bio 1.3.1 → 1.4.0

data/sample/demo_sosui_report.rb

@@ -0,0 +1,89 @@
+#
+# = sample/demo_sosui_report.rb - demonstration of Bio::SOSUI::Report
+# 
+# Copyright::   Copyright (C) 2003 
+#               Mitsuteru C. Nakao <n@bioruby.org>
+# License::     The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::SOSUI::Report, SOSUI output parser.
+#
+# SOSUI performs classification and secondary structures prediction
+# of membrane proteins.
+#
+# == Usage
+#
+# Usage 1: Without arguments, runs demo using preset example data.
+#
+#  $ ruby demo_sosui_report.rb
+#
+# Usage 2: Specify files containing SOSUI reports.
+#
+#  $ ruby demo_sosui_report.rb files...
+#
+# Example usage using test data:
+#
+#  $ ruby -Ilib sample/demo_sosui_report.rb test/data/SOSUI/sample.report
+#
+# == References
+#
+# * http://bp.nuap.nagoya-u.ac.jp/sosui/
+#
+# == Development information
+#
+# The code was moved from lib/bio/appl/sosui/report.rb, and modified as below:
+# * Disables internal sample data when arguments are specified.
+# * Method name is changed.
+# * Bug fix about tmhs demo.
+
+require 'bio'
+
+  begin
+    require 'pp'
+    alias p pp 
+  rescue LoadError
+  end
+
+
+  sample = <<HOGE
+>HOGE1
+ MEMBRANE PROTEIN
+ NUMBER OF TM HELIX = 6
+ TM 1   12-  34 SECONDARY   LLVPILLPEKCYDQLFVQWDLLH
+ TM 2   36-  58 PRIMARY     PCLKILLSKGLGLGIVAGSLLVK
+ TM 3  102- 124 SECONDARY   SWGEALFLMLQTITICFLVMHYR
+ TM 4  126- 148 PRIMARY     QTVKGVAFLACYGLVLLVLLSPL
+ TM 5  152- 174 SECONDARY   TVVTLLQASNVPAVVVGRLLQAA
+ TM 6  214- 236 SECONDARY   AGTFVVSSLCNGLIAAQLLFYWN
+
+>HOGE2
+ SOLUBLE PROTEIN
+
+HOGE
+
+  def demo_sosui_report(ent)
+    puts '==='
+    puts ent
+    puts '==='
+    sosui = Bio::SOSUI::Report.new(ent)
+    p [:entry_id, sosui.entry_id]
+    p [:prediction, sosui.prediction]
+    p [:tmhs, sosui.tmhs]
+  end
+
+if ARGV.empty? then
+
+  sample.split(/#{Bio::SOSUI::Report::DELIMITER}/).each {|ent|
+    demo_sosui_report(ent)
+  }
+
+else 
+
+  while ent = $<.gets(Bio::SOSUI::Report::DELIMITER)
+    demo_sosui_report(ent)
+  end
+
+end
+

