wwood-bioruby 1.2.11

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

@@ -0,0 +1,41 @@
+#
+# = bio/db/kegg/brite.rb - KEGG/BRITE database class
+#
+# Copyright::  Copyright (C) 2001 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: brite.rb,v 0.8 2007/04/05 23:35:41 trevor Exp $
+#
+
+require 'bio/db'
+
+module Bio
+class KEGG
+
+# == Note
+#
+# This class is not completely implemented, but obsolete as the original
+# database BRITE has changed it's meaning.
+#
+class BRITE < KEGGDB
+
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
+
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # ENTRY
+  # DEFINITION
+  # RELATION
+  # FACTORS
+  # INTERACTION
+  # SOURCE
+  # REFERENCE
+
+end # BRITE
+
+end # KEGG
+end # Bio
+

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

@@ -0,0 +1,131 @@
+#
+# = bio/db/kegg/compound.rb - KEGG COMPOUND database class
+#
+# Copyright::  Copyright (C) 2001, 2002, 2004, 2007 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: compound.rb,v 0.17 2007/11/27 07:09:43 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+class KEGG
+
+class COMPOUND < KEGGDB
+
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
+
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # ENTRY
+  def entry_id
+    field_fetch('ENTRY')[/\S+/]
+  end
+
+  # NAME
+  def names
+    field_fetch('NAME').split(/\s*;\s*/)
+  end
+
+  def name
+    names.first
+  end
+
+  # FORMULA
+  def formula
+    field_fetch('FORMULA')
+  end
+
+  # MASS
+  def mass
+    field_fetch('MASS').to_f
+  end
+
+  # REMARK
+  def remark
+    field_fetch('REMARK')
+  end
+
+  # GLYCAN
+  def glycans
+    unless @data['GLYCAN']
+      @data['GLYCAN'] = fetch('GLYCAN').split(/\s+/)
+    end
+    @data['GLYCAN']
+  end
+
+  # REACTION
+  def reactions
+    unless @data['REACTION']
+      @data['REACTION'] = fetch('REACTION').split(/\s+/)
+    end
+    @data['REACTION']
+  end
+
+  # RPAIR
+  def rpairs
+    unless @data['RPAIR']
+      @data['RPAIR'] = fetch('RPAIR').split(/\s+/)
+    end
+    @data['RPAIR']
+  end
+
+  # PATHWAY
+  def pathways
+    lines_fetch('PATHWAY') 
+  end
+
+  # ENZYME
+  def enzymes
+    unless @data['ENZYME']
+      field = fetch('ENZYME')
+      if /\(/.match(field)	# old version
+        @data['ENZYME'] = field.scan(/\S+ \(\S+\)/)
+      else
+        @data['ENZYME'] = field.scan(/\S+/)
+      end
+    end
+    @data['ENZYME']
+  end
+
+  # DBLINKS
+  def dblinks
+    lines_fetch('DBLINKS')
+  end
+
+  # ATOM, BOND
+  def kcf
+    return "#{get('ATOM')}#{get('BOND')}"
+  end
+
+  # COMMENT
+  def comment
+    field_fetch('COMMENT')
+  end
+
+end # COMPOUND
+
+end # KEGG
+end # Bio
+
+
+if __FILE__ == $0
+  entry = ARGF.read
+  cpd = Bio::KEGG::COMPOUND.new(entry)
+  p cpd.entry_id
+  p cpd.names
+  p cpd.name
+  p cpd.formula
+  p cpd.mass
+  p cpd.reactions
+  p cpd.rpairs
+  p cpd.pathways
+  p cpd.enzymes
+  p cpd.dblinks
+  p cpd.kcf
+end
+

