bio 1.4.0 → 1.4.1

data/lib/bio/command.rb

@@ -1,7 +1,7 @@
 #
 # = bio/command.rb - general methods for external command execution
 #
-# Copyright::	Copyright (C) 2003-2008
+# Copyright::	Copyright (C) 2003-2010
 # 		Naohisa Goto <ng@bioruby.org>,
 #		Toshiaki Katayama <k@bioruby.org>
 # License::	The Ruby License
@@ -34,6 +34,59 @@ module Command
 
   module_function
 
+  # *CAUTION* Bio::Command INTERNAL USE ONLY.
+  # Users must NOT use the method.
+  # The method will be removed when it is not needed.
+  #
+  # Checks if the program is running on Microsoft Windows.
+  # If Windows, returns true. Otherwise, returns false.
+  # Note that Cygwin is not treated as Windows.
+  #
+  # Known issues:
+  # * It might make a mistake in minor platforms/architectures/interpreters.
+  # * When running JRuby on Cygwin, the result is unknown.
+  # ---
+  # *Returns*:: true or false
+  def windows_platform?
+    case RUBY_PLATFORM
+    when /(?:mswin|bccwin|mingw)(?:32|64)/i
+      true
+    when /java/i
+      # Reference: Redmine's platform.rb
+      # http://www.redmine.org/projects/redmine/repository/revisions/1753/entry/trunk/lib/redmine/platform.rb
+      if /windows/i =~ (ENV['OS'] || ENV['os']).to_s then
+        true
+      else
+        false
+      end
+    else
+      false
+    end
+  end
+  private_class_method :windows_platform?
+
+  # *CAUTION* Bio::Command INTERNAL USE ONLY.
+  # Users must NOT use the method.
+  # The method will be removed when it is not needed.
+  #
+  # Checks if the OS does not support fork(2) system call.
+  # When not supported, it returns true.
+  # When supported or unknown, it returns false or nil.
+  #
+  # Known issues:
+  # * It might make a mistake in minor platforms/architectures/interpreters.
+  # ---
+  # *Returns*:: true, false or nil.
+  def no_fork?
+    if (defined?(@@no_fork) && @@no_fork) or
+        windows_platform? or /java/i =~ RUBY_PLATFORM then
+      true
+    else
+      false
+    end
+  end
+  private_class_method :no_fork?
+
   # Escape special characters in command line string for cmd.exe on Windows.
   # ---
   # *Arguments*:
@@ -66,8 +119,7 @@ module Command
   # * (required) _str_: String
   # *Returns*:: String object
   def escape_shell(str)
-    case RUBY_PLATFORM
-    when /mswin32|bccwin32/
+    if windows_platform? then
       escape_shell_windows(str)
     else
       escape_shell_unix(str)
@@ -80,8 +132,7 @@ module Command
   # * (required) _ary_: Array containing String objects
   # *Returns*:: String object
   def make_command_line(ary)
-    case RUBY_PLATFORM
-    when /mswin32|bccwin32/
+    if windows_platform? then
       make_command_line_windows(ary)
     else
       make_command_line_unix(ary)
@@ -130,8 +181,8 @@ module Command
     [ arg0 ]
   end
 
-  # Executes the program.  Automatically select popen for Windows
-  # environment and fork for the others.
+  # Executes the program. Automatically select popen for Ruby 1.9 or
+  # Windows environment and fork for the others.
   # A block must be given. An IO object is passed to the block.
   #
   # Available options:
@@ -143,27 +194,62 @@ module Command
   # * (optional) _options_: Hash
   # *Returns*:: (undefined)
   def call_command(cmd, options = {}, &block) #:yields: io
-    case RUBY_PLATFORM
-    when /mswin32|bccwin32/
+    if RUBY_VERSION >= "1.9.0" then
+      return call_command_popen(cmd, options, &block)
+    elsif no_fork? then
       call_command_popen(cmd, options, &block)
     else
-      call_command_fork(cmd, options, &block)
+      begin
+        call_command_fork(cmd, options, &block)
+      rescue NotImplementedError
+        # fork(2) not implemented
+        @@no_fork = true
+        call_command_popen(cmd, options, &block)
+      end
     end
   end
 