data/sample/demo_targetp_report.rb

@@ -0,0 +1,135 @@
+#
+# = sample/demo_targetp_report.rb - demonstration of Bio::TargetP::Report
+# 
+# Copyright::  Copyright (C) 2003 
+#              Mitsuteru C. Nakao <n@bioruby.org>
+# License::    The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::TargetP::Report, TargetP output parser.
+#
+# == Usage
+#
+# Usage 1: Without arguments, runs demo using preset example data.
+#
+#  $ ruby demo_targetp_report.rb
+#
+# Usage 2: Specify files containing TargetP reports.
+#
+#  $ ruby demo_targetp_report.rb files...
+#
+# == References
+#
+# * http://www.cbs.dtu.dk/services/TargetP/
+#
+# == Development information
+#
+# The code was moved from lib/bio/appl/targetp/report.rb, and modified
+# as below:
+# * Disables internal sample data when arguments are specified.
+# * Method name is changed.
+#
+
+require 'bio'
+
+
+  begin
+    require 'pp'
+    alias p pp 
+  rescue LoadError
+  end
+
+
+  plant = <<HOGE
+ 
+### ### ###  T A R G E T P  1.0  prediction results  ### ### ### 
+ 
+# Number of input sequences:  1
+# Cleavage site predictions not included.
+# Using PLANT networks.
+ 
+#                        Name   Length	  cTP   mTP    SP other  Loc.  RC
+#----------------------------------------------------------------------------------
+                   MGI_2141503	  640	0.031 0.161 0.271 0.844   _     3
+#----------------------------------------------------------------------------------
+# cutoff                                 0.00  0.00  0.00  0.00
+
+
+HOGE
+
+plant_c = <<HOGE
+ 
+### ### ###  T A R G E T P  1.0  prediction results  ### ### ### 
+ 
+# Number of input sequences:  1
+# Cleavage site predictions included.
+# Using PLANT networks.
+ 
+#                        Name   Length	  cTP   mTP    SP other  Loc.  RC     TPlen
+#----------------------------------------------------------------------------------
+                   MGI_2141503	  640	0.031 0.161 0.271 0.844   _     3	  -
+#----------------------------------------------------------------------------------
+# cutoff                                 0.00  0.00  0.00  0.00
+
+
+
+HOGE
+
+non_plant_c = <<HOGE
+ 
+### ### ###  T A R G E T P  1.0  prediction results  ### ### ### 
+ 
+# Number of input sequences:  1
+# Cleavage site predictions included.
+# Using NON-PLANT networks.
+ 
+#                        Name   Length    mTP   SP  other  Loc.  RC   TPlen
+#--------------------------------------------------------------------------
+                     MGI_96083	 2187	0.292 0.053 0.746   _     3	  -
+#--------------------------------------------------------------------------
+# cutoff                                 0.00  0.00  0.00
+
+
+
+HOGE
+
+
+  def demo_targetp_report(e)
+    puts e
+    ent = Bio::TargetP::Report.new(e)
+    pp ent
+
+    p [:entry_id, ent.entry_id]
+    p [:name, ent.name]
+    p [:version, ent.version]
+    p [:query_sequnces, ent.query_sequences]
+    p [:cleavage_site_prediction, ent.cleavage_site_prediction]
+    p [:networks, ent.networks]
+    p [:query_len, ent.query_len]
+    p [:prediction, ent.prediction]
+    p [:pred_Name, ent.pred['Name']]
+    p [:pred_SP, ent.pred['SP']]
+    p [:pred_mTP, ent.pred['mTP']]
+    p [:cutoff, ent.cutoff]
+    p [:loc, ent.loc]
+    p [:rc, ent.rc]
+
+    puts '=='
+  end
+
+if ARGV.empty? then
+
+  [plant, plant_c, non_plant_c].each {|e|
+    demo_targetp_report(e)
+  }
+
+else
+
+  while ent = $<.gets(Bio::TargetP::Report::DELIMITER)
+    demo_targetp_report(ent)
+  end
+
+end
+

