bio 1.0.0 → 1.1.0

data/lib/bio/data/aa.rb

@@ -3,27 +3,9 @@
 #
 # Copyright::	Copyright (C) 2001, 2005
 #		Toshiaki Katayama <k@bioruby.org>
-# License::	LGPL
+# License::	The Ruby License
 #
-# $Id: aa.rb,v 0.16 2005/11/15 13:33:11 k Exp $
-#
-#--
-#
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#++
+# $Id: aa.rb,v 0.22 2007/04/06 04:44:51 k Exp $
 #
 
 module Bio
@@ -35,6 +17,7 @@ class AminoAcid
     # IUPAC code
     # * http://www.iupac.org/
     # * http://www.chem.qmw.ac.uk/iubmb/newsletter/1999/item3.html
+    # * http://www.ebi.ac.uk/RESID/faq.html
 
     NAMES = {
 
@@ -60,8 +43,10 @@ class AminoAcid
       'Y' => 'Tyr',
       'B' => 'Asx',	# D/N
       'Z' => 'Glx',	# E/Q
+      'J' => 'Xle',	# I/L
       'U' => 'Sec',	# 'uga' (stop)
-      '?' => 'Pyl',	# 'uag' (stop)
+      'O' => 'Pyl',	# 'uag' (stop)
+      'X' => 'Xaa',	# (unknown)
      
       'Ala' => 'alanine',
       'Cys' => 'cysteine',
@@ -83,10 +68,12 @@ class AminoAcid
       'Val' => 'valine',
       'Trp' => 'tryptophan',
       'Tyr' => 'tyrosine',
-      'Asx' => 'asparagine/aspartic acid',
-      'Glx' => 'glutamine/glutamic acid',
+      'Asx' => 'asparagine/aspartic acid [DN]',
+      'Glx' => 'glutamine/glutamic acid [EQ]',
+      'Xle' => 'isoleucine/leucine [IL]',
       'Sec' => 'selenocysteine',
       'Pyl' => 'pyrrolysine',
+      'Xaa' => 'unknown [A-Z]',
 
     }
 
@@ -230,10 +217,18 @@ class AminoAcid
     end
 
     def to_re(seq)
+      replace = {
+        'B' => '[DNB]',
+        'Z' => '[EQZ]',
+        'J' => '[ILJ]',
+        'X' => '[ACDEFGHIKLMNPQRSTVWYUOX]',
+      }
+      replace.default = '.'
+
       str = seq.to_s.upcase
-      str.gsub!(/[^BZACDEFGHIKLMNPQRSTVWYU]/, ".")
-      str.gsub!("B", "[DN]")
-      str.gsub!("Z", "[EQ]")
+      str.gsub!(/[^ACDEFGHIKLMNPQRSTVWYUO]/) { |aa|
+        replace[aa]
+      }
       Regexp.new(str)
     end
 

data/lib/bio/data/codontable.rb

@@ -3,9 +3,9 @@
 #
 # Copyright::	Copyright (C) 2001, 2004
 #		Toshiaki Katayama <k@bioruby.org>
-# License::	LGPL
+# License::	The Ruby License
 #
-# $Id: codontable.rb,v 0.16 2005/11/15 12:43:37 k Exp $
+# $Id: codontable.rb,v 0.18 2007/04/05 23:35:40 trevor Exp $
 #
 # == Data source
 #
@@ -42,24 +42,6 @@
 #   table = Bio::CodonTable[1]
 #   table.revtrans("A")  # => ["gcg", "gct", "gca", "gcc"]
 #
-#--
-#
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#++
-#
 
 module Bio
 

data/lib/bio/data/na.rb

@@ -3,9 +3,9 @@
 #
 # Copyright::	Copyright (C) 2001, 2005
 #		Toshiaki Katayama <k@bioruby.org>
-# License::	Ruby's
+# License::	The Ruby License
 #
-# $Id: na.rb,v 0.20 2006/02/08 12:15:42 k Exp $
+# $Id: na.rb,v 0.23 2007/04/06 04:41:28 k Exp $
 #
 # == Synopsis
 #
@@ -158,9 +158,24 @@ class NucleicAcid
     end
 
     def to_re(seq, rna = false)
+      replace = {
+        'y' => '[tcy]',
+        'r' => '[agr]',
+        'w' => '[atw]',
+        's' => '[gcw]',
+        'k' => '[tgk]',
+        'm' => '[acm]',
+        'b' => '[tgcyskb]',
+        'd' => '[atgrwkd]',
+        'h' => '[atcwmyh]',
+        'v' => '[agcmrsv]',
+        'n' => '[atgcyrwskmbdhvn]'
+      }
+      replace.default = '.'
+
       str = seq.to_s.downcase
-      str.gsub!(/[^atgcu]/) { |base|
-        NAMES[base] || '.'
+      str.gsub!(/[^atgcu]/) { |na|
+        replace[na]
       }
       if rna
         str.tr!("t", "u")

