wwood-bioruby 1.2.11

data/lib/bio/appl/clustalw.rb

@@ -0,0 +1,219 @@
+#
+# = bio/appl/clustalw.rb - CLUSTAL W wrapper class
+#
+# Copyright:: Copyright (C) 2003 GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+# License::   The Ruby License
+#
+#  $Id: clustalw.rb,v 1.19 2007/07/16 12:27:29 ngoto Exp $
+#
+# Bio::ClustalW is a CLUSTAL W execution wrapper class.
+# It can also be called as an alignment factory.
+# CLUSTAL W is a very popular software for multiple sequence alignment.
+#
+# == References
+#
+# * Thompson,J.D., Higgins,D.G. and Gibson,T.J..
+#   CLUSTAL W: improving the sensitivity of progressive multiple sequence
+#   alignment through sequence weighting, position-specific gap penalties
+#   and weight matrix choice. Nucleic Acids Research, 22:4673-4680, 1994.
+#   http://nar.oxfordjournals.org/cgi/content/abstract/22/22/4673
+# * http://www.ebi.ac.uk/clustalw/
+# * ftp://ftp.ebi.ac.uk/pub/software/unix/clustalw/
+#
+
+
+require 'tempfile'
+
+require 'bio/command'
+require 'bio/sequence'
+require 'bio/alignment'
+
+module Bio
+
+  # Bio::ClustalW is a CLUSTAL W execution wrapper class.
+  # Its object is also called an alignment factory.
+  # CLUSTAL W is a very popular software for multiple sequence alignment.
+  class ClustalW
+
+    autoload :Report, 'bio/appl/clustalw/report'
+
+    # Creates a new CLUSTAL W execution wrapper object (alignment factory).
+    def initialize(program = 'clustalw', opt = [])
+      @program = program
+      @options = opt
+      @command = nil
+      @output = nil
+      @report = nil
+      @data_stdout = nil
+      @exit_status = nil
+      @output_dnd = nil
+    end
+
+    # name of the program (usually 'clustalw' in UNIX)
+    attr_accessor :program
+
+    # options
+    attr_accessor :options
+
+    # option is deprecated. Instead, please use options.
+    def option
+      warn "Bio::ClustalW#option is deprecated. Please use options."
+      options
+    end
+
+    # Returns last command-line strings executed by this factory.
+    # Note that filenames described in the command-line may already
+    # be removed because they are temporary files.
+    # Returns an array.
+    attr_reader :command
+
+    # This method will be deprecated.
+    #
+    # Returns last messages of CLUSTAL W execution.
+    def log
+      #warn 'Bio::ClustalW#log will be deprecated.'
+      @data_stdout
+    end
+
+    # Returns last raw alignment result (String or nil).
+    attr_reader :output
+
+    # Returns last alignment result.
+    # Returns a Bio::ClustalW::Report object.
+    attr_reader :report
+
+    # Last exit status
+    attr_reader :exit_status
+
+    # Last output to the stdout.
+    attr_accessor :data_stdout
+    
+    # Clear the internal data and status, except program and options.
+    def reset
+      @command = nil
+      @output = nil
+      @report = nil
+      @exit_status = nil
+      @data_stdout = nil
+      @output_dnd = nil
+    end
+
+    # Executes the program(clustalw).
+    # If +seqs+ is not nil, perform alignment for seqs.
+    # If +seqs+ is nil, simply executes CLUSTAL W.
+    #
+    # Compatibility note: When seqs is nil,
+    # returns true if the program exits normally, and
+    # returns false if the program exits abnormally.
+    def query(seqs)
+      if seqs then
+        query_align(seqs)
+      else
+        exec_local(@options)
+        @exit_status.exitstatus == 0 ? true : false
+      end
+    end
+
+    # Note that this method will be renamed to query_alignment.
+    #
+    # Performs alignment for +seqs+.
+    # +seqs+ should be Bio::Alignment or Array of sequences or nil.
+    #
+    # Compatibility Note: Nucleic or amino is not determined by this method.
