bio 1.3.1 → 1.4.0

data/sample/demo_litdb.rb

@@ -0,0 +1,42 @@
+#
+# = sample/demo_litdb.rb - demonstration of Bio::LITDB
+#
+# Copyright::  Copyright (C) 2001 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::LITDB, LITDB literature database parser class.
+#
+# == Requirements
+#
+# Internet connection and/or OBDA (Open Bio Database Access) configuration.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_litdb.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/db/litdb.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+
+  entry = Bio::Fetch.query('litdb', '0308004') 
+  puts entry
+  p Bio::LITDB.new(entry).reference
+
+  entry = Bio::Fetch.query('litdb', '0309094')
+  puts entry
+  p Bio::LITDB.new(entry).reference
+
+  entry = Bio::Fetch.query('litdb', '0309093')
+  puts entry
+  p Bio::LITDB.new(entry).reference
+#end

data/sample/demo_locations.rb

@@ -0,0 +1,99 @@
+#
+# = sample/demo_locations.rb - demonstration of Bio::Locations
+#
+# Copyright::	Copyright (C) 2001, 2005 Toshiaki Katayama <k@bioruby.org>
+#                             2006       Jan Aerts <jan.aerts@bbsrc.ac.uk>
+#                             2008       Naohisa Goto <ng@bioruby.org>
+# License::	The Ruby License
+#
+# == Description
+#
+# Demonstration of Bio::Locations, a parser class for the location string
+# used in the INSDC Feature Table.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_locations.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/location.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+  puts "Test new & span methods"
+  [
+    '450',
+    '500..600',
+    'join(500..550, 600..625)',
+    'complement(join(500..550, 600..625))',
+    'join(complement(500..550), 600..625)',
+    '754^755',
+    'complement(53^54)',
+    'replace(4792^4793,"a")',
+    'replace(1905^1906,"acaaagacaccgccctacgcc")',
+    '157..(800.806)',
+    '(67.68)..(699.703)',
+    '(45934.45974)..46135',
+    '<180..(731.761)',
+    '(88.89)..>1122',
+    'complement((1700.1708)..(1715.1721))',
+    'complement(<22..(255.275))',
+    'complement((64.74)..1525)',
+    'join((8298.8300)..10206,1..855)',
+    'replace((651.655)..(651.655),"")',
+    'one-of(898,900)..983',
+    'one-of(5971..6308,5971..6309)',
+    '8050..one-of(10731,10758,10905,11242)',
+    'one-of(623,627,632)..one-of(628,633,637)',
+    'one-of(845,953,963,1078,1104)..1354',
+    'join(2035..2050,complement(1775..1818),13..345,414..992,1232..1253,1024..1157)',
+    'join(complement(1..61),complement(AP000007.1:252907..253505))',
+    'complement(join(71606..71829,75327..75446,76039..76203))',
+    'order(3..26,complement(964..987))',
+    'order(L44135.1:(454.445)..>538,<1..181)',
+    '<200001..<318389',
+  ].each do |pos|
+    p pos
+#    p Bio::Locations.new(pos)
+#    p Bio::Locations.new(pos).span
+#    p Bio::Locations.new(pos).range
+    Bio::Locations.new(pos).each do |location|
+      puts "class=" + location.class.to_s
+      puts "start=" + location.from.to_s + "\tend=" + location.to.to_s + "\tstrand=" + location.strand.to_s
+    end
+
+  end
+
+  puts "Test rel2abs/abs2rel method"
+  [
+    '6..15',
+    'join(6..10,16..30)',
+    'complement(join(6..10,16..30))',
+    'join(complement(6..10),complement(16..30))',
+    'join(6..10,complement(16..30))',
+  ].each do |pos|
+    loc = Bio::Locations.new(pos)
+    p pos
+#   p loc
+    (1..21).each do |x|
+      print "absolute(#{x}) #=> ", y = loc.absolute(x), "\n"
+      print "relative(#{y}) #=> ", y ? loc.relative(y) : y, "\n"
+      print "absolute(#{x}, :aa) #=> ", y = loc.absolute(x, :aa), "\n"
+      print "relative(#{y}, :aa) #=> ", y ? loc.relative(y, :aa) : y, "\n"
+    end
+  end
+
+  pos = 'join(complement(6..10),complement(16..30))'
+  loc = Bio::Locations.new(pos)
+  print "pos         : "; p pos
+  print "`- loc[1]   : "; p loc[1]
+  print "   `- range : "; p loc[1].range
+
+  puts Bio::Location.new('5').<=>(Bio::Location.new('3'))
+#end
+