data/lib/bio/db.rb

@@ -1,11 +1,11 @@
 #
 # = bio/db.rb - common API for database parsers
 #
-# Copyright::	Copyright (C) 2001, 2002, 2005
-#		KATAYAMA Toshiaki <k@bioruby.org>
-# License::	Ruby's
+# Copyright::  Copyright (C) 2001, 2002, 2005
+#              Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
 #
-# $Id: db.rb,v 0.34 2006/02/27 09:13:08 k Exp $
+# $Id: db.rb,v 0.38 2007/05/08 17:02:13 nakao Exp $
 #
 # == On-demand parsing and cache
 #
@@ -220,12 +220,27 @@ class DB
 
   # Returns an Array containing each line of the field without a tag.
   # lines_fetch also stores the result in the @data hash.
-  def lines_fetch(tag) 
-    unless @data[tag]  
-      @data[tag] = get(tag).split(/\n/).map{ |l| tag_cut(l) }  
-    end  
-    @data[tag]  
-  end 
+  def lines_fetch(tag)
+    unless @data[tag]
+      list = []
+      lines = get(tag).split(/\n/)
+      lines.each do |line|
+        data = tag_cut(line)
+        if data[/^\S/]                  # next sub field
+          list << data
+        else                            # continued sub field
+          data.strip!
+          if list.last[/\-$/]           # folded
+            list[-1] += data
+          else
+            list[-1] += " #{data}"     # rest of list
+          end
+        end
+      end
+      @data[tag] = list
+    end
+    @data[tag]
+  end
 
 end # class DB
 
@@ -298,12 +313,12 @@ class EMBLDB < DB
 
   # Returns the contents of the entry as a Hash.
   def entry2hash(entry)
-    hash = Hash.new('')
+    hash = Hash.new { |h,k| h[k] = '' }
     entry.each_line do |line|
       tag = tag_get(line)
       next if tag == 'XX'
       tag = 'R' if tag =~ /^R./	# Reference lines
-      hash[tag] += line
+      hash[tag].concat line
     end
     return hash
   end

data/lib/bio/db/aaindex.rb

@@ -5,9 +5,9 @@
 #              KAWASHIMA Shuichi <s@bioruby.org>
 # Copyright::  Copyright (C) 2006
 #              Mitsuteru C. Nakao <n@bioruby.org>
-# License::    LGPL
+# License::    The Ruby License
 #
-# $Id: aaindex.rb,v 1.18 2006/02/22 07:35:19 nakao Exp $
+# $Id: aaindex.rb,v 1.20 2007/04/05 23:35:40 trevor Exp $
 #
 # == Description
 #
@@ -34,24 +34,6 @@
 #
 # * http://www.genome.jp/aaindex/
 #
-#--
-#
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#++
-#
 
 require "bio/db"
 require "matrix"

data/lib/bio/db/embl/common.rb

@@ -1,10 +1,11 @@
 #
 # = bio/db/embl.rb - Common methods for EMBL style database classes
 #
-# Copyright::   Copyright (C) 2001-2005 Mitsuteru C. Nakao <n@bioruby.org>
-# License::     LGPL
+# Copyright::   Copyright (C) 2001-2006
+#               Mitsuteru C. Nakao <n@bioruby.org>
+# License::     The Ruby License
 #
-# $Id: common.rb,v 1.9 2006/01/28 06:40:38 nakao Exp $
+# $Id: common.rb,v 1.12 2007/04/05 23:35:40 trevor Exp $
 #
 # == Description
 #
@@ -69,24 +70,6 @@
 # * The UniProtKB/SwissProt/TrEMBL User Manual 
 #   http://www.expasy.org/sprot/userman.html
 #
-#--
-#
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#++
-#
 
 require 'bio/db'
 require 'bio/reference'

data/lib/bio/db/embl/embl.rb

@@ -2,10 +2,10 @@
 # = bio/db/embl/embl.rb - EMBL database class
 #
 # 
-# Copyright::   Copyright (C) 2001-2005 Mitsuteru C. Nakao <n@bioruby.org>
-# License::     LGPL
+# Copyright::   Copyright (C) 2001-2007 Mitsuteru C. Nakao <n@bioruby.org>
+# License::     The Ruby License
 #
-# $Id: embl.rb,v 1.26 2006/01/28 06:40:38 nakao Exp $
+# $Id: embl.rb,v 1.29 2007/04/05 23:35:40 trevor Exp $
 #
 # == Description
 #
@@ -28,24 +28,6 @@
 # * The EMBL Nucleotide Sequence Database: Users Manual
 #   http://www.ebi.ac.uk/embl/Documentation/User_manual/usrman.html
 #
-#--
-#
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#++
-#
 