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

@@ -0,0 +1,98 @@
+#
+# = bio/db/kegg/drug.rb - KEGG DRUG database class
+#
+# Copyright::  Copyright (C) 2007 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: drug.rb,v 1.3 2007/06/28 11:27:24 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+class KEGG
+
+class DRUG < KEGGDB
+
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
+
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # ENTRY
+  def entry_id
+    field_fetch('ENTRY')[/\S+/]
+  end
+
+  # NAME
+  def names
+    field_fetch('NAME').split(/\s*;\s*/)
+  end
+
+  def name
+    names.first
+  end
+
+  # FORMULA
+  def formula
+    field_fetch('FORMULA')
+  end
+
+  # MASS
+  def mass
+    field_fetch('MASS').to_f
+  end
+
+  # ACTIVITY
+  def activity
+    field_fetch('ACTIVITY')
+  end
+
+  # REMARK
+  def remark
+    field_fetch('REMARK')
+  end
+
+  # COMMENT
+  def comment
+    field_fetch('COMMENT')
+  end
+
+  # PATHWAY
+  def pathways
+    lines_fetch('DBLINKS')
+  end
+
+  # DBLINKS
+  def dblinks
+    lines_fetch('DBLINKS')
+  end
+
+  # ATOM, BOND
+  def kcf
+    return "#{get('ATOM')}#{get('BOND')}"
+  end
+
+end # DRUG
+
+end # KEGG
+end # Bio
+
+
+if __FILE__ == $0
+  entry = ARGF.read	# dr:D00001
+  dr = Bio::KEGG::DRUG.new(entry)
+  p dr.entry_id
+  p dr.names
+  p dr.name
+  p dr.formula
+  p dr.mass
+  p dr.activity
+  p dr.remark
+  p dr.comment
+  p dr.dblinks
+  p dr.kcf
+end
+

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

@@ -0,0 +1,148 @@
+#
+# = bio/db/kegg/enzyme.rb - KEGG/ENZYME database class
+#
+# Copyright::  Copyright (C) 2001, 2002, 2007 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: enzyme.rb,v 0.12 2007/12/14 16:20:38 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+class KEGG
+
+class ENZYME < KEGGDB
+
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
+
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # ENTRY
+  def entry
+    field_fetch('ENTRY')
+  end
+
+  def entry_id
+    entry[/EC (\S+)/, 1]
+  end
+
+  def obsolete?
+    entry[/Obsolete/] ? true : false
+  end
+
+  # NAME
+  def names
+    field_fetch('NAME').split(/\s*;\s*/)
+  end
+
+  def name
+    names.first
+  end
+
+  # CLASS
+  def classes
+    lines_fetch('CLASS')
+  end
+
+  # SYSNAME
+  def sysname
+    field_fetch('SYSNAME')
+  end
+
+  # REACTION
+  def reaction
+    field_fetch('REACTION')
+  end
+
+  # ALL_REAC ';'
+  def all_reac
+    field_fetch('ALL_REAC')
+  end
+
+  def iubmb_reactions
+    all_reac.sub(/;\s*\(other\).*/, '').split(/\s*;\s*/)
+  end
+
+  def kegg_reactions
+    reac = all_reac
+    if reac[/\(other\)/]
+      reac.sub(/.*\(other\)\s*/, '').split(/\s*;\s*/)
+    else
+      []
+    end
+  end
+  
+  # SUBSTRATE
+  def substrates
+    field_fetch('SUBSTRATE').split(/\s*;\s*/)
+  end
+
+  # PRODUCT
+  def products
+    field_fetch('PRODUCT').split(/\s*;\s*/)
+  end
+
+  # INHIBITOR
+  def inhibitors
+    field_fetch('INHIBITOR').split(/\s*;\s*/)
+  end
+
+  # COFACTOR
+  def cofactors
+    field_fetch('COFACTOR').split(/\s*;\s*/)
+  end
+
+  # COMMENT
+  def comment
+    field_fetch('COMMENT')
+  end
+
+  # PATHWAY
+  def pathways
+    lines_fetch('PATHWAY')
+  end
+
+  # ORTHOLOGY
+  def orthologs
+    lines_fetch('ORTHOLOGY')
+  end
+
+  # GENES
+  def genes
+    lines_fetch('GENES')
+  end
+
+  # DISEASE
+  def diseases
+    lines_fetch('DISEASE')
+  end
+
+  # MOTIF
+  def motifs
+    lines_fetch('MOTIF')
+  end
+
+  # STRUCTURES
+  def structures
+    unless @data['STRUCTURES']
+      @data['STRUCTURES'] = fetch('STRUCTURES').sub(/(PDB: )*/,'').split(/\s+/)
+    end
+    @data['STRUCTURES']
+  end
+
+  # REFERENCE
+
+  # DBLINKS
+  def dblinks
+    lines_fetch('DBLINKS')
+  end
+
+end # ENZYME
+
+end # KEGG
+end # Bio
+

