bio 0.7.0

data/lib/bio/db/nbrf.rb

@@ -0,0 +1,199 @@
+#
+# = bio/db/nbrf.rb - NBRF/PIR format sequence data class
+#
+# Copyright:: Copyright (C) 2001-2003 GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+#             Copyright (C) 2001-2002 KATAYAMA Toshiaki <k@bioruby.org>
+# License::   LGPL
+#
+#--
+#  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: nbrf.rb,v 1.7 2005/12/18 15:58:41 k Exp $
+#
+# Sequence data class for NBRF/PIR flatfile format.
+#
+# = References
+#
+# * http://pir.georgetown.edu/pirwww/otherinfo/doc/techbulletin.html
+# * http://www.sander.embl-ebi.ac.uk/Services/webin/help/webin-align/align_format_help.html#pir
+# * http://www.cmbi.kun.nl/bioinf/tools/crab_pir.html
+#
+
+require 'bio/db'
+require 'bio/sequence'
+
+module Bio
+
+  # Sequence data class for NBRF/PIR flatfile format.
+  class NBRF < DB
+    #--
+    # based on Bio::FastaFormat class
+    #++
+
+    # Delimiter of each entry. Bio::FlatFile uses it.
+    DELIMITER	= RS = "*\n"
+
+    # Creates a new NBRF object. It stores the comment and sequence
+    # information from one entry of the NBRF/PIR format string.
+    # If the argument contains more than one
+    # entry, only the first entry is used.
+    def initialize(str)
+      str = str.sub(/\A[\r\n]+/, '') # remove first void lines
+      line1, line2, rest = str.split(/^/, 3)
+
+      rest = rest.to_s
+      rest.sub!(/^>.*/m, '') # remove trailing entries for sure
+      @entry_overrun = $&
+      rest.sub!(/\*\s*\z/, '') # remove last '*' and "\n"
+      @data = rest
+
+      @definition = line2.to_s.chomp
+      if /^>?([A-Za-z0-9]{2})\;(.*)/ =~ line1.to_s then
+        @seq_type = $1
+        @entry_id = $2
+      end
+    end
+
+    # Returns sequence type described in the entry.
+    #  P1 (protein), F1 (protein fragment)
+    #  DL (DNA linear), DC (DNA circular)
+    #  RL (DNA linear), RC (DNA circular)
+    #  N3 (tRNA), N1 (other functional RNA)
+    attr_accessor :seq_type
+
+    # Returns ID described in the entry.
+    attr_accessor :entry_id
+    alias accession entry_id
+
+    # Returns the description line of the NBRF/PIR formatted data.
+    attr_accessor :definition
+
+    # sequence data of the entry (???)
+    attr_accessor :data
+
+    # piece of next entry. Bio::FlatFile uses it.
+    attr_reader :entry_overrun
+
+
+    # Returns the stored one entry as a NBRF/PIR format. (same as to_s)
+    def entry
+      @entry = ">#{@seq_type or 'XX'};#{@entry_id}\n#{definition}\n#{@data}*\n"
+    end
+    alias to_s entry
+
+    # Returns Bio::Sequence::AA, Bio::Sequence::NA, or Bio::Sequence,
+    # depending on sequence type.
+    def seq_class
+      case @seq_type
+      when /[PF]1/
+        # protein
+        Sequence::AA
+      when /[DR][LC]/, /N[13]/
+        # nucleic
+        Sequence::NA
+      else
+        Sequence
+      end
+    end
+
+    # Returns sequence data.
+    # Returns Bio::Sequence::NA, Bio::Sequence::AA or Bio::Sequence,
+    # according to the sequence type.
+    def seq
+      unless defined?(@seq)
+        @seq = seq_class.new(@data.tr(" \t\r\n0-9", '')) # lazy clean up
+      end
+      @seq
+    end
+
+    # Returns sequence length.
+    def length
+      seq.length
+    end
+
+    # Returens the nucleic acid sequence.
+    # If you call naseq for protein sequence, RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def naseq
+      if seq.is_a?(Bio::Sequence::AA) then
+        raise 'not nucleic but protein sequence'
+      elsif seq.is_a?(Bio::Sequence::NA) then
+        seq
+      else
+        Bio::Sequence::NA.new(seq)
+      end
+    end
+      
+    # Returens the length of sequence.
+    # If you call nalen for protein sequence, RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def nalen
+      naseq.length
+    end
+
+    # Returens the protein (amino acids) sequence.
+    # If you call aaseq for nucleic acids sequence,
+    # RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def aaseq
+      if seq.is_a?(Bio::Sequence::NA) then
+        raise 'not nucleic but protein sequence'
+      elsif seq.is_a?(Bio::Sequence::AA) then
+        seq
+      else
+        Bio::Sequence::AA.new(seq)
+      end
+    end
+
+    # Returens the length of protein (amino acids) sequence.
+    # If you call aaseq for nucleic acids sequence,
+    # RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def aalen
+      aaseq.length
+    end
+
+    #--
+    #class method
+    #++
+
+    # Creates a NBRF/PIR formatted text.
+    # Parameters can be omitted.
+    def self.to_nbrf(hash)
+      seq_type = hash[:seq_type]
+      seq = hash[:seq]
+      unless seq_type
+        if seq.is_a?(Bio::Sequence::AA) then
+          seq_type = 'P1'
+        elsif seq.is_a?(Bio::Sequence::NA) then
+          seq_type = /u/i =~ seq ? 'RL' : 'DL'
+        else
+          seq_type = 'XX'
+        end
+      end
+      width = hash.has_key?(:width) ? hash[:width] : 70
+      if width then
+        seq = seq.to_s + "*"
+        seq.gsub!(Regexp.new(".{1,#{width}}"), "\\0\n")
+      else
+        seq = seq.to_s + "*\n"
+      end
+      ">#{seq_type};#{hash[:entry_id]}\n#{hash[:definition]}\n#{seq}"
+    end
+
+  end #class NBRF
+end #module Bio
+

