bio-phyloxml 0.9.0

data/lib/bio/phyloxml/writer.rb

@@ -0,0 +1,227 @@
+#
+# = bio/db/phyloxml_writer.rb - PhyloXML writer
+#
+# Copyright::   Copyright (C) 2009
+#               Diana Jaunzeikare <latvianlinuxgirl@gmail.com>
+# License::     The Ruby License
+#
+# $Id:$
+#
+# == Description
+#
+# This file containts writer for PhyloXML.
+#
+# == Requirements
+#
+# Libxml2 XML parser is required. Install libxml-ruby bindings from
+# http://libxml.rubyforge.org or
+#
+#   gem install -r libxml-ruby
+#
+# == References
+#
+# * http://www.phyloxml.org
+#
+# * https://www.nescent.org/wg_phyloinformatics/PhyloSoC:PhyloXML_support_in_BioRuby
+
+require 'libxml'
+
+module Bio
+
+  module PhyloXML
+
+  # == Description
+  #
+  # Bio::PhyloXML::Writer is for writing phyloXML (version 1.10) format files.
+  #
+  # == Requirements
+  #
+  # Libxml2 XML parser is required. Install libxml-ruby bindings from
+  # http://libxml.rubyforge.org or
+  #
+  #   gem install -r libxml-ruby
+  #
+  # == Usage
+  #
+  #   require 'bio'
+  #
+  #  # Create new phyloxml parser
+  #  phyloxml = Bio::PhyloXML::Parser.open('example.xml')
+  #
+  #  # Read in some trees from file
+  #  tree1 = phyloxml.next_tree
+  #  tree2 = phyloxml.next_tree
+  #
+  #  # Create new phyloxml writer
+  #  writer = Bio::PhyloXML::Writer.new('tree.xml')
+  #
+  #  # Write tree to the file tree.xml
+  #  writer.write(tree1)
+  #
+  #  # Add another tree to the file
+  #  writer.write(tree2)
+  #
+  # == References
+  #
+  # http://www.phyloxml.org/documentation/version_100/phyloxml.xsd.html
+
+    class Writer
+
+      include LibXML
+
+      SCHEMA_LOCATION = 'http://www.phyloxml.org http://www.phyloxml.org/1.10/phyloxml.xsd'
+            
+      attr_accessor :write_branch_length_as_subelement
+
+      #
+      # Create new Writer object. As parameters provide filename of xml file
+      # you wish to create. Optional parameter is whether to indent or no.
+      # Default is true. By default branch_length is written as subelement of
+      # clade element.
+      #
+      def initialize(filename, indent=true)
+      @write_branch_length_as_subelement = true #default value
+      @filename = filename
+      @indent = indent
+
+      @doc = XML::Document.new()
+      @doc.root = XML::Node.new('phyloxml')
+      @root = @doc.root
+      @root['xmlns:xsi'] = 'http://www.w3.org/2001/XMLSchema-instance'
+      @root['xsi:schemaLocation'] = SCHEMA_LOCATION
+      @root['xmlns'] = 'http://www.phyloxml.org'
+
+      #@todo save encoding to be UTF-8. (However it is the default one).
+      #it gives error NameError: uninitialized constant LibXML::XML::Encoding
+      #@doc.encoding = XML::Encoding::UTF_8
+
+      @doc.save(@filename, :indent => true)
+      end
+
+      #
+      # Write a tree to a file in phyloxml format.
+      #
+      #  require 'Bio'
+      #  writer = Bio::PhyloXML::Writer.new
+      #  writer.write(tree)
+      #
+      def write(tree)
+        @root << phylogeny = XML::Node.new('phylogeny')        
+        
+        PhyloXML::Writer.generate_xml(phylogeny, tree, [
+            [:attr, 'rooted'],
+            [:simple, 'name', tree.name],
+            [:complex, 'id', tree.phylogeny_id],
+            [:simple, 'description', tree.description],
+            [:simple, 'date', tree.date],
+            [:objarr, 'confidence', 'confidences']])
+
+        root_clade = tree.root.to_xml(nil, @write_branch_length_as_subelement)
+        
+        phylogeny << root_clade 
+
+        tree.children(tree.root).each do |node|
+          root_clade << node_to_xml(tree, node, tree.root)
+        end
+
+        Bio::PhyloXML::Writer::generate_xml(phylogeny, tree, [
+            [:objarr, 'clade_relation', 'clade_relations'],
+            [:objarr, 'sequence_relation', 'sequence_relations'],
+            [:objarr, 'property', 'properties']] )
+
+        @doc.save(@filename, :indent => @indent)
+      end #writer#write
+
+
+      #
+      # PhyloXML Schema allows to save data in different xml format after all
+      # phylogeny elements. This method is to write these additional data.
