &block)
-    @level ||= 0
-    if children = @tree[parent]
-      yield parent, children, @level
-      @level += 1
-      children.keys.each do |child|
-        dfs_with_level(child, &block)
-      end
-      @level -= 1
-    end
-  end
-
-  # Convert the taxonomic tree structure to a simple ascii art.
-  def to_s
-    result = "#{@root}\n"
-    @tree[@root].keys.each do |node|
-      result += ascii_tree(node, "  ")
-    end
-    return result
-  end
-
-  private
-
-  # Helper method for the to_s method.
-  def ascii_tree(node, indent)
-    result = "#{indent}+- #{node}\n"
-    indent += "  "
-    @tree[node].keys.each do |child|
-      if @tree[child]
-        result += ascii_tree(child, indent)
-      else
-        result += "#{indent}+- #{child}\n"
-      end
-    end
-    return result
-  end
-
-  def sanitize(str)
-    str.gsub(/[^A-z0-9]/, '_')
-  end
-
-end # Taxonomy
-
-end # KEGG
-end # Bio
-

data/lib/bio/io/dbget.rb

@@ -1,194 +0,0 @@
-#
-# = bio/io/dbget.rb - GenomeNet/DBGET client module
-#
-# Copyright::	Copyright (C) 2000, 2001
-#		Mitsuteru C. Nakao <n@bioruby.org>,
-#		Toshiaki Katayama <k@bioruby.org>
-# License::	The Ruby License
-#
-# $Id: dbget.rb,v 1.13 2007/04/05 23:35:41 trevor Exp $
-#
-# == DBGET
-#
-# Accessing the GenomeNet/DBGET data retrieval system
-# http://www.genome.jp/dbget/ within the intranet.
-#
-
-require 'socket'
-
-module Bio
-
-class DBGET
-
-  # default DBGET server address
-# SERV = "dbgetserv.genome.jp"
-  SERV = "dbget.genome.jp"
-  # default DBGET port number
-  PORT = "3266"
-
-  # Main class method to access DBGET server.  Optionally, this method
-  # can be called with the alternative DBGET server address and the
-  # TCP/IP port number.
-  #
-  # 'com' should be one of the following DBGET commands:
-  #
-  # * alink, bfind, bget, binfo, blink, bman, bref, btab, btit
-  #
-  # These methods are shortcut for the dbget commands.  Actually,
-  # Bio::DBGET.((|com|))(arg) internally calls Bio::DBGET.dbget(com, arg).
-  # Most of these methods accept the argument "-h" for help.
-  #
-  # 'arg' should be one of the following formats :
-  #
-  # * [options] db
-  #   * specify the database name only for binfo, bman etc.
-  # * [options] db:entry
-  #   * specify the database name and the entry name to retrieve.
-  # * [options] db entry1 entry2 ...
-  #   * specify the database name and the list of entries to retrieve.
-  #
-  # Note that options in the above example can be omitted.  If 'arg' is
-  # empty, the help message with a list of options for 'com' will be
-  # shown by default.  Supported database names will be found at the
-  # GenomeNet DBGET web page http://www.genome.jp/dbget/.
-  #
-  def DBGET.dbget(com, arg, serv = nil, port = nil)
-
-    unless serv or port		# if both of serv and port are nil
-      if ENV["DBGET"] =~ /:/		# and ENV["DBGET"] exists
-        serv, port = ENV["DBGET"].split(':')
-      end
-    end
-    serv = serv ? serv : SERV
-    port = port ? port : PORT
-
-    if arg.empty?
-      arg = "-h"			# DBGET help message
-    end
-
-    query = "#{com} #{arg}\n"		# DBGET query string
-
-    sock = TCPSocket.open("#{serv}", "#{port}")
-
-    sock.write(query)			# submit query
-    sock.flush			# buffer flush
-
-    sock.gets				# skip "+Helo DBgetServ ..."