data/lib/bio/db/pdb.rb

@@ -0,0 +1,38 @@
+#
+# bio/db/pdb.rb - PDB database classes
+#
+#   Copyright (C) 2004 GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+#
+#  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: pdb.rb,v 1.5 2005/12/16 19:23:03 ngoto Exp $
+#
+
+require 'bio/db'
+
+# definition of the PDB class
+module Bio
+  class PDB #< DB
+  end #class PDB
+end #module Bio
+
+# require other files under pdb directory
+require 'bio/db/pdb/utils'
+require 'bio/db/pdb/atom'
+require 'bio/db/pdb/residue'
+require 'bio/db/pdb/chain'
+require 'bio/db/pdb/model'
+require 'bio/db/pdb/pdb'
+

data/lib/bio/db/pdb/atom.rb

@@ -0,0 +1,60 @@
+#
+# bio/db/pdb/atom.rb - Coordinate and atom class for PDB
+#
+#   Copyright (C) 2004 Alex Gutteridge <alexg@ebi.ac.uk>
+#   Copyright (C) 2004 GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+#
+#  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: atom.rb,v 1.5 2005/12/18 17:33:32 ngoto Exp $
+
+require 'matrix'
+require 'bio/db/pdb'
+
+module Bio
+  class PDB
+
+    class Coordinate < Vector
+      def self.[](x,y,z)
+        super
+      end
+
+      def self.elements(array, *a)
+        raise 'Size of given array must be 3' if array.size != 3
+        super
+      end
+      
+      def x; self[0]; end
+      def y; self[1]; end
+      def z; self[2]; end
+      def x=(n); self[0]=n; end
+      def y=(n); self[1]=n; end
+      def z=(n); self[2]=n; end
+
+      # Definition of 'to_ary' means objects of the class is
+      # implicitly regarded as an array.
+      def to_ary; self.to_a; end
+
+      def xyz; self; end
+      
+      def distance(object2)
+        Utils::to_xyz(object2)
+        (self - object2).r
+      end
+    end #class Coordinate
+
+  end #class PDB
+end #class Bio
+