+      #
+      #  parser = PhyloXML::Parser.open('phyloxml_examples.xml')
+      #  writer = PhyloXML::Writer.new('new.xml')
+      #
+      #  parser.each do |tree|
+      #    writer.write(tree)
+      #  end
+      #
+      #  # When all the trees are read in by the parser, whats left is saved at
+      #  # PhyloXML::Parser#other
+      #  writer.write(parser.other)
+      #
+
+      def write_other(other_arr)
+        other_arr.each do |other_obj|
+          @root << other_obj.to_xml
+        end
+        @doc.save(@filename, :indent => @indent)
+      end
+
+      #class method
+
+      #
+      # Used by to_xml methods of PhyloXML element classes. Generally not to be
+      # invoked directly. 
+      #
+      def self.generate_xml(root, elem, subelement_array)
+       #example usage: generate_xml(node, self, [[ :complex,'accession', ], [:simple, 'name',  @name], [:simple, 'location', @location]])
+      subelement_array.each do |subelem|
+        if subelem[0] == :simple         
+          root << XML::Node.new(subelem[1], subelem[2].to_s) if subelem[2] != nil and not subelem[2].to_s.empty?
+
+        elsif subelem[0] == :complex
+          root << subelem[2].send("to_xml") if subelem[2] != nil
+
+        elsif subelem[0] == :pattern
+          #seq, self, [[:pattern, 'symbol', @symbol, "\S{1,10}"]
+          if subelem[2] != nil
+            if subelem[2] =~ subelem[3]
+              root << XML::Node.new(subelem[1], subelem[2])
+            else
+              raise "#{subelem[2]} is not a valid value of #{subelem[1]}. It should follow pattern #{subelem[3]}"
+            end
+          end
+
+        elsif subelem[0] == :objarr
+          #[:objarr, 'annotation', 'annotations']])
+          obj_arr = elem.send(subelem[2])
+          obj_arr.each do |arr_elem|
+            root << arr_elem.to_xml
+          end
+
+        elsif subelem[0] == :simplearr
+          #  [:simplearr, 'common_name', @common_names]
+          subelem[2].each do |elem_val|
+            root << XML::Node.new(subelem[1], elem_val)
+          end
+        elsif subelem[0] == :attr
+          #[:attr, 'rooted']
+          obj = elem.send(subelem[1])
+          if obj != nil
+            root[subelem[1]] = obj.to_s
+          end
+        else
+          raise "Not supported type of element by method generate_xml."
+        end
+      end
+      return root
+     end
+
+      private
+
+      def node_to_xml(tree, node, parent)
+        edge = tree.get_edge(parent, node)
+        branch_length = edge.distance
+
+        clade = node.to_xml(branch_length, @write_branch_length_as_subelement)
+
+        tree.children(node).each do |new_node|
+          clade << node_to_xml(tree, new_node, node)
+        end
+
+        return clade
+      end
+
+    end
+
+  end
+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

data/test/data/phyloxml/apaf.xml

@@ -0,0 +1,666 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<phyloxml xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.phyloxml.org http://www.phyloxml.org/1.00/phyloxml.xsd" xmlns="http://www.phyloxml.org">
+<phylogeny rooted="true">
+   <clade>
+      <clade>
+         <branch_length>0.18105</branch_length>
+         <confidence type="unknown">89.0</confidence>
+         <clade>
+            <branch_length>0.07466</branch_length>
+            <confidence type="unknown">32.0</confidence>
+            <clade>
+               <branch_length>0.26168</branch_length>
+               <confidence type="unknown">100.0</confidence>
+               <clade>
+                  <branch_length>0.22058</branch_length>
+                  <confidence type="unknown">89.0</confidence>
+                  <clade>
+                     <branch_length>0.28901</branch_length>
+                     <confidence type="unknown">100.0</confidence>
+                     <clade>
+                        <branch_length>0.06584</branch_length>
+                        <confidence type="unknown">100.0</confidence>
+                        <clade>
+                           <branch_length>0.02309</branch_length>
+                           <confidence type="unknown">43.0</confidence>
+                           <clade>
+                              <branch_length>0.0746</branch_length>
+                              <confidence type="unknown">100.0</confidence>
+                              <clade>
+                                 <branch_length>0.02365</branch_length>
+                                 <confidence type="unknown">88.0</confidence>
+                                 <clade>
+                                    <name>22_MOUSE</name>
+                                    <branch_length>0.05998</branch_length>
+                                    <taxonomy>
+                                       <code>MOUSE</code>
+                                    </taxonomy>
+                                    <sequence>
+                                       <domain_architecture length="1249">
+                                          <domain from="6" to="90" confidence="7.0E-26">CARD</domain>
+                                          <domain from="109" to="414" confidence="7.2E-117">NB-ARC</domain>
+                                          <domain from="605" to="643" confidence="2.4E-6">WD40</domain>