data/sample/demo_tmhmm_report.rb

@@ -0,0 +1,68 @@
+#
+# = sample/demo_tmhmm_report.rb - demonstration of Bio::TMHMM::Report
+# 
+# Copyright::  Copyright (C) 2003 
+#              Mitsuteru C. Nakao <n@bioruby.org>
+# License::    The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::TMHMM::Report, TMHMM output parser.
+#
+# == Usage
+#
+# Specify files containing SOSUI reports.
+#
+#  $ ruby demo_tmhmm_report.rb files...
+#
+# Example usage using test data:
+#
+#  $ ruby -Ilib sample/demo_tmhmm_report.rb test/data/TMHMM/sample.report
+#
+# == References
+#
+# * http://www.cbs.dtu.dk/services/TMHMM/
+#
+# == Development information
+#
+# The code was moved from lib/bio/appl/tmhmm/report.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+
+  begin
+    require 'pp'
+    alias p pp
+  rescue LoadError
+  end
+
+  Bio::TMHMM.reports(ARGF.read) do |ent|
+    puts '==>'
+    puts ent.to_s
+    pp ent
+
+    p [:entry_id, ent.entry_id]
+    p [:query_len, ent.query_len]
+    p [:predicted_tmhs, ent.predicted_tmhs]
+    p [:tmhs_size, ent.tmhs.size]
+    p [:exp_aas_in_tmhs, ent.exp_aas_in_tmhs]
+    p [:exp_first_60aa, ent.exp_first_60aa]
+    p [:total_prob_of_N_in, ent.total_prob_of_N_in]
+
+    ent.tmhs.each do |t|
+      p t
+      p [:entry_id, t.entry_id]
+      p [:version, t.version]
+      p [:status, t.status]
+      p [:range, t.range]
+      p [:pos, t.pos]
+    end
+
+    p [:helix, ent.helix]
+    p ent.tmhs.map {|t| t if t.status == 'TMhelix' }.compact
+  end
+
+#end

data/sample/pmfetch.rb

@@ -18,12 +18,14 @@
 #  along with this program; if not, write to the Free Software
 #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 #
-#  $Id: pmfetch.rb,v 1.2 2002/07/23 04:52:03 k Exp $
+#  $Id:$
 #
 
 require 'bio' 
 
-if ARGV[0] =~ /-f/
+Bio::NCBI.default_email = 'staff@bioruby.org'
+
+if ARGV[0] =~ /\A\-f/
   ARGV.shift
   form = ARGV.shift
 else
@@ -31,12 +33,19 @@ else
 end
 
 ARGV.each do |id| 
-  entry = Bio::PubMed.query(id) 
+  entries = Bio::PubMed.efetch(id) 
+  if entries and entries.size == 1 then
+    entry = entries[0]
+  else
+    # dummy entry if not found or possibly incorrect result
+    entry = 'PMID- '
+  end
   case form
   when 'medline'
     puts entry
   else
-    puts Bio::MEDLINE.new(entry).reference.send(form)
+    puts Bio::MEDLINE.new(entry).reference.__send__(form.intern)
   end
+  print "\n"
 end 
 

data/sample/pmsearch.rb

@@ -18,25 +18,36 @@
 #  along with this program; if not, write to the Free Software
 #  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 #
-#  $Id: pmsearch.rb,v 1.2 2002/07/23 04:52:03 k Exp $
+#  $Id:$
 #
 
 require 'bio'
 
-if ARGV[0] =~ /-f/
+Bio::NCBI.default_email = 'staff@bioruby.org'
+
+if ARGV[0] =~ /\A\-f/
   ARGV.shift
   form = ARGV.shift
 else
   form = 'bibtex'
 end
 
-entries = Bio::PubMed.search(ARGV.join(' '))
+keywords = ARGV.join(' ')
+uids = Bio::PubMed.esearch(keywords)
+
+if uids and !uids.empty? then
+  entries = Bio::PubMed.efetch(uids)
+else
+  entries = []
+end
+
 entries.each do |entry| 
   case form
   when 'medline'
     puts entry
   else
-    puts Bio::MEDLINE.new(entry).reference.send(form)
+    puts Bio::MEDLINE.new(entry).reference.__send__(form.intern)
   end
+  print "\n"
 end
 

