bio 1.2.1 → 1.3.0

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

@@ -7,7 +7,7 @@
 #              Toshiaki Katayama <k@bioruby.org>
 # License::    The Ruby License
 #
-# $Id: xmlparser.rb,v 1.17 2007/04/05 23:35:39 trevor Exp $
+# $Id:$
 #
 # == Description
 # 
@@ -115,26 +115,35 @@ class Blast
       end
     end
 
-    def xmlparser_parse_parameters(hash)
-      labels = { 
-        'matrix'       => 'Parameters_matrix',
-        'expect'       => 'Parameters_expect',
-        'include'      => 'Parameters_include',
-        'sc-match'     => 'Parameters_sc-match',
-        'sc-mismatch'  => 'Parameters_sc-mismatch',
-        'gap-open'     => 'Parameters_gap-open',
-        'gap-extend'   => 'Parameters_gap-extend',
-        'filter'       => 'Parameters_filter',
-        'pattern'      => 'Parameters_pattern',
-        'entrez-query' => 'Parameters_entrez-query',
-      }
-      labels.each do |k,v|
+    # set parameter of the key as val
+    def xml_set_parameter(key, val)
+      #labels = { 
+      #  'matrix'       => 'Parameters_matrix',
+      #  'expect'       => 'Parameters_expect',
+      #  'include'      => 'Parameters_include',
+      #  'sc-match'     => 'Parameters_sc-match',
+      #  'sc-mismatch'  => 'Parameters_sc-mismatch',
+      #  'gap-open'     => 'Parameters_gap-open',
+      #  'gap-extend'   => 'Parameters_gap-extend',
+      #  'filter'       => 'Parameters_filter',
+      #  'pattern'      => 'Parameters_pattern',
+      #  'entrez-query' => 'Parameters_entrez-query',
+      #}
+      k = key.sub(/\AParameters\_/, '')
+      @parameters[k] =
         case k
-        when 'filter', 'matrix'
-          @parameters[k] = hash[v].to_s
+        when 'expect', 'include'
+          val.to_f
+        when /\Agap\-/, /\Asc\-/
+          val.to_i
         else
-          @parameters[k] = hash[v].to_i
+          val
         end
+    end
+
+    def xmlparser_parse_parameters(hash)
+      hash.each do |k, v|
+        xml_set_parameter(k, v)
       end
     end
 
@@ -144,6 +153,14 @@ class Blast
         @iterations.last.num = hash[tag].to_i
       when 'Iteration_message'
         @iterations.last.message = hash[tag].to_s
+
+        # for new BLAST XML format
+      when 'Iteration_query-ID'
+        @iterations.last.query_id = hash[tag].to_s
+      when 'Iteration_query-def'
+        @iterations.last.query_def = hash[tag].to_s
+      when 'Iteration_query-len'
+        @iterations.last.query_len = hash[tag].to_i
       end
     end
 

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

@@ -1,10 +1,10 @@
 #
 # = bio/appl/blat/report.rb - BLAT result parser
 #
-# Copyright:: Copyright (C) 2004 GOTO Naohisa <ng@bioruby.org>
+# Copyright:: Copyright (C) 2004, 2006, 2008 Naohisa Goto <ng@bioruby.org>
 # License:: The Ruby License
 #
-#  $Id: report.rb,v 1.13 2007/04/05 23:35:39 trevor Exp $
+#  $Id:$
 #
 # BLAT result parser (psl / pslx format).
 #
@@ -46,15 +46,18 @@ module Bio
       # In Bio::Blat::Report, it it nil (1 entry 1 file).
       DELIMITER = RS = nil # 1 file 1 entry
 
+      # Splitter for Bio::FlatFile
+      FLATFILE_SPLITTER = Bio::FlatFile::Splitter::LineOriented
+
       # Creates a new Bio::Blat::Report object from BLAT result text (String).
       # You can use Bio::FlatFile to read a file.
       # Currently, results created with options -out=psl (default) or
       # -out=pslx are supported.
-      def initialize(text)
+      def initialize(text = '')
         flag = false
         head = []
         @hits = []
-        text.each do |line|
+        text.each_line do |line|
           if flag then
             @hits << Hit.new(line)
           else
@@ -71,7 +74,45 @@ module Bio
             end
           end
         end
-        @columns = parse_header(head)
+        @columns = parse_header(head) unless head.empty?
+      end
+
+      # Adds a header line if the header data is not yet given and
+      # the given line is suitable for header.
+      # Returns self if adding header line is succeeded.
+      # Otherwise, returns false (the line is not added).
+      def add_header_line(line)
+        return false if defined? @columns
+        line = line.chomp
+        case line
+        when /^\d/
+          @columns = (defined? @header_lines) ? parse_header(@header_lines) : []
+          return false
+        when /\A\-+\s*\z/
+          @columns = (defined? @header_lines) ? parse_header(@header_lines) : []
+          return self
+        else
+          @header_lines ||= []
+          @header_lines.push line
+        end
+      end
+
+      # Adds a line to the entry if the given line is regarded as
+      # a part of the current entry.
+      # If the current entry (self) is empty, or the line has the same
+      # query name, the line is added and returns self.
+      # Otherwise, returns false (the line is not added).
+      def add_line(line)
+        if /\A\s*\z/ =~ line then
+          return @hits.empty? ? self : false
+        end
+        hit = Hit.new(line.chomp)
+        if @hits.empty? or @hits.first.query.name == hit.query.name then
+          @hits.push hit
+          return self
+        else
+          return false
+        end
       end
 