+    def query_align(seqs)
+      unless seqs.is_a?(Bio::Alignment)
+        seqs = Bio::Alignment.new(seqs)
+      end
+      query_string(seqs.output_fasta(:width => 70,
+                                     :avoid_same_name => true))
+    end
+
+    # Performs alignment for +seqs+.
+    # +seqs+ should be Bio::Alignment or Array of sequences or nil.
+    def query_alignment(seqs)
+      query_align(seqs)
+    end
+
+    # Performs alignment for +str+.
+    # +str+ should be a string that can be recognized by CLUSTAL W.
+    #
+    # Compatibility Note: 2nd argument is deprecated and ignored.
+    def query_string(str, *arg)
+      if arg.size > 0 then
+        warn '2nd argument of Bio::ClustalW#query_string is ignored'
+      end
+      begin
+        tf_in = Tempfile.open('align')
+        tf_in.print str
+      ensure
+        tf_in.close(false)
+      end
+      r = query_by_filename(tf_in.path)
+      tf_in.close(true)
+      r
+    end
+
+    # Performs alignment of sequences in the file named +path+.
+    #
+    # Compatibility Note: 2nd argument (seqtype) is deprecated and ignored.
+    def query_by_filename(path, *arg)
+      if arg.size > 0 then
+        warn '2nd argument of Bio::ClustalW#query_by_filename is ignored'
+      end
+
+      tf_out = Tempfile.open('clustalout')
+      tf_out.close(false)
+      tf_dnd = Tempfile.open('clustaldnd')
+      tf_dnd.close(false)
+
+      opt = [ "-align",
+        "-infile=#{path}",
+        "-outfile=#{tf_out.path}",
+        "-newtree=#{tf_dnd.path}",
+        "-outorder=input"
+      ]
+      #opt << "-type=#{seqtype}" if seqtype
+      opt.concat(@options)
+      exec_local(opt)
+      tf_out.open
+      @output = tf_out.read
+      tf_out.close(true)
+      tf_dnd.open
+      @output_dnd = tf_dnd.read
+      tf_dnd.close(true)
+      @report = Report.new(@output)
+      @report
+    end
+
+    # Returns last alignment guild-tree (file.dnd).
+    attr_reader :output_dnd
+
+    #---
+    # Returns last error messages (to stderr) of CLUSTAL W execution.
+    #attr_reader :errorlog
+    #+++
+    #errorlog is deprecated (no replacement) and returns empty string.
+    def errorlog
+      warn "errorlog is deprecated (no replacement) and returns empty string."
+      ''
+    end
+
+    private
+    # Executes the program in the local machine.
+    def exec_local(opt)
+      @command = [ @program,  *opt ]
+      #STDERR.print "DEBUG: ", @command.join(" "), "\n"
+      @data_stdout = nil
+      @exit_status = nil
+
+      Bio::Command.call_command(@command) do |io|
+        io.close_write
+        @data_stdout = io.read
+      end
+      @exit_status = $?
+    end
+
+  end #class ClustalW
+
+end #module Bio
+

data/lib/bio/appl/clustalw/report.rb

@@ -0,0 +1,152 @@
+#
+# = bio/appl/clustalw/report.rb - CLUSTAL W format data (*.aln) class
+#
+# Copyright:: Copyright (C) 2003 GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+# License::   The Ruby License
+#
+#  $Id: report.rb,v 1.13 2007/07/18 08:47:39 ngoto Exp $
+#
+# Bio::ClustalW::Report is a CLUSTAL W report (*.aln file) parser.
+# CLUSTAL W is a very popular software for multiple sequence alignment.
+#
+# == References
+#
+# * Thompson,J.D., Higgins,D.G. and Gibson,T.J..
+#   CLUSTAL W: improving the sensitivity of progressive multiple sequence
+#   alignment through sequence weighting, position-specific gap penalties
+#   and weight matrix choice. Nucleic Acids Research, 22:4673-4680, 1994.