data/sample/demo_ncbi_rest.rb

@@ -0,0 +1,130 @@
+#
+# = sample/demo_ncbi_rest.rb - demonstration of Bio::NCBI::REST, NCBI E-Utilities client
+#
+# Copyright::  Copyright (C) 2008 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::NCBI::REST, NCBI E-Utilities client.
+#
+# == Requirements
+#
+# Internet connection is needed.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_ncbi_rest.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/io/ncbirest.rb.
+#
+
+require 'bio'
+
+Bio::NCBI.default_email = 'staff@bioruby.org'
+
+#if __FILE__ == $0
+
+  gbopts = {"db"=>"nuccore", "rettype"=>"gb"}
+  pmopts = {"db"=>"pubmed", "rettype"=>"medline"}
+  count = {"rettype" => "count"}
+  xml = {"retmode"=>"xml"}
+  max = {"retmax"=>5}
+
+  puts "=== class methods ==="
+
+  puts "--- Search NCBI by E-Utils ---"
+
+  puts Time.now
+  puts "# count of 'tardigrada' in nuccore"
+  puts Bio::NCBI::REST.esearch("tardigrada", gbopts.merge(count))
+
+  puts Time.now
+  puts "# max 5 'tardigrada' entries in nuccore"
+  puts Bio::NCBI::REST.esearch("tardigrada", gbopts.merge(max))
+
+  puts Time.now
+  puts "# count of 'yeast kinase' in nuccore"
+  puts Bio::NCBI::REST.esearch("yeast kinase", gbopts.merge(count))
+
+  puts Time.now
+  puts "# max 5 'yeast kinase' entries in nuccore (XML)"
+  puts Bio::NCBI::REST.esearch("yeast kinase", gbopts.merge(xml).merge(max))
+
+  puts Time.now
+  puts "# count of 'genome&analysis|bioinformatics' in pubmed"
+  puts Bio::NCBI::REST.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(count))
+
+  puts Time.now
+  puts "# max 5 'genome&analysis|bioinformatics' entries in pubmed (XML)"
+  puts Bio::NCBI::REST.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(xml).merge(max))
+
+  puts Time.now
+  Bio::NCBI::REST.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(max)).each do |x|
+    puts "# each of 5 'genome&analysis|bioinformatics' entries in pubmed"
+    puts x
+  end
+
+  puts "--- Retrieve NCBI entry by E-Utils ---"
+
+  puts Time.now
+  puts "# '185041' entry in nuccore"
+  puts Bio::NCBI::REST.efetch("185041", gbopts)
+
+  puts Time.now
+  puts "# 'J00231' entry in nuccore (XML)"
+  puts Bio::NCBI::REST.efetch("J00231", gbopts.merge(xml))
+
+  puts Time.now
+  puts "# 16381885 entry in pubmed"
+  puts Bio::NCBI::REST.efetch(16381885, pmopts)
+
+  puts Time.now
+  puts "# '16381885' entry in pubmed"
+  puts Bio::NCBI::REST.efetch("16381885", pmopts)
+
+  puts Time.now
+  puts "# [10592173,14693808] entries in pubmed"
+  puts Bio::NCBI::REST.efetch([10592173, 14693808], pmopts)
+
+  puts Time.now
+  puts "# [10592173,14693808] entries in pubmed (XML)"
+  puts Bio::NCBI::REST.efetch([10592173, 14693808], pmopts.merge(xml))
+
+
+  puts "=== instance methods ==="
+
+  ncbi = Bio::NCBI::REST.new
+
+  puts "--- Search NCBI by E-Utils ---"
+
+  puts Time.now
+  puts "# count of 'genome&analysis|bioinformatics' in pubmed"
+  puts ncbi.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(count))
+
+  puts Time.now
+  puts "# max 5 'genome&analysis|bioinformatics' entries in pubmed"
+  puts ncbi.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(max))
+
+  puts Time.now
+  ncbi.esearch("(genome AND analysis) OR bioinformatics", pmopts).each do |x|
+    puts "# each 'genome&analysis|bioinformatics' entries in pubmed"
+    puts x
+  end
+
+  puts "--- Retrieve NCBI entry by E-Utils ---"
+
+  puts Time.now
+  puts "# 16381885 entry in pubmed"
+  puts ncbi.efetch(16381885, pmopts)
+
+  puts Time.now
+  puts "# [10592173,14693808] entries in pubmed"
+  puts ncbi.efetch([10592173, 14693808], pmopts)
+
+#end

