bio 1.3.1 → 1.4.0

data/lib/bio/tree.rb

@@ -261,9 +261,22 @@ module Bio
       @pathway = Bio::Pathway.new([], true)
       @root = nil
       @options = {}
+      _init_cache
       self.concat(tree) if tree
     end
 
+    # (private) clear internal cache
+    def _init_cache
+      @cache_parent = {}
+    end
+    private :_init_cache
+
+    # (private) clear internal cache
+    def _clear_cache
+      @cache_parent.clear
+    end
+    private :_clear_cache
+
     # root node of this tree
     # (even if unrooted tree, it is used by some methods)
     attr_accessor :root
@@ -366,6 +379,7 @@ module Bio
     # Returns the newly added edge.
     # If the edge already exists, it is overwritten with new one.
     def add_edge(source, target, edge = Edge.new)
+      _clear_cache
       @pathway.append(Bio::Relation.new(source, target, edge))
       edge
     end
@@ -387,6 +401,7 @@ module Bio
     # Returns self.
     # If the node already exists, it does nothing.
     def add_node(node)
+      _clear_cache
       @pathway.graph[node] ||= {}
       self
     end
@@ -404,6 +419,7 @@ module Bio
       unless self.include?(node)
         raise IndexError, 'the node does not exist'
       end
+      _clear_cache
       @pathway.relations.delete_if do |rel|
         rel.node.include?(node)
       end
@@ -419,6 +435,7 @@ module Bio
     # Returns self.
     # If the node does not exist, raises IndexError.
     def remove_node(node)
+      #_clear_cache #done in clear_node(node)
       self.clear_node(node)
       @pathway.graph.delete(node)
       self
@@ -428,6 +445,7 @@ module Bio
     # All edges connected with the removed nodes are also removed.
     # Returns self.
     def remove_node_if
+      #_clear_cache #done in clear_node(node)
       all = self.nodes
       all.each do |node|
         if yield node then
@@ -449,6 +467,7 @@ module Bio
       unless self.get_edge(source, target) then
         raise IndexError, 'edge not found'
       end
+      _clear_cache
       fwd = [ source, target ]
       rev = [ target, source ]
       @pathway.relations.delete_if do |rel|
@@ -464,6 +483,7 @@ module Bio
     # Removes each edge if the block returns not nil.
     # Returns self.
     def remove_edge_if #:yields: source, target, edge
+      _clear_cache
       removed_rel = []
       @pathway.relations.delete_if do |rel|
         if yield rel.node[0], rel.node[1], edge then
@@ -485,6 +505,7 @@ module Bio
     # Replaces each node by each block's return value.
     # Returns self.
     def collect_node! #:yields: node
+      _clear_cache
       tr = {}
       self.each_node do |node|
         tr[node] = yield node
@@ -505,6 +526,7 @@ module Bio
     # Replaces each edge by each block's return value.
     # Returns self.
     def collect_edge! #:yields: source, target, edge
+      _clear_cache
       @pathway.relations.each do |rel|
         newedge = yield rel.node[0], rel.node[1], rel.relation
         rel.relation = newedge
@@ -573,6 +595,7 @@ module Bio
     # shared in the concatinated tree.
     def concat(other)
       #raise TypeError unless other.kind_of?(self.class)
+      _clear_cache
       other.each_node do |node|
         self.add_node(node)
       end
@@ -591,6 +614,7 @@ module Bio
       raise IndexError, 'node1 not found' unless @pathway.graph[node1]
       raise IndexError, 'node2 not found' unless @pathway.graph[node2]
       return [ node1 ] if node1 == node2
+      return [ node1, node2 ] if @pathway.graph[node1][node2]
       step, path = @pathway.bfs_shortest_path(node1, node2)
       unless path[0] == node1 and path[-1] == node2 then
         raise NoPathError, 'node1 and node2 are not connected'
@@ -622,13 +646,53 @@ module Bio
       distance
     end
 