+#   http://nar.oxfordjournals.org/cgi/content/abstract/22/22/4673
+# * http://www.ebi.ac.uk/clustalw/
+# * ftp://ftp.ebi.ac.uk/pub/software/unix/clustalw/
+#
+
+require 'bio/sequence'
+require 'bio/db'
+require 'bio/alignment'
+require 'bio/appl/clustalw'
+
+module Bio
+  class ClustalW
+
+    # CLUSTAL W result data (*.aln file) parser class.
+    class Report < Bio::DB
+
+      # Delimiter of each entry. Bio::FlatFile uses it.
+      # In Bio::ClustalW::Report, it it nil (1 entry 1 file).
+      DELIMITER = nil
+
+      # Creates new instance.
+      # +str+ should be a CLUSTAL format string.
+      # +seqclass+ should on of following:
+      # * Class:  Bio::Sequence::AA, Bio::Sequence::NA, ...
+      # * String: 'PROTEIN', 'DNA', ...
+      def initialize(str, seqclass = nil)
+        @raw = str
+        @align = nil
+        @match_line = nil
+        @header = nil
+        case seqclass
+        when /PROTEIN/i
+          @seqclass = Bio::Sequence::AA
+        when /[DR]NA/i
+          @seqclass = Bio::Sequence::NA
+        else
+          if seqclass.is_a?(Module) then
+            @seqclass = seqclass
+          else
+            @seqclass = Bio::Sequence
+          end
+        end
+      end
+      # string of whole result
+      attr_reader :raw
+
+      # sequence class (one of Bio::Sequence, Bio::Sequence::NA,
+      # Bio::Sequence::AA, ...)
+      attr_reader :seqclass
+
+      # Shows first line of the result data, for example,
+      # 'CLUSTAL W (1.82) multiple sequence alignment'.
+      # Returns a string.
+      def header
+        @header or (do_parse or @header)
+      end
+
+      # Shows "match line" of CLUSTAL's alignment result, for example,
+      # ':* :* .*   *       .*::*.   ** :* . *    .        '.
+      # Returns a string.
+      def match_line
+        @match_line or (do_parse or @match_line)
+      end
+
+      # Gets an multiple alignment.
+      # Returns a Bio::Alignment object.
+      def alignment
+        do_parse() unless @align
+        @align
+      end
+
+      # This will be deprecated. Instead, please use alignment.
+      #
+      # Gets an multiple alignment.
+      # Returns a Bio::Alignment object.
+      def align
+        warn "Bio::ClustalW#align will be deprecated. Please use \'alignment\'."
+        alignment
+      end
+
+      # This will be deprecated. Instead, please use alignment.output_fasta.
+      #
+      # Gets an fasta-format string of the sequences.
+      # Returns a string.
+      def to_fasta(*arg)
+        warn "Bio::ClustalW::report#to_fasta is deprecated. Please use \'alignment.output_fasta\'"
+        alignment.output_fasta(*arg)
+      end
+
+      # Compatibility note: Behavior of the method will be changed
+      # in the future.
+      #
+      # Gets an array of the sequences.
+      # Returns an array of Bio::FastaFormat objects.
+      def to_a
+        alignment.to_fastaformat_array
+      end
+
+      private
+      # Parses Clustal W result text.
+      def do_parse
+        return nil if @align
+        a = @raw.split(/\r?\n\r?\n/)
+        @header = a.shift.to_s
+        xalign = Bio::Alignment.new
+        @match_line = ''
+        if a.size > 0 then
+          a[0].gsub!(/\A(\r?\n)+/, '')
+          a.collect! { |x| x.split(/\r?\n/) }
+          a.each { |x|
+            x.each { |y| y.sub!(/ +\d+\s*$/, '') }} #for -SEQNOS=on option
+          @tagsize = ( a[0][0].rindex(/\s/) or -1 ) + 1
+          a.each do |x|
+            @match_line << x.pop.to_s[@tagsize..-1]
+          end
+          a[0].each do |y|
+            xalign.store(y[0, @tagsize].sub(/\s+\z/, ''), '')
+          end
+          a.each do |x|
+            x.each do |y|
+              name = y[0, @tagsize].sub(/\s+\z/, '')
+              seq = y[@tagsize..-1]
+              xalign[name] << seq
+            end
+          end
+          xalign.collect! { |x| @seqclass.new(x) }
+        end
+        @align = xalign
+        nil
+      end
+
+    end #class Report
+  end #class ClustalW
+end #module Bio
+

data/lib/bio/appl/emboss.rb

@@ -0,0 +1,203 @@
+#
+# = bio/appl/emboss.rb - EMBOSS wrapper
+# 
+# Copyright::  Copyright (C) 2002, 2005 Toshiaki Katayama<k@bioruby.org>
+# Copyright::  Copyright (C) 2006       Jan Aerts <jan.aerts@bbsrc.ac.uk>
+# License::    The Ruby License
+#
+# $Id: emboss.rb,v 1.9 2008/01/10 03:51:06 ngoto Exp $
+#
+
+module Bio
+
+# == Description
+#
+# This file holds classes pertaining to the EMBOSS software suite.