       # hits of the result.

data/lib/bio/appl/emboss.rb

@@ -5,7 +5,7 @@
 # Copyright::  Copyright (C) 2006       Jan Aerts <jan.aerts@bbsrc.ac.uk>
 # License::    The Ruby License
 #
-# $Id: emboss.rb,v 1.8 2007/04/05 23:35:39 trevor Exp $
+# $Id: emboss.rb,v 1.9 2008/01/10 03:51:06 ngoto Exp $
 #
 
 module Bio
@@ -35,22 +35,34 @@ module 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 Bio::EMBOSS object
-#  # by creating a new Bio::EMBOSS object and subsequently executing it.
-#  xlrhodop = Bio::EMBOSS.new('seqret embl:xlrhodop')
-#  puts xlrhodop.exec
+#  # 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.new('seqret embl:xlrhodop').exec
+#  puts Bio::EMBOSS.run('seqret', 'embl:xlrhodop')
 #
 #  # Similarly:
-#  puts Bio::EMBOSS.new('transeq -sbegin 110 -send 1171 embl:xlrhodop')
-#  puts Bio::EMBOSS.new('showfeat embl:xlrhodop').exec
-#  puts Bio::EMBOSS.new('seqret embl:xlrhodop -osformat acedb').exec
+#  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
 #
@@ -76,8 +88,8 @@ class EMBOSS
   #  puts object.exec
   # ---
   # *Arguments*:
-  # * (required) _command_: emboss command
-  # *Returns*:: Bio::EMBOSS object
+  # * (required) _arg_: argument given to the emboss seqret command
+  # *Returns*:: String
   def self.seqret(arg)
     str = self.retrieve('seqret', arg)
   end
@@ -92,12 +104,16 @@ class EMBOSS
   #  puts object.exec
   # ---
   # *Arguments*:
-  # * (required) _command_: emboss command
-  # *Returns*:: Bio::EMBOSS object
+  # * (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.
@@ -114,6 +130,7 @@ class EMBOSS
   # * (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
 
@@ -142,6 +159,38 @@ class EMBOSS
   # 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)

data/lib/bio/appl/fasta.rb

@@ -4,11 +4,11 @@
 # Copyright::  Copyright (C) 2001, 2002 Toshiaki Katayama <k@bioruby.org>
 # License::    The Ruby License
 #
-# $Id: fasta.rb,v 1.25 2007/05/18 15:22:52 k Exp $
+# $Id:$
 #
 
 require 'net/http'
-require 'cgi' unless defined?(CGI)
+require 'uri'
 require 'bio/command'
 require 'shellwords'
 
@@ -154,16 +154,14 @@ class Fasta
       'style'        => 'raw',
       'prog'         => @program,
       'dbname'       => @db,
-      'sequence'     => CGI.escape(query),
-      'other_param'  => CGI.escape(Bio::Command.make_command_line_unix(@options)),
+      'sequence'     => query,
+      'other_param'  => Bio::Command.make_command_line_unix(@options),
       'ktup_value'   => @ktup,
       'matrix'       => @matrix,
     }
 
-    data = []
-
-    form.each do |k, v|
-      data.push("#{k}=#{v}") if v
+    form.keys.each do |k|
+      form.delete(k) unless form[k]
     end
 
     report = nil
@@ -172,7 +170,7 @@ class Fasta
       http = Bio::Command.new_http(host)
       http.open_timeout = 3000
       http.read_timeout = 6000
-      result, = http.post(path, data.join('&'))
+      result = Bio::Command.http_post_form(http, path, form)
       # workaround 2006.8.1 - fixed for new batch queuing system
       case result.code
       when "302"
@@ -191,9 +189,9 @@ class Fasta
       end
       @output = result.body.to_s
       # workaround 2005.08.12
-      re = %r{<A HREF="http://#{host}(/tmp/[^"]+)">Show all result</A>} # "
+      re = %r{<A HREF="http://#{host}(/tmp/[^"]+)">Show all result</A>}i # "
       if path = @output[re, 1]
-        result, = http.get(path)
+        result = http.get(path)
         @output = result.body
         txt = @output.to_s.split(/\<pre\>/)[1]
         raise 'cannot understand response' unless txt