data/sample/test_phyloxml_big.rb

@@ -0,0 +1,205 @@
+#
+# = sample/test_phyloxml_big.rb - Tests for Bio::PhyloXML. Testing very big files.
+#
+# Copyright::   Copyright (C) 2009
+#               Diana Jaunzeikare <latvianlinuxgirl@gmail.com>
+#               Naohisa Goto <ng@bioruby.org>
+# License::     The Ruby License
+#
+
+# libraries needed for the tests
+require 'libxml'
+require 'pathname'
+require 'test/unit'
+require 'digest/sha1'
+
+require 'bio/command'
+require 'bio/db/phyloxml/phyloxml_parser'
+require 'bio/db/phyloxml/phyloxml_writer'
+
+PhyloXMLBigDataPath = ARGV.shift
+
+if !PhyloXMLBigDataPath then
+  exit_code = 0
+elsif !File.directory?(PhyloXMLBigDataPath) then
+  exit_code = 1
+else
+  exit_code = false
+end
+
+if exit_code then
+  puts "Usage: #{$0} path_to_data (test options...)"
+  puts ""
+  puts "Requirements:"
+  puts " - Write permission to the path_to_data"
+  puts " - Internet connection for downloading test data"
+  puts " - unzip command to extract downloaded test data"
+  puts ""
+  puts "You may want to run Ruby with -rubygems and -I<path_to_bioruby_lib>."
+  puts ""
+  puts "Example of usage using /tmp:"
+  puts "    $ mkdir /tmp/phyloxml"
+  puts "    $ ruby -rubygems -I lib #{$0} /tmp/phyloxml -v"
+  puts ""
+  exit(exit_code)
+end
+
+module TestPhyloXMLBigData
+
+  module_function
+
+  def metazoa_xml
+    #puts "Metazoa 30MB"
+    filename = 'ncbi_taxonomy_metazoa.xml'
+    uri = "http://www.phylosoft.org/archaeopteryx/examples/data/ncbi_taxonomy_metazoa.xml.zip"
+    download_and_unzip_if_not_found(filename, uri, "1M", "33M")
+  end
+
+  def metazoa_test_xml
+    #puts "writing Metazoa 30MB"
+    File.join PhyloXMLBigDataPath, 'writer_test_ncbi_taxonomy_metazoa.xml'
+  end
+
+  def metazoa_roundtrip_xml
+    #puts "writing Metazoa 30MB roundtrip"
+    File.join PhyloXMLBigDataPath, 'roundtrip_test_ncbi_taxonomy_metazoa.xml'
+  end
+
+  def mollusca_xml
+    #puts "Mollusca 1.5MB"
+    filename = 'ncbi_taxonomy_mollusca.xml'
+    uri = "http://www.phylosoft.org/archaeopteryx/examples/data/ncbi_taxonomy_mollusca.xml.zip"
+    download_and_unzip_if_not_found(filename, uri, "67K", "1.5M")
+  end
+
+  def mollusca_test_xml
+    #puts "Writing Mollusca 1.5MB"
+    File.join PhyloXMLBigDataPath, 'writer_test_ncbi_taxonomy_mollusca.xml'
+  end
+
+  def mollusca_roundtrip_xml
+    #puts "Writing Mollusca 1.5MB roundtrip"
+    File.join PhyloXMLBigDataPath, 'roundtrip_test_ncbi_taxonomy_mollusca.xml'
+  end
+
+  def life_xml
+    #Right now this file is not compatible with xsd 1.10
+    filename = 'tol_life_on_earth_1.xml'
+    uri = "http://www.phylosoft.org/archaeopteryx/examples/data/tol_life_on_earth_1.xml.zip"
+
+    download_and_unzip_if_not_found(filename, uri, '10M', '45M')
+  end
+
+  def life_test_xml
+    File.join PhyloXMLBigDataPath, 'writer_test_tol_life_on_earth_1.xml'
+  end
+
+  def life_roundtrip_xml
+    File.join PhyloXMLBigDataPath, 'roundtrip_test_tol_life_on_earth_1.xml'
+  end
+
+  def unzip_file(file, target_dir)
+    flag = system('unzip', "#{file}.zip", "-d", target_dir)
+    unless flag then
+      raise "Failed to unzip #{file}.zip"
+    end
+    file