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

@@ -0,0 +1,155 @@
+#
+# = bio/db/kegg/expression.rb - KEGG EXPRESSION database class
+#
+# Copyright::	Copyright (C) 2001-2003, 2005
+#		Shuichi Kawashima <shuichi@hgc.jp>,
+#		Toshiaki Katayama <k@bioruby.org>
+# License::	The Ruby License
+#
+# $Id: expression.rb,v 1.11 2007/04/05 23:35:41 trevor Exp $
+#
+
+require "bio/db"
+
+module Bio
+class KEGG
+
+class EXPRESSION
+
+  def initialize(entry)
+    @orf2val   = Hash.new('')
+    @orf2rgb   = Hash.new('')
+    @orf2ratio = Hash.new('')
+    @max_intensity = 10000
+    entry.split("\n").each do |line|
+      unless /^#/ =~ line
+        ary = line.split("\t")
+        orf = ary.shift
+        val = ary[2, 4].collect {|x| x.to_f}
+        @orf2val[orf] = val 
+      end
+    end
+  end
+  attr_reader :orf2val
+  attr_reader :orf2rgb
+  attr_reader :orf2ratio
+  attr_reader :max_intensity
+
+  def control_avg
+    sum = 0.0
+    @orf2val.values.each do |v|
+      sum += v[0] - v[1]
+    end
+    sum/orf2val.size
+  end
+
+  def target_avg
+    sum = 0.0
+    @orf2val.values.each do |v|
+      sum += v[2] - v[3]
+    end
+    sum/orf2val.size
+  end
+
+  def control_var
+    sum = 0.0
+    avg = self.control_avg
+    @orf2val.values.each do |v|
+      tmp = v[0] - v[1]
+      sum += (tmp - avg)*(tmp - avg)
+    end
+    sum/orf2val.size
+  end
+
+  def target_var
+    sum = 0.0
+    avg = self.target_avg
+    @orf2val.values.each do |v|
+      tmp = v[2] - v[3]
+      sum += (tmp - avg)*(tmp - avg)
+    end
+    sum/orf2val.size
+  end
+
+  def control_sd
+    var = self.control_var
+    Math.sqrt(var)
+  end
+
+  def target_sd
+    var = self.target_var
+    Math.sqrt(var)
+  end
+
+  def up_regulated(num=20, threshold=nil)
+    logy_minus_logx
+    ary = @orf2ratio.to_a.sort{|a, b| b[1] <=> a[1]}
+    if threshold != nil
+      i = 0
+      while ary[i][1] > threshold
+        i += 1
+      end
+      return ary[0..i]
+    else
+      return ary[0..num-1]
+    end
+  end
+
+  def down_regulated(num=20, threshold=nil)
+    logy_minus_logx
+    ary = @orf2ratio.to_a.sort{|a, b| a[1] <=> b[1]}
+    if threshold != nil
+      i = 0
+      while ary[i][1] < threshold
+        i += 1
+      end
+      return ary[0..i]
+    else
+      return ary[0..num-1]
+    end
+  end
+
+  def regulated(num=20, threshold=nil)
+    logy_minus_logx
+    ary = @orf2ratio.to_a.sort{|a, b| b[1].abs <=> a[1].abs}
+    if threshold != nil
+      i = 0
+      while ary[i][1].abs > threshold
+        i += 1
+      end
+      return ary[0..i]
+    else
+      return ary[0..num-1]
+    end
+  end
+
+  def logy_minus_logx
+    @orf2val.each do |k, v|
+      @orf2ratio[k] = (1.0/Math.log10(2))*(Math.log10(v[2]-v[3]) - Math.log10(v[0]-v[1]))
+    end
+  end
+
+  def val2rgb
+    col_unit = @max_intensity/255
+    @orf2val.each do |k, v|
+      tmp_val = ((v[0] - v[1])/col_unit).to_i
+      if tmp_val > 255
+        g = "ff" 
+      else
+        g = format("%02x", tmp_val)
+      end
+      tmp_val = ((v[2] - v[3])/col_unit).to_i
+      if tmp_val > 255
+        r = "ff" 
+      else
+        r = format("%02x", tmp_val)
+      end
+      @orf2rgb[k] = r + g + "00"
+    end
+  
+  end
+
+end # class EXPRESSION
+
+end # class KEGG
+end # module Bio