-    sock.gets				# skip "#If you see this message, ..."
-    sock.gets				# skip "*Request-IDent"
-
-    result = sock.read		# DBGET result
-
-    sock.close
-
-    return result
-  end
-
-  # Show the version information of the DBGET server.
-  def DBGET.version
-    dbget("bget", "-V")
-  end
-
-
-  #--
-  # bacc("db entry")	- not supported : get accession(s)
-  # bent("db entry")	- not supported : get entry name
-  # lmarge("db entry")	- not supported
-  #++
-
-  # alink("db entry") method returns relations
-  def DBGET.alink(arg)
-    dbget("alink", arg)
-  end
-
-  # bfind("db keyword")	method searches entries by keyword
-  def DBGET.bfind(arg)
-    dbget("bfind", arg)
-  end
-
-  # bget("db entry") method retrieves entries specified by the entry names
-  def DBGET.bget(arg)
-    dbget("bget", arg)
-  end
-
-  # seq("db entry") method retrieves the first sequence of the entry
-  #
-  # Shortcut to retrieve the sequence of the entry in FASTA format.
-  # This method is equivalent to Bio::DBGET.bget("-f -n 1 #{arg}") and
-  # 'arg' should be the "db:entry" or "db entry1 entry2 ..." format.
-  def DBGET.seq(arg)
-    dbget("bget", "-f -n 1 #{arg}")
-  end
-
-  # seq2("db entry") method retrieves the second sequence of the entry if any
-  #
-  # Shortcut to retrieve the second sequence of the entry in FASTA format.
-  # This method is equivalent to Bio::DBGET.bget("-f -n 2 #{arg}").
-  # Only useful when treating the KEGG GENES database entries which have
-  # both AASEQ and NTSEQ fields. This method is obsolete and it is
-  # recommended to use 'naseq' and 'aaseq' instead.
-  def DBGET.seq2(arg)
-    dbget("bget", "-f -n 2 #{arg}")
-  end
-
-  # naseq("db entry") method retrieves the nucleic acid sequence of the
-  # entry if any.
-  def DBGET.naseq(arg)
-    dbget("bget", "-f -n n #{arg}")
-  end
-
-  # aaseq("db entry") method retrieves the amino acid sequence of the
-  # entry if any.
-  def DBGET.aaseq(arg)
-    dbget("bget", "-f -n a #{arg}")
-  end
-
-  # binfo("db")	method retrieves the database information
-  def DBGET.binfo(arg)
-    dbget("binfo", arg)
-  end
-
-  # blink("db entry") method retrieves the link information
-  def DBGET.blink(arg)
-    dbget("blink", arg)
-  end
-
-  # bman ("db entry") method shows the manual page
-  def DBGET.bman(arg)
-    dbget("bman", arg)
-  end
-
-  # bref("db entry") method retrieves the references and authors
-  def DBGET.bref(arg)
-    dbget("bref", arg)
-  end
-
-  # btab ("db entry") method retrives (and generates) the database alias table
-  def DBGET.btab(arg)
-    dbget("btab", arg)
-  end
-
-  # btit("db entry ..")	method retrieves the entry definition
-  def DBGET.btit(arg)
-    dbget("btit", arg)
-  end
-
-end
-
-end # module Bio
-
-
-if __FILE__ == $0
-  puts "### DBGET version"
-  p Bio::DBGET.version
-  puts "### DBGET.dbget('bfind', 'sce tyrosin kinase')"
-  puts Bio::DBGET.dbget('bfind', 'sce tyrosin kinase')
-  puts "### DBGET.bfind('sce tyrosin kinase')"
-  puts Bio::DBGET.bfind('sce tyrosin kinase')
-  puts "### DBGET.bget('sce:YDL028C')"
-  puts Bio::DBGET.bget('sce:YDL028C')
-  puts "### DBGET.binfo('dbget')"
-  puts Bio::DBGET.binfo('dbget')
-end
-
-