+    # (private) get parent only by using cache
+    def _get_cached_parent(node, root)
+      @cache_parent[root] ||= Hash.new
+      cache = @cache_parent[root]
+      if node == root then
+        unless cache.has_key?(root) then
+          self.adjacent_nodes(root).each do |n|
+            cache[n] ||= root if n != root
+          end
+          cache[root] = nil
+        end
+        parent = nil
+      else
+        unless parent = cache[node] then
+          parent = self.adjacent_nodes(node).find { |n|
+            (m = cache[n]) && (m != node)
+          }
+          _cache_parent(node, parent, root) if parent
+        end
+        parent
+      end
+    end
+    private :_get_cached_parent
+
+    # (private) set parent cache
+    def _cache_parent(node, parent, root)
+      return unless parent
+      cache = @cache_parent[root]
+      cache[node] = parent
+      self.adjacent_nodes(node).each do |n|
+        cache[n] ||= node if n != parent
+      end
+    end
+    private :_cache_parent
+
     # Gets the parent node of the _node_.
     # If _root_ isn't specified or _root_ is <code>nil</code>, @root is used.
     # Returns an <code>Node</code> object or nil.
     # The result is unspecified for cyclic trees.
     def parent(node, root = nil)
       root ||= @root
-      self.path(root, node)[-2]
+      raise IndexError, 'can not get parent for unrooted tree' unless root
+      unless ret = _get_cached_parent(node, root) then
+        ret = self.path(root, node)[-2]
+        _cache_parent(node, ret, root)
+      end
+      ret
     end
 
     # Gets the adjacent children nodes of the _node_.
@@ -637,10 +701,9 @@ module Bio
     # The result is unspecified for cyclic trees.
     def children(node, root = nil)
       root ||= @root
-      path = self.path(root, node)
-      result = self.adjacent_nodes(node)
-      result -= path
-      result
+      c = self.adjacent_nodes(node)
+      c.delete(self.parent(node, root))
+      c
     end
 
     # Gets all descendent nodes of the _node_.
@@ -788,6 +851,7 @@ module Bio
     # Returns removed nodes.
     # Note that orphan nodes are still kept unchanged.
     def remove_nonsense_nodes
+      _clear_cache
       hash = {}
       self.each_node do |node|
         hash[node] = true if @pathway.graph[node].size == 2
@@ -828,6 +892,7 @@ module Bio
       unless edge = self.get_edge(node1, node2) then
         raise IndexError, 'nodes not found or two nodes are not adjacent'
       end
+      _clear_cache
       new_edge = Edge.new(new_distance)
       self.remove_edge(node1, node2)
       self.add_edge(node1, new_node, new_edge)

data/lib/bio/util/restriction_enzyme/single_strand.rb

@@ -68,8 +68,9 @@ class SingleStrand < Bio::Sequence::NA
   # *Returns*:: nothing
   def initialize( sequence, *c )
     c.flatten! # if an array was supplied as an argument
-    validate_args(sequence, c)
-    sequence.downcase!
+  # NOTE t| 2009-09-19 commented out for library efficiency
+    # validate_args(sequence, c)
+    sequence = sequence.downcase
     
     if sequence =~ re_cut_symbol
       @cut_locations_in_enzyme_notation = CutLocationsInEnzymeNotation.new( strip_padding(sequence) )

data/lib/bio/util/sirna.rb

@@ -5,7 +5,7 @@
 #               Itoshi NIKAIDO <dritoshi@gmail.com>
 # License::     The Ruby License
 #
-# $Id: sirna.rb,v 1.11 2007/04/05 23:35:41 trevor Exp $
+# $Id:$
 #
 # == Bio::SiRNA - Designing siRNA.
 #
@@ -250,28 +250,6 @@ module Bio
 
 end # module Bio
 
-
-if __FILE__ == $0
-  
-  seq = Bio::Sequence::NA.new(ARGF.read)
-
-  sirna = Bio::SiRNA.new(seq)
-  pairs = sirna.design # or .design('uitei') or .uitei or .reynolds
-
-  pairs.each do |pair|
-    puts pair.report
-
-    shrna = Bio::SiRNA::ShRNA.new(pair)
-    shrna.design # or .design('BLOCK-iT') or .block_it
-    puts shrna.report
-
-    puts "# as DNA"
-    puts shrna.top_strand.dna
-    puts shrna.bottom_strand.dna
-  end
-
-end  
-
 =begin
 