data/lib/bio/db/pdb/chain.rb

@@ -0,0 +1,117 @@
+#
+# bio/db/pdb/chain.rb - chain class for PDB
+#
+#   Copyright (C) 2004 Alex Gutteridge <alexg@ebi.ac.uk>
+#
+#  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: chain.rb,v 1.2 2005/09/26 13:00:08 k Exp $
+
+require 'bio/db/pdb'
+
+module Bio
+
+  class PDB
+
+    class Chain
+      
+      include Utils
+      include AtomFinder
+      include ResidueFinder
+      include Enumerable
+      include Comparable
+      
+      attr_reader :id, :model
+      attr_writer :id
+      
+      def initialize(id = nil, model = nil)
+        
+        @id       = id
+        
+        @model    = model
+        
+        @residues = Array.new
+        @ligands  = Array.new
+        
+      end
+      
+      #Keyed access to residues based on ids
+      def [](key)
+        #If you want to find HETATMS you need to add LIGAND to the id
+        if key.to_s[0,6] == 'LIGAND'
+          residue = @ligands.find{ |residue| key.to_s == residue.id }
+        else
+          residue = @residues.find{ |residue| key.to_s == residue.id }
+        end
+      end
+      
+      #Add a residue to this chain
+      def addResidue(residue)
+        raise "Expecting a Bio::PDB::Residue" if not residue.is_a? Bio::PDB::Residue
+        @residues.push(residue)
+        self
+      end
+      
+      #Add a ligand to this chain
+      def addLigand(residue)
+        raise "Expecting a Bio::PDB::Residue" if not residue.is_a? Bio::PDB::Residue
+        @ligands.push(residue)
+        self
+      end
+      
+      #Residue iterator
+      def each
+        @residues.each{ |residue| yield residue }
+      end
+      #Alias to override ResidueFinder#each_residue
+      alias each_residue each
+      
+      #Sort based on chain id
+      def <=>(other)
+        return @id <=> other.id
+      end
+      
+      #Stringifies each residue
+      def to_s
+        string = ""
+        @residues.each{ |residue| string << residue.to_s }
+        string = string << "TER\n"
+        return string
+      end
+
+      def atom_seq
+        string = ""
+        last_residue_num = nil
+        @residues.each{ |residue|
+          if last_residue_num and 
+              (residue.resSeq.to_i - last_residue_num).abs > 1
+            (residue.resSeq.to_i - last_residue_num).abs.times{ string << 'X' }
+          end
+          tlc = residue.resName.capitalize
+          olc = AminoAcid.names.invert[tlc]
+          if !olc
+            olc = 'X'
+          end
+          string << olc
+        }
+        Bio::Sequence::AA.new(string)
+        
+      end
+      
+    end
+
+  end
+
+end

data/lib/bio/db/pdb/model.rb

@@ -0,0 +1,106 @@
+#
+# bio/db/pdb/model.rb - model class for PDB
+#
+#   Copyright (C) 2004 Alex Gutteridge <alexg@ebi.ac.uk>
+#
+#  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: model.rb,v 1.2 2005/09/26 13:00:08 k Exp $
+
+require 'bio/db/pdb'
+
+module Bio
+
+  class PDB
+
+    #Model class
+    class Model
+      
+      include Utils
+      include AtomFinder
+      include ResidueFinder
+      include ChainFinder
+      include Enumerable
+      include Comparable
+      
+      attr_reader :model_serial, :structure, :solvent
+      attr_writer :model_serial
+      
+      def initialize(model_serial = nil, structure = nil)
+        
+        @model_serial = model_serial
+        
+        @structure    = structure
+        
+        @chains       = Array.new
+        @solvent      = Chain.new('',self)
+        
+      end
+      
+      #Adds a chain
+      def addChain(chain)
+        raise "Expecting a Bio::PDB::Chain" if not chain.is_a? Bio::PDB::Chain
+        @chains.push(chain)
+        self        
+      end
+      
+      #adds a solvent molecule
+      def addSolvent(solvent)
+        raise "Expecting a Bio::PDB::Residue" if not solvent.is_a? Bio::PDB::Residue
+        @solvent.addResidue(solvent)
+      end
+
+      def removeSolvent
+        @solvent = nil
+      end
+
+      #Chain iterator
+      def each
+        @chains.each{ |chain| yield chain }
+      end
+      #Alias to override ChainFinder#each_chain
+      alias each_chain each
+     
+      #Sorts models based on serial number
+      def <=>(other)
+        return @mode_serial <=> other.model_serial
+      end
+      
+      #Keyed access to chains
+      def [](key)
+        chain = @chains.find{ |chain| key == chain.id }
+      end
+      
+      #stringifies to chains
+      def to_s
+        string = ""
+        if model_serial
+          string = "MODEL     #{model_serial}" #Should use proper formatting
+        end
+        @chains.each{ |chain| string << chain.to_s }
+        if solvent
+          string << @solvent.to_s
+        end
+        if model_serial
+          string << "ENDMDL"
+        end
+        return string
+      end
+      
+    end #class Model
+
+  end
+
+end