+  # This method is internally called from the call_command method.
+  # In normal case, use call_command, and do not call this method directly.
+  #
   # Executes the program via IO.popen for OS which doesn't support fork.
   # A block must be given. An IO object is passed to the block.
+  #
+  # See the document of call_command for available options.
+  #
+  # Note for Ruby 1.8:
+  # In Ruby 1.8, although shell unsafe characters are escaped.
+  # If inescapable characters exists, it raises RuntimeError.
+  # So, call_command_fork is normally recommended.
+  #
+  # Note for Ruby 1.9:
+  # In Ruby 1.9, call_command_popen is safe and robust enough, and is the
+  # recommended way, because IO.popen is improved to get a command-line
+  # as an array without calling shell.
+  #
   # ---
   # *Arguments*:
   # * (required) _cmd_: Array containing String objects
   # * (optional) _options_: Hash
   # *Returns*:: (undefined)
   def call_command_popen(cmd, options = {})
+    if RUBY_VERSION >= "1.9.0" then
+      # For Ruby 1.9 or later, using command line array with options.
+      dir = options[:chdir]
+      cmd = safe_command_line_array(cmd)
+      if dir then
+        cmd = cmd + [ { :chdir => dir } ]
+      end
+      r = IO.popen(cmd, "r+") do |io|
+        yield io
+      end
+      return r
+    end
+    # For Ruby 1.8, using command line string.
     str = make_command_line(cmd)
     # processing options
     if dir = options[:chdir] then
-      case RUBY_PLATFORM
-      when /mswin32|bccwin32/
+      if windows_platform?
         # Unix-like dir separator is changed to Windows dir separator
         # by using String#gsub.
         dirstr = dir.gsub(/\//, "\\")
@@ -182,11 +268,24 @@ module Command
     end
   end
 
+  # This method is internally called from the call_command method.
+  # In normal case, use call_command, and do not call this method directly.
+  #
   # Executes the program via fork (by using IO.popen("-")) and exec.
   # A block must be given. An IO object is passed to the block.
   #
-  # From the view point of security, this method is recommended
-  # rather than call_command_popen.
+  # See the document of call_command for available options.
+  #
+  # Note for Ruby 1.8:
+  # In Ruby 1.8, from the view point of security, this method is recommended
+  # rather than call_command_popen. However, this method might have problems
+  # with multi-threads.
+  #
+  # Note for Ruby 1.9:
+  # In Ruby 1.9, this method can not be used, because Thread.critical is
+  # removed. In Ruby 1.9, call_command_popen is safe and robust enough, and
+  # is the recommended way, because IO.popen is improved to get a
+  # command-line as an array without calling shell.
   #
   # ---
   # *Arguments*:
@@ -196,12 +295,17 @@ module Command
   def call_command_fork(cmd, options = {})
     dir = options[:chdir]
     cmd = safe_command_line_array(cmd)
+    begin
+    tc, Thread.critical, flag0, flag1 = Thread.critical, true, true, true
     IO.popen("-", "r+") do |io|
       if io then
         # parent
+        flag0, Thread.critical, flag1 = false, tc, false
         yield io
       else
         # child
+        Thread.critical = true # for safety, though already true
+        GC.disable
         # chdir to options[:chdir] if available
         begin
           Dir.chdir(dir) if dir
@@ -218,6 +322,11 @@ module Command
         Process.exit!(1)
       end
     end
+    ensure
+      # When IO.popen("-") raises error, Thread.critical will be set here.
+      Thread.critical = tc if flag0 or flag1
+      #warn 'Thread.critical might have wrong value.' if flag0 != flag1
+    end
   end
 
   # Executes the program via Open3.popen3
@@ -240,7 +349,8 @@ module Command
   # waits the program termination, and returns the output data printed to the
   # standard output as a string.
   # 
-  # Automatically select popen for Windows environment and fork for the others.
+  # Automatically select popen for Ruby 1.9 or Windows environment and
+  # fork for the others.
   #
   # Available options:
   #   :chdir => "path" : changes working directory to the specified path.
@@ -252,19 +362,32 @@ module Command
   # * (optional) _options_: Hash
   # *Returns*:: String or nil
   def query_command(cmd, query = nil, options = {})
-    case RUBY_PLATFORM
-    when /mswin32|bccwin32/
+    if RUBY_VERSION >= "1.9.0" then
+      return query_command_popen(cmd, query, options)
+    elsif no_fork? then
       query_command_popen(cmd, query, options)
     else
-      query_command_fork(cmd, query, options)
+      begin
+        query_command_fork(cmd, query, options)
+      rescue NotImplementedError
+        # fork(2) not implemented
+        @@no_fork = true
+        query_command_fork(cmd, query, options)
+      end
     end
   end
 