 = ChangeLog

data/lib/bio/version.rb

@@ -10,7 +10,7 @@
 module Bio
 
   # BioRuby version (Array containing Integer)
-  BIORUBY_VERSION = [1, 3, 1].extend(Comparable).freeze
+  BIORUBY_VERSION = [1, 4, 0].extend(Comparable).freeze
 
   # Extra version specifier (String or nil).
   # Existance of the value indicates pre-release version or modified version.

data/sample/demo_aaindex.rb

@@ -0,0 +1,67 @@
+#
+# = sample/demo_aaindex.rb - demonstration of Bio::AAindex1 and AAindex2
+#
+# Copyright::  Copyright (C) 2001 
+#              KAWASHIMA Shuichi <s@bioruby.org>
+# Copyright::  Copyright (C) 2006
+#              Mitsuteru C. Nakao <n@bioruby.org>
+# License::    The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::AAindex1 and Bio::AAindex2.
+#
+# == Requirements
+#
+# Internet connection and/or OBDA (Open Bio Database Access) configuration.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_aaindex.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/db/aaindex.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+
+  puts "### AAindex1 (PRAM900102)"
+  aax1 = Bio::AAindex1.new(Bio::Fetch.query('aaindex', 'PRAM900102', 'raw'))
+  p aax1.entry_id
+  p aax1.definition
+  p aax1.dblinks
+  p aax1.author
+  p aax1.title
+  p aax1.journal
+  p aax1.comment
+  p aax1.correlation_coefficient
+  p aax1.index
+  p aax1
+  puts "### AAindex2 (DAYM780301)"
+  aax2 = Bio::AAindex2.new(Bio::Fetch.query('aaindex', 'DAYM780301', 'raw'))
+  p aax2.entry_id
+  p aax2.definition
+  p aax2.dblinks
+  p aax2.author
+  p aax2.title
+  p aax2.journal
+  p aax1.comment
+  p aax2.rows
+  p aax2.cols
+  p aax2.matrix
+  p aax2.matrix[2,2]
+  p aax2.matrix[2,3]
+  p aax2.matrix[4,3]
+  p aax2.matrix.determinant
+  p aax2.matrix.rank
+  p aax2.matrix.transpose
+  p aax2
+
+#end
+