+                                          <domain from="647" to="685" confidence="1.1E-12">WD40</domain>
+                                          <domain from="689" to="729" confidence="2.4E-7">WD40</domain>
+                                          <domain from="733" to="771" confidence="4.7E-14">WD40</domain>
+                                          <domain from="872" to="910" confidence="2.5E-8">WD40</domain>
+                                          <domain from="993" to="1031" confidence="4.6E-6">WD40</domain>
+                                          <domain from="1075" to="1113" confidence="6.3E-7">WD40</domain>
+                                          <domain from="1117" to="1155" confidence="1.4E-7">WD40</domain>
+                                          <domain from="1168" to="1204" confidence="0.3">WD40</domain>
+                                       </domain_architecture>
+                                    </sequence>
+                                 </clade>
+                                 <clade>
+                                    <name>Apaf-1_HUMAN</name>
+                                    <branch_length>0.01825</branch_length>
+                                    <taxonomy>
+                                       <code>HUMAN</code>
+                                    </taxonomy>
+                                    <sequence>
+                                       <domain_architecture length="1248">
+                                          <domain from="6" to="90" confidence="1.1E-25">CARD</domain>
+                                          <domain from="109" to="414" confidence="3.0E-134">NB-ARC</domain>
+                                          <domain from="605" to="643" confidence="8.5E-6">WD40</domain>
+                                          <domain from="647" to="685" confidence="2.5E-11">WD40</domain>
+                                          <domain from="689" to="729" confidence="2.4E-8">WD40</domain>
+                                          <domain from="733" to="771" confidence="3.6E-14">WD40</domain>
+                                          <domain from="872" to="910" confidence="3.8E-8">WD40</domain>
+                                          <domain from="1075" to="1113" confidence="4.0E-7">WD40</domain>
+                                          <domain from="1117" to="1155" confidence="5.9E-8">WD40</domain>
+                                       </domain_architecture>
+                                    </sequence>
+                                 </clade>
+                              </clade>
+                              <clade>
+                                 <name>12_CANFA</name>
+                                 <branch_length>0.04683</branch_length>
+                                 <taxonomy>
+                                    <code>CANFA</code>
+                                 </taxonomy>
+                                 <sequence>
+                                    <domain_architecture length="1153">
+                                       <domain from="6" to="90" confidence="4.5E-22">CARD</domain>
+                                       <domain from="110" to="415" confidence="4.0E-119">NB-ARC</domain>
+                                       <domain from="597" to="635" confidence="3.9E-5">WD40</domain>
+                                       <domain from="639" to="677" confidence="2.5E-11">WD40</domain>
+                                       <domain from="681" to="721" confidence="1.8E-7">WD40</domain>
+                                       <domain from="725" to="763" confidence="9.4E-13">WD40</domain>
+                                       <domain from="889" to="927" confidence="1.1E-6">WD40</domain>
+                                       <domain from="971" to="1009" confidence="1.7E-7">WD40</domain>
+                                       <domain from="1013" to="1051" confidence="1.9E-7">WD40</domain>
+                                    </domain_architecture>
+                                 </sequence>
+                              </clade>
+                           </clade>
+                           <clade>
+                              <name>11_CHICK</name>
+                              <branch_length>0.15226</branch_length>
+                              <taxonomy>
+                                 <code>CHICK</code>
+                              </taxonomy>
+                              <sequence>
+                                 <domain_architecture length="1207">
+                                    <domain from="6" to="90" confidence="3.6E-21">CARD</domain>
+                                    <domain from="109" to="414" confidence="3.6E-109">NB-ARC</domain>
+                                    <domain from="603" to="641" confidence="1.6E-4">WD40</domain>
+                                    <domain from="645" to="683" confidence="8.2E-11">WD40</domain>
+                                    <domain from="687" to="727" confidence="6.2E-10">WD40</domain>
+                                    <domain from="731" to="769" confidence="1.8E-11">WD40</domain>
+                                    <domain from="828" to="866" confidence="1.8">WD40</domain>