data/sample/demo_nucleicacid.rb

@@ -0,0 +1,49 @@
+#
+# = sample/demo_nucleicacid.rb - demonstration of Bio::NucleicAcid
+#
+# Copyright::	Copyright (C) 2001, 2005
+#		Toshiaki Katayama <k@bioruby.org>
+# License::	The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::NucleicAcid, data related to nucleic acids.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_nucleicacid.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/data/na.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+
+  puts "### na = Bio::NucleicAcid.new"
+  na = Bio::NucleicAcid.new
+
+  puts "# na.to_re('yrwskmbdhvnatgc')"
+  p na.to_re('yrwskmbdhvnatgc')
+
+  puts "# Bio::NucleicAcid.to_re('yrwskmbdhvnatgc')"
+  p Bio::NucleicAcid.to_re('yrwskmbdhvnatgc')
+
+  puts "# na.weight('A')"
+  p na.weight('A')
+
+  puts "# Bio::NucleicAcid.weight('A')"
+  p Bio::NucleicAcid.weight('A')
+
+  puts "# na.weight('atgc')"
+  p na.weight('atgc')
+
+  puts "# Bio::NucleicAcid.weight('atgc')"
+  p Bio::NucleicAcid.weight('atgc')
+
+#end

data/sample/demo_pathway.rb

@@ -0,0 +1,196 @@
+#
+# = sample/demo_pathway.rb - demonstration of Bio::Pathway
+#
+# Copyright:    Copyright (C) 2001
+#               Toshiaki Katayama <k@bioruby.org>,
+#               Shuichi Kawashima <shuichi@hgc.jp>
+# License::     The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::Pathway, an implementation of the graph data structure
+# and graph algorithms.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_pathway.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/pathway.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+
+  puts "--- Test === method true/false"
+  r1 = Bio::Relation.new('a', 'b', 1)
+  r2 = Bio::Relation.new('b', 'a', 1)
+  r3 = Bio::Relation.new('b', 'a', 2)
+  r4 = Bio::Relation.new('a', 'b', 1)
+  p r1 === r2
+  p r1 === r3
+  p r1 === r4
+  p [ r1, r2, r3, r4 ].uniq
+  p r1.eql?(r2)
+  p r3.eql?(r2)
+
+  # Sample Graph :
+  #                  +----------------+
+  #                  |                |
+  #                  v                |
+  #       +---------(q)-->(t)------->(y)<----(r)
+  #       |          |     |          ^       |
+  #       v          |     v          |       |
+  #   +--(s)<--+     |    (x)<---+   (u)<-----+
+  #   |        |     |     |     |
+  #   v        |     |     v     |
+  #  (v)----->(w)<---+    (z)----+
+
+  data = [
+    [ 'q', 's', 1, ],
+    [ 'q', 't', 1, ],
+    [ 'q', 'w', 1, ],
+    [ 'r', 'u', 1, ],
+    [ 'r', 'y', 1, ],
+    [ 's', 'v', 1, ],
+    [ 't', 'x', 1, ],
+    [ 't', 'y', 1, ],
+    [ 'u', 'y', 1, ],
+    [ 'v', 'w', 1, ],
+    [ 'w', 's', 1, ],
+    [ 'x', 'z', 1, ],
+    [ 'y', 'q', 1, ],
+    [ 'z', 'x', 1, ],
+  ]
+
+  ary = []
+
+  puts "--- List of relations"
+  data.each do |x|
+    ary << Bio::Relation.new(*x)
+  end
+  p ary
+
+  puts "--- Generate graph from list of relations"
+  graph = Bio::Pathway.new(ary)
+  p graph
+
+  puts "--- Test to_matrix method"
+  p graph.to_matrix
+
+  puts "--- Test dump_matrix method"
+  puts graph.dump_matrix(0)