data/sample/demo_aminoacid.rb

@@ -0,0 +1,101 @@
+#
+# = sample/demo_aminoacid.rb - demonstration of Bio::AminoAcid
+#
+# Copyright::	Copyright (C) 2001, 2005
+#		Toshiaki Katayama <k@bioruby.org>
+# License::	The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::AminoAcid, the class for amino acid data.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_aminoacid.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/data/aa.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+
+  puts "### aa = Bio::AminoAcid.new"
+  aa = Bio::AminoAcid.new
+
+  puts "# Bio::AminoAcid['A']"
+  p Bio::AminoAcid['A']
+  puts "# aa['A']"
+  p aa['A']
+
+  puts "# Bio::AminoAcid.name('A'), Bio::AminoAcid.name('Ala')"
+  p Bio::AminoAcid.name('A'), Bio::AminoAcid.name('Ala')
+  puts "# aa.name('A'), aa.name('Ala')"
+  p aa.name('A'), aa.name('Ala')
+
+  puts "# Bio::AminoAcid.to_1('alanine'), Bio::AminoAcid.one('alanine')"
+  p Bio::AminoAcid.to_1('alanine'), Bio::AminoAcid.one('alanine')
+  puts "# aa.to_1('alanine'), aa.one('alanine')"
+  p aa.to_1('alanine'), aa.one('alanine')
+  puts "# Bio::AminoAcid.to_1('Ala'), Bio::AminoAcid.one('Ala')"
+  p Bio::AminoAcid.to_1('Ala'), Bio::AminoAcid.one('Ala')
+  puts "# aa.to_1('Ala'), aa.one('Ala')"
+  p aa.to_1('Ala'), aa.one('Ala')
+  puts "# Bio::AminoAcid.to_1('A'), Bio::AminoAcid.one('A')"
+  p Bio::AminoAcid.to_1('A'), Bio::AminoAcid.one('A')
+  puts "# aa.to_1('A'), aa.one('A')"
+  p aa.to_1('A'), aa.one('A')
+
+  puts "# Bio::AminoAcid.to_3('alanine'), Bio::AminoAcid.three('alanine')"
+  p Bio::AminoAcid.to_3('alanine'), Bio::AminoAcid.three('alanine')
+  puts "# aa.to_3('alanine'), aa.three('alanine')"
+  p aa.to_3('alanine'), aa.three('alanine')
+  puts "# Bio::AminoAcid.to_3('Ala'), Bio::AminoAcid.three('Ala')"
+  p Bio::AminoAcid.to_3('Ala'), Bio::AminoAcid.three('Ala')
+  puts "# aa.to_3('Ala'), aa.three('Ala')"
+  p aa.to_3('Ala'), aa.three('Ala')
+  puts "# Bio::AminoAcid.to_3('A'), Bio::AminoAcid.three('A')"
+  p Bio::AminoAcid.to_3('A'), Bio::AminoAcid.three('A')
+  puts "# aa.to_3('A'), aa.three('A')"
+  p aa.to_3('A'), aa.three('A')
+
+  puts "# Bio::AminoAcid.one2three('A')"
+  p Bio::AminoAcid.one2three('A')
+  puts "# aa.one2three('A')"
+  p aa.one2three('A')
+
+  puts "# Bio::AminoAcid.three2one('Ala')"
+  p Bio::AminoAcid.three2one('Ala')
+  puts "# aa.three2one('Ala')"
+  p aa.three2one('Ala')
+
+  puts "# Bio::AminoAcid.one2name('A')"
+  p Bio::AminoAcid.one2name('A')
+  puts "# aa.one2name('A')"
+  p aa.one2name('A')
+
+  puts "# Bio::AminoAcid.name2one('alanine')"
+  p Bio::AminoAcid.name2one('alanine')
+  puts "# aa.name2one('alanine')"
+  p aa.name2one('alanine')
+
+  puts "# Bio::AminoAcid.three2name('Ala')"
+  p Bio::AminoAcid.three2name('Ala')
+  puts "# aa.three2name('Ala')"
+  p aa.three2name('Ala')
+
+  puts "# Bio::AminoAcid.name2three('alanine')"
+  p Bio::AminoAcid.name2three('alanine')
+  puts "# aa.name2three('alanine')"
+  p aa.name2three('alanine')
+
+  puts "# Bio::AminoAcid.to_re('BZACDEFGHIKLMNPQRSTVWYU')"
+  p Bio::AminoAcid.to_re('BZACDEFGHIKLMNPQRSTVWYU')
+
+#end
+