+  # This method is internally called from the query_command method.
+  # In normal case, use query_command, and do not call this method directly.
+  #
   # Executes the program with the query (String) given to the standard input,
   # waits the program termination, and returns the output data printed to the
   # standard output as a string.
   #
-  # IO.popen is used for OS which doesn't support fork.
+  # See the document of query_command for available options.
+  #
+  # See the document of call_command_popen for the security and Ruby
+  # version specific issues.
   #
   # ---
   # *Arguments*:
@@ -283,14 +406,19 @@ module Command
     ret
   end
 
+  # This method is internally called from the query_command method.
+  # In normal case, use query_command, and do not call this method directly.
+  #
   # Executes the program with the query (String) given to the standard input,
   # waits the program termination, and returns the output data printed to the
   # standard output as a string.
   #
   # Fork (by using IO.popen("-")) and exec is used to execute the program.
   #
-  # From the view point of security, this method is recommended
-  # rather than query_command_popen.
+  # See the document of query_command for available options.
+  #
+  # See the document of call_command_fork for the security and Ruby
+  # version specific issues.
   #
   # ---
   # *Arguments*:

data/lib/bio/db/aaindex.rb

@@ -254,7 +254,17 @@ module Bio
         label_data.each_line do |line|
           ma << line.strip.split(/\s+/).map {|x| x.to_f }
         end
-        @data['matrix'] = Matrix[*ma]
+        ma_len = ma.size
+        ma.each do |row|
+          row_size = row.size
+          if row_size < ma_len
+            (row_size..ma_len-1).each do |i|
+              row[i] = ma[i][row_size-1]
+            end
+          end
+        end
+        mat = Matrix[*ma]
+        @data['matrix'] = mat
       end
     end
 

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

@@ -188,7 +188,7 @@ class SPTR < EMBLDB
   def gn
     unless @data['GN']
       case fetch('GN')
-      when /Name=/,/ORFNames=/
+      when /Name=/,/ORFNames=/,/OrderedLocusNames=/,/Synonyms=/
         @data['GN'] = gn_uniprot_parser
       else
         @data['GN'] = gn_old_parser

data/lib/bio/db/fasta/defline.rb

@@ -126,10 +126,14 @@ module Bio
   #   http://www.ncbi.nlm.nih.gov/BLAST/fasta.shtml
   #
   # * Frequently Asked Questions:  Indexing of Sequence Identifiers (by Warren R. Gish.)
+  #   (Dead link. Please find in http://web.archive.org/ ).
   #   http://blast.wustl.edu/doc/FAQ-Indexing.html#Identifiers
   #
-  # * README.formatdb
-  #   ftp://ftp.ncbi.nih.gov/blast/documents/README.formatdb
+  # * Program Parameters for formatdb and fastacmd (by Tao Tao)
+  #   http://www.ncbi.nlm.nih.gov/staff/tao/URLAPI/formatdb_fastacmd.html#t1.1
+  #
+  # * Formatdb README
+  #   ftp://ftp.ncbi.nih.gov/blast/documents/formatdb.html
   # 
   class FastaDefline
 
@@ -140,6 +144,7 @@ module Bio
       'emb' => [ 'acc_version', 'locus' ],      # EMBL
       'dbj' => [ 'acc_version', 'locus' ],      # DDBJ
       'sp'  => [ 'accession', 'entry_id' ],   # SWISS-PROT
+      'tr'  => [ 'accession', 'entry_id' ],   # TREMBL
       'pdb' => [ 'entry_id', 'chain' ],       # PDB
       'bbs' => [ 'number' ],                  # GenInfo Backbone Id
       'gnl' => [ 'database' , 'entry_id' ],   # General database identifier