+
+  puts "--- Test dump_list method"
+  puts graph.dump_list
+
+  puts "--- Labeling some nodes"
+  hash = { 'q' => "L1", 's' => "L2", 'v' => "L3", 'w' => "L4" }
+  graph.label = hash
+  p graph
+
+  puts "--- Extract subgraph by label"
+  p graph.subgraph
+
+  puts "--- Extract subgraph by list"
+  p graph.subgraph(['q', 't', 'x', 'y', 'z'])
+
+  puts "--- Test cliquishness of the node 'q'"
+  p graph.cliquishness('q')
+
+  puts "--- Test cliquishness of the node 'q' (undirected)"
+  u_graph = Bio::Pathway.new(ary, 'undirected')
+  p u_graph.cliquishness('q')
+
+  puts "--- Test small_world histgram"
+  p graph.small_world
+
+  puts "--- Test breadth_first_search method"
+  distance, predecessor = graph.breadth_first_search('q')
+  p distance
+  p predecessor
+
+  puts "--- Test bfs_shortest_path method"
+  step, path = graph.bfs_shortest_path('y', 'w')
+  p step
+  p path
+
+  puts "--- Test depth_first_search method"
+  timestamp, tree, back, cross, forward = graph.depth_first_search
+  p timestamp
+  print "tree edges : "; p tree
+  print "back edges : "; p back
+  print "cross edges : "; p cross
+  print "forward edges : "; p forward
+
+  puts "--- Test dfs_topological_sort method"
+  #
+  # Professor Bumstead topologically sorts his clothing when getting dressed.
+  #
+  #  "undershorts"       "socks"
+  #     |      |            |
+  #     v      |            v           "watch"
+  #  "pants" --+-------> "shoes"
+  #     |
+  #     v
+  #  "belt" <----- "shirt" ----> "tie" ----> "jacket"
+  #     |                                       ^
+  #     `---------------------------------------'
+  #
+  dag = Bio::Pathway.new([
+    Bio::Relation.new("undeershorts", "pants", true),
+    Bio::Relation.new("undeershorts", "shoes", true),
+    Bio::Relation.new("socks", "shoes", true),
+    Bio::Relation.new("watch", "watch", true),
+    Bio::Relation.new("pants", "belt", true),
+    Bio::Relation.new("pants", "shoes", true),
+    Bio::Relation.new("shirt", "belt", true),
+    Bio::Relation.new("shirt", "tie", true),
+    Bio::Relation.new("tie", "jacket", true),
+    Bio::Relation.new("belt", "jacket", true),
+  ])
+  p dag.dfs_topological_sort
+
+  puts "--- Test dijkstra method"
+  distance, predecessor = graph.dijkstra('q')
+  p distance
+  p predecessor
+
+  puts "--- Test dijkstra method by weighted graph"
+  #
+  # 'a' --> 'b'
+  #  |   1   | 3
+  #  |5      v
+  #  `----> 'c'
+  #
+  r1 = Bio::Relation.new('a', 'b', 1)
+  r2 = Bio::Relation.new('a', 'c', 5)
+  r3 = Bio::Relation.new('b', 'c', 3)
+  w_graph = Bio::Pathway.new([r1, r2, r3])
+  p w_graph
+  p w_graph.dijkstra('a')
+
+  puts "--- Test bellman_ford method by negative weighted graph"
+  #
+  # ,-- 'a' --> 'b'
+  # |    |   1   | 3
+  # |    |5      v
+  # |    `----> 'c'
+  # |            ^
+  # |2           | -5
+  # `--> 'd' ----'
+  #
+  r4 = Bio::Relation.new('a', 'd', 2)
+  r5 = Bio::Relation.new('d', 'c', -5)
+  w_graph.append(r4)
+  w_graph.append(r5)
+  p w_graph.bellman_ford('a')
+  p graph.bellman_ford('q')
+
+#end
+