+                                    <domain from="993" to="1030" confidence="2.9E-4">WD40</domain>
+                                    <domain from="1034" to="1072" confidence="1.7E-8">WD40</domain>
+                                    <domain from="1076" to="1114" confidence="7.5E-9">WD40</domain>
+                                    <domain from="1127" to="1163" confidence="0.044">WD40</domain>
+                                 </domain_architecture>
+                              </sequence>
+                           </clade>
+                        </clade>
+                        <clade>
+                           <name>16_XENLA</name>
+                           <branch_length>0.4409</branch_length>
+                           <taxonomy>
+                              <code>XENLA</code>
+                           </taxonomy>
+                           <sequence>
+                              <domain_architecture length="1362">
+                                 <domain from="6" to="90" confidence="4.0E-20">CARD</domain>
+                                 <domain from="109" to="410" confidence="3.1E-56">NB-ARC</domain>
+                                 <domain from="148" to="298" confidence="0.8">NACHT</domain>
+                                 <domain from="729" to="767" confidence="7.0E-6">WD40</domain>
+                                 <domain from="771" to="809" confidence="2.3E-11">WD40</domain>
+                                 <domain from="813" to="853" confidence="1.1E-8">WD40</domain>
+                                 <domain from="857" to="895" confidence="1.1E-10">WD40</domain>
+                                 <domain from="992" to="1030" confidence="8.4E-9">WD40</domain>
+                                 <domain from="1116" to="1154" confidence="7.3E-11">WD40</domain>
+                                 <domain from="1158" to="1196" confidence="1.6E-8">WD40</domain>
+                                 <domain from="1200" to="1238" confidence="1.2E-7">WD40</domain>
+                              </domain_architecture>
+                           </sequence>
+                        </clade>
+                     </clade>
+                     <clade>
+                        <branch_length>0.17031</branch_length>
+                        <confidence type="unknown">100.0</confidence>
+                        <clade>
+                           <branch_length>0.10929</branch_length>
+                           <confidence type="unknown">100.0</confidence>
+                           <clade>
+                              <name>14_FUGRU</name>
+                              <branch_length>0.02255</branch_length>
+                              <taxonomy>
+                                 <code>FUGRU</code>
+                              </taxonomy>
+                              <sequence>
+                                 <domain_architecture length="1258">
+                                    <domain from="8" to="92" confidence="4.6E-24">CARD</domain>
+                                    <domain from="111" to="418" confidence="7.0E-74">NB-ARC</domain>
+                                    <domain from="609" to="647" confidence="2.8E-4">WD40</domain>
+                                    <domain from="651" to="689" confidence="2.3E-12">WD40</domain>
+                                    <domain from="740" to="778" confidence="1.8E-6">WD40</domain>
+                                    <domain from="874" to="912" confidence="1.6E-9">WD40</domain>
+                                    <domain from="998" to="1036" confidence="9.8E-13">WD40</domain>
+                                    <domain from="1040" to="1080" confidence="1.6E-4">WD40</domain>
+                                    <domain from="1084" to="1122" confidence="1.5E-9">WD40</domain>
+                                    <domain from="1126" to="1164" confidence="6.2E-9">WD40</domain>
+                                 </domain_architecture>
+                              </sequence>
+                           </clade>
+                           <clade>
+                              <name>15_TETNG</name>
+                              <branch_length>0.09478</branch_length>
+                              <taxonomy>
+                                 <code>TETNG</code>
+                              </taxonomy>
+                              <sequence>
+                                 <domain_architecture length="621">
+                                    <domain from="8" to="92" confidence="2.5E-24">CARD</domain>
+                                    <domain from="104" to="308" confidence="9.8E-11">NB-ARC</domain>
+                                    <domain from="366" to="404" confidence="1.2E-12">WD40</domain>
+                                    <domain from="455" to="493" confidence="1.0E-10">WD40</domain>
+                                    <domain from="537" to="575" confidence="4.1E-10">WD40</domain>
+                                 </domain_architecture>
+                              </sequence>
+                           </clade>
+                        </clade>
+                        <clade>
+                           <name>17_BRARE</name>