data/lib/bio/db/fasta/qual.rb

@@ -95,6 +95,30 @@ module Bio
       data[n]
     end
 
+    # Returns the data as a Bio::Sequence object.
+    # In the returned sequence object, the length of the sequence is zero,
+    # and the numeric data is stored to the Bio::Sequence#quality_scores
+    # attirbute.
+    #
+    # Because the meaning of the numeric data is unclear,
+    # Bio::Sequence#quality_score_type is not set by default.
+    #
+    # Note: If you modify the returned Bio::Sequence object,
+    # the sequence or definition in this FastaNumericFormat object
+    # might also be changed (but not always be changed)
+    # because of efficiency.
+    # 
+    # ---
+    # *Arguments*:
+    # *Returns*:: (Bio::Sequence) sequence object
+    def to_biosequence
+      s = Bio::Sequence.adapter(self,
+                                Bio::Sequence::Adapter::FastaNumericFormat)
+      s.seq = Bio::Sequence::Generic.new('')
+      s
+    end
+    alias to_seq to_biosequence
+
     undef query, blast, fasta, seq, naseq, nalen, aaseq, aalen
 
   end #class FastaNumericFormat

data/lib/bio/db/fasta/qual_to_biosequence.rb

@@ -0,0 +1,29 @@
+#
+# = bio/db/fasta/qual_to_biosequence.rb - Bio::FastaNumericFormat to Bio::Sequence adapter module
+#
+# Copyright::   Copyright (C) 2010
+#               Naohisa Goto <ng@bioruby.org>
+# License::     The Ruby License
+#
+
+require 'bio/sequence'
+require 'bio/sequence/adapter'
+require 'bio/db/fasta/fasta_to_biosequence'
+
+# Internal use only. Normal users should not use this module.
+#
+# Bio::FastaNumericFormat to Bio::Sequence adapter module.
+# It is internally used in Bio::FastaNumericFormat#to_biosequence.
+#
+module Bio::Sequence::Adapter::FastaNumericFormat
+
+  extend Bio::Sequence::Adapter
+
+  include Bio::Sequence::Adapter::FastaFormat
+
+  private
+
+  def_biosequence_adapter :quality_scores, :data
+
+end #module Bio::Sequence::Adapter::FastaNumericFormat
+

data/lib/bio/db/fastq.rb

@@ -640,6 +640,21 @@ class Fastq
     Bio::Sequence.adapter(self, Bio::Sequence::Adapter::Fastq)
   end
 
+  # Masks low quality sequence regions.
+  # For each sequence position, if the quality score is smaller than
+  # the threshold, the sequence in the position is replaced with
+  # <em>mask_char</em>.
+  #
+  # Note: This method does not care quality_score_type.
+  # ---
+  # *Arguments*:
+  # * (required) <em>threshold</em> : (Numeric) threshold
+  # * (optional) <em>mask_char</em> : (String) character used for masking
+  # *Returns*:: Bio::Sequence object
+  def mask(threshold, mask_char = 'n')
+    to_biosequence.mask_with_quality_score(threshold, mask_char)
+  end
+
 end #class Fastq
 
 end #module Bio

data/lib/bio/db/go.rb

@@ -293,8 +293,8 @@ class GO
 
     # Bio::GO::GeneAssociation#to_str -> a line of gene_association file.
     def to_str
-      return [@db, @db_object_id, @db_object_symbol, @quialifier, @goid, 
-              @qualifier.join("|"), @evidence, @with.join("|"), @aspect,
+      return [@db, @db_object_id, @db_object_symbol, @qualifier, @goid, 
+              @db_reference.join("|"), @evidence, @with.join("|"), @aspect,
               @db_object_name, @db_object_synonym.join("|"), @db_object_type,
               @taxon, @date, @assigned_by].join("\t")
     end

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

@@ -1,7 +1,7 @@
 #
 # = bio/db/kegg/common.rb - Common methods for KEGG database classes
 #
-# Copyright::  Copyright (C) 2003-2007 Toshiaki Katayama <k@bioruby.org>
+# Copyright::  Copyright (C) 2001-2007 Toshiaki Katayama <k@bioruby.org>
 # Copyright::  Copyright (C) 2003 Masumi Itoh <m@bioruby.org>
 # Copyright::  Copyright (C) 2009 Kozo Nishida <kozo-ni@is.naist.jp>
 # License::    The Ruby License
@@ -23,6 +23,69 @@ class KEGG
   # Namespace for methods commonly used in the Bio::KEGG::* classes.
   module Common
 