+  end
+
+  def download_and_unzip_if_not_found(basename, uri, zipsize, origsize)
+    file = File.join PhyloXMLBigDataPath, basename
+    return file if File.exists?(file)
+
+    if File.exists?("#{file}.zip")
+      unzip_file(file, PhyloXMLBigDataPath)
+      return file
+    end
+
+    puts "File #{basename} does not exist. Do you want to download it? (If yes, ~#{zipsize}B zip file will be downloaded and extracted (to #{origsize}B), if no, the test will be skipped.) y/n?"
+    res = gets
+    if res.to_s.chomp.downcase == "y"
+      File.open("#{file}.zip", "wb") do |f|
+        f.write(Bio::Command.read_uri(uri))
+      end
+      puts "File downloaded."
+      self.unzip_file(file, PhyloXMLBigDataPath)
+      return file
+    else
+      return nil
+      #return File.join PHYLOXML_TEST_DATA, "#{basename}.stub"
+    end
+  end
+
+end #end module TestPhyloXMLBigData
+
+module Bio
+
+  class TestPhyloXMLBig < Test::Unit::TestCase
+
+    def do_test_next_tree(readfilename)
+      raise "the test is skipped" unless readfilename
+      filesizeMB = File.size(readfilename) / 1048576.0
+      printf "Reading %s (%2.1f MB)\n", readfilename, filesizeMB
+             
+      begin
+        phyloxml = Bio::PhyloXML::Parser.open(readfilename)
+      rescue NoMethodError
+        phyloxml = Bio::PhyloXML::Parser.new(readfilename)
+      end
+      tree = nil
+      assert_nothing_raised {
+        tree = phyloxml.next_tree
+      }
+      tree
+    end
+    private :do_test_next_tree
+
+    def do_test_write(tree, writefilename)
+      printf "Writing to %s\n", writefilename
+      writer = Bio::PhyloXML::Writer.new(writefilename)
+      assert_nothing_raised {
+        writer.write(tree)
+      }
+
+      # checks file size and sha1sum
+      str = File.open(writefilename, 'rb') { |f| f.read }
+      sha1 = Digest::SHA1.hexdigest(str)
+      puts "Wrote #{str.length} bytes."
+      puts "sha1: #{sha1}"
+    end
+    private :do_test_write
+
+    def test_mollusca
+      tree = do_test_next_tree(TestPhyloXMLBigData.mollusca_xml)
+      do_test_write(tree, TestPhyloXMLBigData.mollusca_test_xml)
+
+      tree2 = do_test_next_tree(TestPhyloXMLBigData.mollusca_test_xml)
+      do_test_write(tree2, TestPhyloXMLBigData.mollusca_roundtrip_xml)
+    end
+
+    def test_metazoa
+      tree = do_test_next_tree(TestPhyloXMLBigData.metazoa_xml)
+      do_test_write(tree, TestPhyloXMLBigData.metazoa_test_xml)
+
+      tree2 = do_test_next_tree(TestPhyloXMLBigData.metazoa_test_xml)
+      do_test_write(tree2, TestPhyloXMLBigData.metazoa_roundtrip_xml)
+    end
+
+    if false
+      # Disabled because of the error.
+      # LibXML::XML::Error: Fatal error: Input is not proper UTF-8,
+      # indicate encoding !
+      # Bytes: 0xE9 0x6B 0x65 0x73 at tol_life_on_earth_1.xml:132170.
+      #
+      def test_life
+        tree = do_test_next_tree(TestPhyloXMLBigData.life_xml)
+        do_test_write(tree, TestPhyloXMLBigData.life_test_xml)
+        
+        tree2 = do_test_next_tree(TestPhyloXMLBigData.life_test_xml)
+        do_test_write(tree2, TestPhyloXMLBigData.life_roundtrip_xml)
+      end
+    end #if false
+
+  end
+
+end