+#
+# This class provides a wrapper for the applications of the EMBOSS suite, which 
+# is a mature and stable collection of open-source applications that can handle
+# a huge range of sequence formats.
+# Applications include:
+# * Sequence alignment
+# * Rapid database searching with sequence patterns
+# * Protein motif identification, including domain analysis
+# * Nucleotide sequence pattern analysis---for example to identify CpG islands or repeats
+# * Codon usage analysis for small genomes
+# * Rapid identification of sequence patterns in large scale sequence sets
+# * Presentation tools for publication
+#
+# See the emboss website for more information: http://emboss.sourceforge.net.
+#
+#
+# == Usage
+#
+#  require 'bio'
+#
+#  # Suppose that you could get the sequence for XLRHODOP by running
+#  # the EMBOSS command +seqret embl:xlrhodop+ on the command line.
+#  # Then you can get the output of that command in a String object
+#  # by using  Bio::EMBOSS.run method.
+#  xlrhodop = Bio::EMBOSS.run('seqret', 'embl:xlrhodop')
+#  puts xlrhodop
+#
+#  # Or all in one go:
+#  puts Bio::EMBOSS.run('seqret', 'embl:xlrhodop')
+#
+#  # Similarly:
+#  puts Bio::EMBOSS.run('transeq', '-sbegin', '110','-send', '1171',
+#                       'embl:xlrhodop')
+#  puts Bio::EMBOSS.run('showfeat', 'embl:xlrhodop')
+#  puts Bio::EMBOSS.run('seqret', 'embl:xlrhodop', '-osformat', 'acedb')
+#
+#  # A shortcut exists for this two-step process for +seqret+ and +entret+.
+#  puts Bio::EMBOSS.seqret('embl:xlrhodop')
+#  puts Bio::EMBOSS.entret('embl:xlrhodop')
+#
+#  # You can use %w() syntax.
+#  puts Bio::EMBOSS.run(*%w( transeq -sbegin 110 -send 1171 embl:xlrhodop ))
+#
+#  # You can also use Shellwords.shellwords.
+#  require 'shellwords'
+#  str = 'transeq -sbegin 110 -send 1171 embl:xlrhodop'
+#  cmd = Shellwords.shellwords(str)
+#  puts Bio::EMBOSS.run(*cmd)
+#
+
+#
+# == Pre-requisites
+#
+# You must have the EMBOSS suite installed locally. You can download from the
+# project website (see References below).
+#
+# = Rereferences
+#
+# * http://emboss.sourceforge.net
+# * Rice P, Longden I and Bleasby A. \
+#    EMBOSS: the European Molecular Biology Open Software Suite. \
+#    Trends Genet. 2000 Jun ; 16(6): 276-7 
+#
+class EMBOSS
+
+  # Combines the initialization and execution for the emboss +seqret+ command.
+  #
+  #  puts Bio::EMBOSS.seqret('embl:xlrhodop')
+  #
+  # is equivalent to:
+  #
+  #  object = Bio::EMBOSS.new('seqret embl:xlrhodop')
+  #  puts object.exec
+  # ---
+  # *Arguments*:
+  # * (required) _arg_: argument given to the emboss seqret command
+  # *Returns*:: String
+  def self.seqret(arg)
+    str = self.retrieve('seqret', arg)
+  end
+
+  # Combines the initialization and execution for the emboss +entret+ command.