data/sample/demo_bl2seq_report.rb

@@ -0,0 +1,220 @@
+#
+# = sample/demo_bl2seq_report.rb - demo of bl2seq (BLAST 2 sequences) parser
+# 
+# Copyright:: Copyright (C) 2005 Naohisa Goto <ng@bioruby.org>
+# License::   The Ruby License
+#
+# == Description
+#
+# Demonstration of Bio::Blast::Bl2seq::Report, bl2seq (BLAST 2 sequences)
+# parser class.
+#
+# == Usage
+#
+# Run this script with specifying filename(s) containing bl2seq result(s).
+#
+#  $ ruby demo_bl2seq_report.rb files...
+#
+# Example usage using test data:
+#
+#  $ ruby -I lib sample/demo_bl2seq_report.rb test/data/bl2seq/cd8a_cd8b_blastp.bl2seq
+#
+# == Development information
+#
+# The code was moved from lib/bio/appl/bl2seq/report.rb
+#
+
+require 'bio'
+
+if ARGV.empty? then
+  puts "Demonstration of bl2seq (BLAST 2 sequences) parser."
+  puts "Usage: #{$0} files..."
+  exit(0)
+end
+
+Bio::FlatFile.open(Bio::Blast::Bl2seq::Report, ARGF) do |ff|
+ff.each do |rep|
+
+  print "# === Bio::Blast::Bl2seq::Report\n"
+  puts
+  #@#print "  rep.program           #=> "; p rep.program
+  #@#print "  rep.version           #=> "; p rep.version
+  #@#print "  rep.reference         #=> "; p rep.reference
+  #@#print "  rep.db                #=> "; p rep.db
+  #print "  rep.query_id          #=> "; p rep.query_id
+  print "  rep.query_def         #=> "; p rep.query_def
+  print "  rep.query_len         #=> "; p rep.query_len
+  #puts
+  #@#print "  rep.version_number    #=> "; p rep.version_number
+  #@#print "  rep.version_date      #=> "; p rep.version_date
+  puts
+
+  print "# === Parameters\n"
+  #puts
+  #print "  rep.parameters        #=> "; p rep.parameters
+  puts
+  print "  rep.matrix            #=> "; p rep.matrix
+  print "  rep.expect            #=> "; p rep.expect
+  #print "  rep.inclusion         #=> "; p rep.inclusion
+  print "  rep.sc_match          #=> "; p rep.sc_match
+  print "  rep.sc_mismatch       #=> "; p rep.sc_mismatch
+  print "  rep.gap_open          #=> "; p rep.gap_open
+  print "  rep.gap_extend        #=> "; p rep.gap_extend
+  #print "  rep.filter            #=> "; p rep.filter
+  #@#print "  rep.pattern           #=> "; p rep.pattern
+  #print "  rep.entrez_query      #=> "; p rep.entrez_query
+  #puts
+  #@#print "  rep.pattern_positions  #=> "; p rep.pattern_positions
+  puts
+
+  print "# === Statistics (last iteration's)\n"
+  #puts
+  #print "  rep.statistics        #=> "; p rep.statistics
+  puts
+  print "  rep.db_num            #=> "; p rep.db_num
+  print "  rep.db_len            #=> "; p rep.db_len
+  #print "  rep.hsp_len           #=> "; p rep.hsp_len
+  print "  rep.eff_space         #=> "; p rep.eff_space
+  print "  rep.kappa             #=> "; p rep.kappa
+  print "  rep.lambda            #=> "; p rep.lambda
+  print "  rep.entropy           #=> "; p rep.entropy
+  puts
+  print "  rep.num_hits          #=> "; p rep.num_hits
+  print "  rep.gapped_kappa      #=> "; p rep.gapped_kappa
+  print "  rep.gapped_lambda     #=> "; p rep.gapped_lambda
+  print "  rep.gapped_entropy    #=> "; p rep.gapped_entropy
+  print "  rep.posted_date       #=> "; p rep.posted_date
+  puts
+
+  #@#print "# === Message (last iteration's)\n"
+  #@#puts
+  #@#print "  rep.message           #=> "; p rep.message
+  #puts
+  #@#print "  rep.converged?        #=> "; p rep.converged?
+  #@#puts
+
+  print "# === Iterations\n"
+  puts
+  print "  rep.itrerations.each do |itr|\n"
+  puts
+
+  rep.iterations.each do |itr|
+      
+  print "# --- Bio::Blast::Bl2seq::Report::Iteration\n"
+  puts
+
+  print "    itr.num             #=> "; p itr.num
+  #print "    itr.statistics      #=> "; p itr.statistics
+  #@#print "    itr.message         #=> "; p itr.message
+  print "    itr.hits.size       #=> "; p itr.hits.size
+  #puts
+  #@#print "    itr.hits_newly_found.size    #=> "; p itr.hits_newly_found.size;
+  #@#print "    itr.hits_found_again.size    #=> "; p itr.hits_found_again.size;
+  #@#if itr.hits_for_pattern then
+  #@#itr.hits_for_pattern.each_with_index do |hp, hpi|