 require 'bio/db'
 require 'bio/db/embl/common'
@@ -58,7 +40,7 @@ class EMBL < EMBLDB
   # * Bio::EMBL#id_line -> <ID Hash>
   # where <ID Hash> is:
   #  {'ENTRY_NAME' => String, 'MOLECULE_TYPE' => String, 'DIVISION' => String,
-  #   'SEQUENCE_LENGTH' => Int}
+  #   'SEQUENCE_LENGTH' => Int, 'SEQUENCE_VERSION' => Int}
   #
   # ID Line
   #  "ID  ENTRY_NAME DATA_CLASS; MOLECULE_TYPE; DIVISION; SEQUENCE_LENGTH BP."
@@ -87,14 +69,31 @@ class EMBL < EMBLDB
   #  UNC (Unclassified)
   #  VRL (Viruses)
   #
+  # Rel 89-
+  # ID   CD789012; SV 4; linear; genomic DNA; HTG; MAM; 500 BP.
+  # ID <1>; SV <2>; <3>; <4>; <5>; <6>; <7> BP.
+  # 1. Primary accession number
+  # 2. Sequence version number
+  # 3. Topology: 'circular' or 'linear'
+  # 4. Molecule type (see note 1 below)
+  # 5. Data class (see section 3.1)
+  # 6. Taxonomic division (see section 3.2)
+  # 7. Sequence length (see note 2 below)
   def id_line(key=nil)
     unless @data['ID']
       tmp = Hash.new
       idline = fetch('ID').split(/; +/)         
-      tmp['ENTRY_NAME'], tmp['DATA_CLASS'] = idline[0].split(/ +/)
-      tmp['MOLECULE_TYPE'] = idline[1]
-      tmp['DIVISION'] = idline[2]
-      tmp['SEQUENCE_LENGTH'] = idline[3].strip.split(' ').first.to_i
+      tmp['ENTRY_NAME'], tmp['DATA_CLASS'] = idline.shift.split(/ +/)
+      if idline.first =~ /^SV/
+        tmp['SEQUENCE_VERSION'] = idline.shift.split(' ').last
+        tmp['TOPOLOGY'] = idline.shift
+        tmp['MOLECULE_TYPE'] = idline.shift
+        tmp['DATA_CLASS'] = idline.shift
+      else
+        tmp['MOLECULE_TYPE'] = idline.shift
+      end
+      tmp['DIVISION'] = idline.shift
+      tmp['SEQUENCE_LENGTH'] = idline.shift.strip.split(' ').first.to_i
 
       @data['ID'] = tmp
     end
@@ -146,10 +145,14 @@ class EMBL < EMBLDB
   # SV Line; sequence version (1/entry)
   #  SV    Accession.Version
   def sv
-    field_fetch('SV').sub(/;/,'')
+    if (v = field_fetch('SV').sub(/;/,'')) == ""
+      [id_line['ENTRY_NAME'], id_line['SEQUENCE_VERSION']].join('.') 
+    else
+      v
+    end  
   end
   def version
-    sv.split(".")[1].to_i
+    (sv.split(".")[1] || id_line['SEQUENCE_VERSION']).to_i
   end
 
   
@@ -394,61 +397,6 @@ class EMBL < EMBLDB
     return feature
   end
 
-end
-
-end
-
-
-if __FILE__ == $0
-  while ent = $<.gets(Bio::EMBL::RS)
-    puts "\n ==> e = Bio::EMBL.new(ent) "
-    e = Bio::EMBL.new(ent)
-
-    puts "\n ==> e.entry_id "
-    p e.entry_id
-    puts "\n ==> e.id_line "
-    p e.id_line
-    puts "\n ==> e.id_line('molecule') "
-    p e.id_line('molecule')
-    puts "\n ==> e.molecule "
-    p e.molecule
-    puts "\n ==> e.ac "
-    p e.ac
-    puts "\n ==> e.sv "
-    p e.sv
-    puts "\n ==> e.dt "
-    p e.dt
-    puts "\n ==> e.dt('created') "
-    p e.dt('created')
-    puts "\n ==> e.de "
-    p e.de
-    puts "\n ==> e.kw "
-    p e.kw
-    puts "\n ==> e.os "
-    p e.os
-    puts "\n ==> e.oc "
-    p e.oc
-    puts "\n ==> e.og "
-    p e.og
-    puts "\n ==> e.ref "
-    p e.ref
-    puts "\n ==> e.dr "
-    p e.dr
-    puts "\n ==> e.ft "
-    p e.ft
-    puts "\n ==> e.each_cds {|c| p c}"
-    p e.each_cds {|c| p c }
-    puts "\n ==> e.sq "
-    p e.sq
-    puts "\n ==> e.sq('a') "
-    p e.sq('a')
-    puts "\n ==> e.gc"    
-    p e.gc
-    puts "\n ==> e.seq "
-    p e.seq
-  end
-
-end
-
-
+end # class EMBL
 
+end # module Bio