+  #
+  #  puts Bio::EMBOSS.entret('embl:xlrhodop')
+  #
+  # is equivalent to:
+  #
+  #  object = Bio::EMBOSS.new('entret embl:xlrhodop')
+  #  puts object.exec
+  # ---
+  # *Arguments*:
+  # * (required) _arg_: argument given to the emboss entret command
+  # *Returns*:: String
+  def self.entret(arg)
+    str = self.retrieve('entret', arg)
+  end
+
+  # WARNING: Bio::EMBOSS.new will be changed in the future because
+  # Bio::EMBOSS.new(cmd_line) is inconvenient and potential security hole.
+  # Using Bio::EMBOSS.run(program, options...) is strongly recommended.
+  #
+  # Initializes a new Bio::EMBOSS object. This provides a holder that can
+  # subsequently be executed (see Bio::EMBOSS.exec). The object does _not_
+  # hold any actual data when initialized.
+  #
+  #   e = Bio::EMBOSS.new('seqret embl:xlrhodop')
+  #
+  # For e to actually hold data, it has to be executed:
+  #   puts e.exec
+  #
+  # For an overview of commands that can be used with this method, see the
+  # emboss website.
+  # ---
+  # *Arguments*:
+  # * (required) _command_: emboss command
+  # *Returns*:: Bio::EMBOSS object
+  def initialize(cmd_line)
+    warn 'Bio::EMBOSS.new(cmd_line) is inconvenient and potential security hole. Using Bio::EMBOSS.run(program, options...) is strongly recommended.'
+    @cmd_line = cmd_line + ' -stdout -auto'
+  end
+
+  # A Bio::EMBOSS object has to be executed before it can return any result.
+  #   obj_A = Bio::EMBOSS.new('transeq -sbegin 110 -send 1171 embl:xlrhodop')
+  #   puts obj_A.result                   #=> nil
+  #   obj_A.exec
+  #   puts obj_A.result                   #=> a FASTA-formatted sequence
+  #
+  #   obj_B = Bio::EMBOSS.new('showfeat embl:xlrhodop')
+  #   obj_B.exec
+  #   puts obj_B.result
+  def exec
+    begin
+      @io = IO.popen(@cmd_line, "w+")
+      @result = @io.read
+      return @result
+    ensure
+      @io.close
+    end
+  end
+  
+  # Pipe for the command
+  attr_reader :io
+  
+  # Result of the executed command
+  attr_reader :result
+
+  # Runs an emboss program and get the result as string.
+  # Note that "-auto -stdout" are automatically added to the options.
+  #
+  # Example 1:
+  #
+  #   result = Bio::EMBOSS.run('seqret', 'embl:xlrhodop')
+  #
+  # Example 2:
+  #
+  #   result = Bio::EMBOSS.run('water',
+  #                             '-asequence', 'swissprot:slpi_human',
+  #                             '-bsequence', 'swissprot:slpi_mouse')
+  #
+  # Example 3:
+  #   options = %w( -asequence swissprot:slpi_human
+  #                 -bsequence swissprot:slpi_mouse )
+  #   result = Bio::EMBOSS.run('needle', *options)
+  #
+  # For an overview of commands that can be used with this method, see the
+  # emboss website.
+  # ---
+  # *Arguments*:
+  # * (required) _program_: command name, or filename of an emboss program
+  # * _options_: options given to the emboss program
+  # *Returns*:: String
+  def self.run(program, *options)
+    cmd = [ program, *options ]
+    cmd.push '-auto'
+    cmd.push '-stdout'
+    return Bio::Command.query_command(cmd)
+  end
+
+  private
+
+  def self.retrieve(cmd, arg)
+    cmd = [ cmd, arg, '-auto', '-stdout' ]
+    return Bio::Command.query_command(cmd)
+  end
+
+end # EMBOSS
+
+end # Bio