+  #@#print "    itr.hits_for_pattern[#{hpi}].size #=> "; p hp.size;
+  #@#end
+  #@#end
+  #@#print "    itr.converged?      #=> "; p itr.converged?
+  puts
+
+  print "    itr.hits.each do |hit|\n"
+  puts
+
+  itr.hits.each_with_index do |hit, i|
+
+  print "# --- Bio::Blast::Bl2seq::Default::Report::Hit"
+  print " ([#{i}])\n"
+  puts
+
+  #print "      hit.num           #=> "; p hit.num
+  #print "      hit.hit_id        #=> "; p hit.hit_id
+  print "      hit.len           #=> "; p hit.len
+  print "      hit.definition    #=> "; p hit.definition
+  #print "      hit.accession     #=> "; p hit.accession
+  #puts
+  print "      hit.found_again?  #=> "; p hit.found_again?
+
+  print "        --- compatible/shortcut ---\n"
+  #print "      hit.query_id      #=> "; p hit.query_id
+  #print "      hit.query_def     #=> "; p hit.query_def
+  #print "      hit.query_len     #=> "; p hit.query_len
+  #print "      hit.target_id     #=> "; p hit.target_id
+  print "      hit.target_def    #=> "; p hit.target_def
+  print "      hit.target_len    #=> "; p hit.target_len
+
+  print "            --- first HSP's values (shortcut) ---\n"
+  print "      hit.evalue        #=> "; p hit.evalue
+  print "      hit.bit_score     #=> "; p hit.bit_score
+  print "      hit.identity      #=> "; p hit.identity
+  #print "      hit.overlap       #=> "; p hit.overlap
+
+  print "      hit.query_seq     #=> "; p hit.query_seq
+  print "      hit.midline       #=> "; p hit.midline
+  print "      hit.target_seq    #=> "; p hit.target_seq
+
+  print "      hit.query_start   #=> "; p hit.query_start
+  print "      hit.query_end     #=> "; p hit.query_end
+  print "      hit.target_start  #=> "; p hit.target_start
+  print "      hit.target_end    #=> "; p hit.target_end
+  print "      hit.lap_at        #=> "; p hit.lap_at
+  print "            --- first HSP's vaules (shortcut) ---\n"
+  print "        --- compatible/shortcut ---\n"
+
+  puts
+  print "      hit.hsps.size     #=> "; p hit.hsps.size
+  if hit.hsps.size == 0 then
+  puts  "          (HSP not found: please see blastall's -b and -v options)"
+  puts
+  else
+
+  puts
+  print "      hit.hsps.each do |hsp|\n"
+  puts
+
+  hit.hsps.each_with_index do |hsp, j|
+
+  print "# --- Bio::Blast::Default::Report::HSP (Bio::Blast::Bl2seq::Report::HSP)"
+  print " ([#{j}])\n"
+  puts
+  #print "        hsp.num         #=> "; p hsp.num
+  print "        hsp.bit_score   #=> "; p hsp.bit_score 
+  print "        hsp.score       #=> "; p hsp.score
+  print "        hsp.evalue      #=> "; p hsp.evalue
+  print "        hsp.identity    #=> "; p hsp.identity
+  print "        hsp.gaps        #=> "; p hsp.gaps
+  print "        hsp.positive    #=> "; p hsp.positive
+  print "        hsp.align_len   #=> "; p hsp.align_len
+  #print "        hsp.density     #=> "; p hsp.density
+
+  print "        hsp.query_frame #=> "; p hsp.query_frame
+  print "        hsp.query_from  #=> "; p hsp.query_from
+  print "        hsp.query_to    #=> "; p hsp.query_to
+
+  print "        hsp.hit_frame   #=> "; p hsp.hit_frame
+  print "        hsp.hit_from    #=> "; p hsp.hit_from
+  print "        hsp.hit_to      #=> "; p hsp.hit_to
+
+  #print "        hsp.pattern_from#=> "; p hsp.pattern_from
+  #print "        hsp.pattern_to  #=> "; p hsp.pattern_to
+
+  print "        hsp.qseq        #=> "; p hsp.qseq
+  print "        hsp.midline     #=> "; p hsp.midline
+  print "        hsp.hseq        #=> "; p hsp.hseq
+  puts
+  print "        hsp.percent_identity  #=> "; p hsp.percent_identity
+  #print "        hsp.mismatch_count    #=> "; p hsp.mismatch_count
+  #
+  print "        hsp.query_strand      #=> "; p hsp.query_strand
+  print "        hsp.hit_strand        #=> "; p hsp.hit_strand
+  print "        hsp.percent_positive  #=> "; p hsp.percent_positive
+  print "        hsp.percent_gaps      #=> "; p hsp.percent_gaps
+  puts
+
+  end #each
+  end #if hit.hsps.size == 0
+  end
+  end
+end #ff.each
+end #FlatFile.open
+