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

@@ -5,7 +5,7 @@
 #              Mitsuteru C. Nakao <n@bioruby.org>
 # License::    The Ruby License
 #
-#  $Id: report.rb,v 1.10 2007/04/05 23:35:39 trevor Exp $
+#  $Id:$
 #
 # == Description
 #
@@ -75,7 +75,7 @@ class Genscan
       @isochore   = nil
       @matrix     = nil
 
-      report.each("\n") do |line|
+      report.each_line("\n") do |line|
         case line
         when /^GENSCAN/
           parse_headline(line)
@@ -94,7 +94,7 @@ class Genscan
 
       # genes/exons
       genes_region = report[i...j]
-      genes_region.each("\n") do |line|
+      genes_region.each_line("\n") do |line|
         if /Init|Intr|Term|PlyA|Prom|Sngl/ =~ line
           gn, en = line.strip.split(" +")[0].split(/\./).map {|i| i.to_i }
           add_exon(gn, en, line)

data/lib/bio/appl/hmmer.rb

@@ -64,7 +64,7 @@ class HMMER
     @output  = ''
     
     begin
-      @options = opt.to_ary
+      @options = options.to_ary
     rescue NameError #NoMethodError
       # backward compatibility
       @options = Shellwords.shellwords(options)

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

@@ -7,7 +7,7 @@
 #               Masashi Fujita <fujita@kuicr.kyoto-u.ac.jp>
 # License::     The Ruby License
 #
-# $Id: report.rb,v 1.13 2007/04/05 23:35:40 trevor Exp $
+# $Id:$
 #
 # == Description
 #
@@ -61,7 +61,7 @@ class HMMER
   #
   def self.reports(multiple_report_text)
     ary = []
-    multiple_report_text.each("\n//\n") do |report|
+    multiple_report_text.each_line("\n//\n") do |report|
       if block_given?
         yield Report.new(report)
       else
@@ -267,7 +267,7 @@ class HMMER
       program['license'] = program_data.split(/\n/)
       
       parameter = {}
-      parameter_data.each do |x|
+      parameter_data.each_line do |x|
         if /^(.+?):\s+(.*?)\s*$/ =~ x
           parameter[$1] = $2
         end
@@ -281,7 +281,7 @@ class HMMER
     # Bio::HMMER::Report#parse_query_info
     def parse_query_info(data)
       hash = {}
-      data.each do |x|
+      data.each_line do |x|
         if /^(.+?):\s+(.*?)\s*$/ =~ x
           hash[$1] = $2
         elsif /\s+\[(.+)\]/ =~ x
@@ -298,7 +298,7 @@ class HMMER
       data.sub!(/.+?---\n/m, '').chop!
       hits = []
       return hits if data == "\t[no hits above thresholds]\n"
-      data.each do |l|
+      data.each_line do |l|
         hits.push(Hit.new(l))
       end
       hits
@@ -311,7 +311,7 @@ class HMMER
       data.sub!(/.+?---\n/m, '').chop!
       hsps=[]
       return hsps if data == "\t[no hits above thresholds]\n"
-      data.each do |l|
+      data.each_line do |l|
         hsps.push(Hsp.new(l, is_hmmsearch))
       end
       return hsps
@@ -326,19 +326,19 @@ class HMMER
 
       statistical_detail = {}
       data.sub!(/(.+?)\n\n/m, '')
-      $1.each do |l|
+      $1.each_line do |l|
         statistical_detail[$1] = $2.to_f if /^\s*(.+?)\s*=\s*(\S+)/ =~ l
       end
         
       total_seq_searched = nil
       data.sub!(/(.+?)\n\n/m, '')
-      $1.each do |l|
+      $1.each_line do |l|
         total_seq_searched = $2.to_i if /^\s*(.+)\s*:\s*(\S+)/ =~ l
       end
         
       whole_seq_top_hits = {}
       data.sub!(/(.+?)\n\n/m, '')
-      $1.each do |l|
+      $1.each_line do |l|
         if /^\s*(.+?):\s*(\d+)\s*$/ =~ l
           whole_seq_top_hits[$1] = $2.to_i
         elsif /^\s*(.+?):\s*(\S+)\s*$/ =~ l
@@ -347,7 +347,7 @@ class HMMER
       end
         
       domain_top_hits = {}
-      data.each do |l|
+      data.each_line do |l|
         if /^\s*(.+?):\s*(\d+)\s*$/ =~ l
           domain_top_hits[$1] = $2.to_i
         elsif /^\s*(.+?):\s*(\S+)\s*$/ =~ l