+    # The module provides references method.
+    module References
+      # REFERENCE -- Returns contents of the REFERENCE records as an Array of
+      # Bio::Reference objects.
+      def references
+        unless @data['REFERENCE']
+          ary = []
+          toptag2array(get('REFERENCE')).each do |ref|
+            hash = Hash.new
+            subtag2array(ref).each do |field|
+              case tag_get(field)
+              when /REFERENCE/
+                cmnt = tag_cut(field).chomp
+                if /^\s*PMID\:(\d+)\s*/ =~ cmnt then
+                  hash['pubmed'] = $1
+                  cmnt = $'
+                end
+                if cmnt and !cmnt.empty? then
+                  hash['comments'] ||= []
+                  hash['comments'].push(cmnt)
+                end
+              when /AUTHORS/
+                authors = truncate(tag_cut(field))
+                authors = authors.split(/\, /)
+                authors[-1] = authors[-1].split(/\s+and\s+/) if authors[-1]
+                authors = authors.flatten.map { |a| a.sub(',', ', ') }
+                hash['authors']	= authors
+              when /TITLE/
+                hash['title']	= truncate(tag_cut(field))
+              when /JOURNAL/
+                journal = truncate(tag_cut(field))
+                case journal
+                  # KEGG style
+                when /(.*) (\d*(?:\([^\)]+\))?)\:(\d+\-\d+) \((\d+)\)$/
+                  hash['journal'] = $1
+                  hash['volume']  = $2
+                  hash['pages']   = $3
+                  hash['year']    = $4
+                  # old KEGG style
+                when /(.*) (\d+):(\d+\-\d+) \((\d+)\) \[UI:(\d+)\]$/
+                  hash['journal'] = $1
+                  hash['volume']  = $2
+                  hash['pages']   = $3
+                  hash['year']    = $4
+                  hash['medline'] = $5
+                  # Only journal name and year are available
+                when /(.*) \((\d+)\)$/
+                  hash['journal'] = $1
+                  hash['year']    = $2
+                else
+                  hash['journal'] = journal
+                end
+              end
+            end
+            ary.push(Reference.new(hash))
+          end
+          @data['REFERENCE'] = ary #.extend(Bio::References::BackwardCompatibility)
+
+        end
+        @data['REFERENCE']
+      end
+    end #module References
+
     # The module providing dblinks_as_hash methods.
     #
     # Bio::KEGG::* internal use only.
@@ -54,7 +117,8 @@ class KEGG
         unless defined? @pathways_as_hash then
           hash = {}
           pathways_as_strings.each do |line|
-            sign, entry_id, name = line.split(/\s+/, 3)
+            line = line.sub(/\APATH\:\s+/, '')
+            entry_id, name = line.split(/\s+/, 2)
             hash[entry_id] = name
           end
           @pathways_as_hash = hash
@@ -72,9 +136,9 @@ class KEGG
       def orthologs_as_hash
         unless defined? @orthologs_as_hash
           kos = {}
-          orthologs_as_strings.each do |ko|
-            entry = ko.scan(/K[0-9]{5}/)[0]
-            sign, entry_id, definition = ko.split(/\s+/, 3)
+          orthologs_as_strings.each do |line|
+            ko = line.sub(/\AKO\:\s+/, '')
+            entry_id, definition = ko.split(/\s+/, 2)
             kos[entry_id] = definition
           end
           @orthologs_as_hash = kos
@@ -106,6 +170,46 @@ class KEGG
       end
     end #module GenesAsHash
 
+    # This module provides modules_as_hash method.
+    #
+    # Bio::KEGG::* internal use only.
+    module ModulesAsHash
+      # Returns MODULE field as a Hash.
+      # Each key of the hash is KEGG MODULE ID,
+      # and each value is the name of the Pathway Module.
+      # ---
+      # *Returns*:: Hash
+      def modules_as_hash
+        unless defined? @modules_s_as_hash then
+          hash = {}
+          modules_as_strings.each do |line|
+            entry_id, name = line.split(/\s+/, 2)
+            hash[entry_id] = name
+          end
+          @modules_as_hash = hash
+        end
+        @modules_as_hash
+      end
+    end #module ModulesAsHash
+
+    # This module provides strings_as_hash private method.
+    #
+    # Bio::KEGG::* internal use only.
+    module StringsAsHash
+      # (Private) Creates a hash from lines.
+      # Each line is consisted of two components, ID and description,
+      # separated with spaces. IDs must be unique with each other.
+      def strings_as_hash(lines)
+        hash = {}
+        lines.each do |line|
+          entry_id, definition = line.split(/\s+/, 2)
+          hash[entry_id] = definition
+        end
+        return hash
+      end
+      private :strings_as_hash
+    end #module StringsAsHash
+
   end #module Common
 end #class KEGG
 end #module Bio