+                           <branch_length>0.1811</branch_length>
+                           <taxonomy>
+                              <code>BRARE</code>
+                           </taxonomy>
+                           <sequence>
+                              <domain_architecture length="1260">
+                                 <domain from="6" to="90" confidence="3.9E-23">CARD</domain>
+                                 <domain from="137" to="444" confidence="1.7E-72">NB-ARC</domain>
+                                 <domain from="635" to="673" confidence="1.6">WD40</domain>
+                                 <domain from="694" to="732" confidence="5.3E-12">WD40</domain>
+                                 <domain from="783" to="821" confidence="2.0E-8">WD40</domain>
+                                 <domain from="1040" to="1078" confidence="2.4E-8">WD40</domain>
+                                 <domain from="1081" to="1121" confidence="6.6E-4">WD40</domain>
+                                 <domain from="1125" to="1163" confidence="5.1E-8">WD40</domain>
+                                 <domain from="1167" to="1205" confidence="1.3E-7">WD40</domain>
+                              </domain_architecture>
+                           </sequence>
+                        </clade>
+                     </clade>
+                  </clade>
+                  <clade>
+                     <branch_length>0.01594</branch_length>
+                     <confidence type="unknown">53.0</confidence>
+                     <clade>
+                        <branch_length>0.10709</branch_length>
+                        <confidence type="unknown">68.0</confidence>
+                        <clade>
+                           <name>1_BRAFL</name>
+                           <branch_length>0.26131</branch_length>
+                           <taxonomy>
+                              <code>BRAFL</code>
+                           </taxonomy>
+                           <sequence>
+                              <domain_architecture length="1238">
+                                 <domain from="6" to="89" confidence="5.7E-19">CARD</domain>
+                                 <domain from="111" to="413" confidence="4.2E-48">NB-ARC</domain>
+                                 <domain from="600" to="638" confidence="3.2E-8">WD40</domain>
+                                 <domain from="642" to="680" confidence="1.5E-10">WD40</domain>
+                                 <domain from="730" to="768" confidence="9.6E-11">WD40</domain>
+                                 <domain from="857" to="895" confidence="3.7E-10">WD40</domain>
+                                 <domain from="984" to="1022" confidence="6.7E-10">WD40</domain>
+                                 <domain from="1025" to="1064" confidence="3.1E-6">WD40</domain>
+                                 <domain from="1069" to="1107" confidence="1.5E-4">WD40</domain>
+                                 <domain from="1111" to="1149" confidence="7.9E-7">WD40</domain>
+                              </domain_architecture>
+                           </sequence>
+                        </clade>
+                        <clade>
+                           <name>18_NEMVE</name>
+                           <branch_length>0.38014</branch_length>
+                           <taxonomy>
+                              <code>NEMVE</code>
+                           </taxonomy>
+                           <sequence>
+                              <domain_architecture length="1290">
+                                 <domain from="7" to="90" confidence="1.5E-13">CARD</domain>
+                                 <domain from="117" to="200" confidence="5.4E-14">CARD</domain>
+                                 <domain from="216" to="517" confidence="1.5E-50">NB-ARC</domain>
+                                 <domain from="711" to="749" confidence="1.0E-7">WD40</domain>
+                                 <domain from="753" to="791" confidence="8.5E-12">WD40</domain>
+                                 <domain from="795" to="833" confidence="4.3E-11">WD40</domain>
+                                 <domain from="837" to="875" confidence="1.0E-12">WD40</domain>
+                                 <domain from="920" to="957" confidence="2.0E-4">WD40</domain>
+                                 <domain from="961" to="999" confidence="3.0E-6">WD40</domain>
+                                 <domain from="1085" to="1123" confidence="4.4E-6">WD40</domain>
+                                 <domain from="1128" to="1166" confidence="3.0E-4">WD40</domain>
+                                 <domain from="1170" to="1207" confidence="1.7E-10">WD40</domain>
+                              </domain_architecture>
+                           </sequence>
+                        </clade>
+                     </clade>
+                     <clade>
+                        <name>23_STRPU</name>
+                        <branch_length>0.48179</branch_length>
+                        <taxonomy>
+                           <code>STRPU</code>
+                        </taxonomy>
+                        <sequence>
+                           <domain_architecture length="1236">
+                              <domain from="110" to="402" confidence="1.0E-40">NB-ARC</domain>
+                              <domain from="594" to="632" confidence="8.9E-4">WD40</domain>
+                              <domain from="636" to="673" confidence="2.5E-6">WD40</domain>
+                              <domain from="721" to="759" confidence="0.0043">WD40</domain>
+                              <domain from="765" to="802" confidence="0.0036">WD40</domain>
+                              <domain from="848" to="886" confidence="9.0E-10">WD40</domain>
+                              <domain from="975" to="1013" confidence="1.9E-5">WD40</domain>
+                              <domain from="1015" to="1053" confidence="2.4E-6">WD40</domain>
+                              <domain from="1057" to="1095" confidence="2.7E-9">WD40</domain>
+                              <domain from="1099" to="1137" confidence="4.9E-8">WD40</domain>
+                              <domain from="1141" to="1177" confidence="0.011">WD40</domain>
+                           </domain_architecture>
+                        </sequence>
+                     </clade>
+                  </clade>
+               </clade>
+               <clade>
+                  <branch_length>0.34475</branch_length>
+                  <confidence type="unknown">100.0</confidence>
+                  <clade>
+                     <name>26_STRPU</name>
+                     <branch_length>0.36374</branch_length>
+                     <taxonomy>
+                        <code>STRPU</code>
+                     </taxonomy>
+                     <sequence>
+                        <domain_architecture length="1319">
+                           <domain from="18" to="98" confidence="3.4E-5">Death</domain>
+                           <domain from="189" to="481" confidence="1.8E-10">NB-ARC</domain>
+                           <domain from="630" to="668" confidence="8.2E-5">WD40</domain>
+                        </domain_architecture>
+                     </sequence>
+                  </clade>
+                  <clade>
+                     <name>25_STRPU</name>
+                     <branch_length>0.33137</branch_length>
+                     <taxonomy>
+                        <code>STRPU</code>
+                     </taxonomy>
+                     <sequence>
+                        <domain_architecture length="1947">
+                           <domain from="143" to="227" confidence="7.4E-5">Death</domain>
+                           <domain from="227" to="550" confidence="2.0E-13">NB-ARC</domain>
+                           <domain from="697" to="736" confidence="7.9E-4">WD40</domain>
+                           <domain from="745" to="785" confidence="1.5">WD40</domain>
+                           <domain from="1741" to="1836" confidence="2.0">Adeno_VII</domain>
+                        </domain_architecture>
+                     </sequence>
+                  </clade>
+               </clade>
+            </clade>
+            <clade>
+               <branch_length>1.31498</branch_length>
+               <confidence type="unknown">100.0</confidence>
+               <clade>
+                  <name>CED4_CAEEL</name>
+                  <branch_length>0.13241</branch_length>
+                  <taxonomy>
+                     <code>CAEEL</code>
+                  </taxonomy>
+                  <sequence>
+                     <domain_architecture length="714">
+                        <domain from="7" to="90" confidence="9.2E-14">CARD</domain>
+                        <domain from="116" to="442" confidence="5.8E-151">NB-ARC</domain>
+                     </domain_architecture>
+                  </sequence>
+               </clade>
+               <clade>
+                  <name>31_CAEBR</name>
+                  <branch_length>0.04777</branch_length>
+                  <taxonomy>
+                     <code>CAEBR</code>
+                  </taxonomy>
+                  <sequence>
+                     <domain_architecture length="554">
+                        <domain from="1" to="75" confidence="0.0046">CARD</domain>
+                        <domain from="101" to="427" confidence="2.1E-123">NB-ARC</domain>
+                     </domain_architecture>
+                  </sequence>
+               </clade>
+            </clade>
+         </clade>
+         <clade>
+            <branch_length>0.13172</branch_length>
+            <confidence type="unknown">45.0</confidence>
+            <clade>
+               <branch_length>0.24915</branch_length>
+               <confidence type="unknown">95.0</confidence>
+               <clade>
+                  <branch_length>0.76898</branch_length>
+                  <confidence type="unknown">100.0</confidence>
+                  <clade>
+                     <name>28_DROPS</name>
+                     <branch_length>0.1732</branch_length>
+                     <taxonomy>
+                        <code>DROPS</code>
+                     </taxonomy>
+                     <sequence>
+                        <domain_architecture length="535">
+                           <domain from="112" to="399" confidence="1.4E-5">NB-ARC</domain>
+                        </domain_architecture>
+                     </sequence>
+                  </clade>
+                  <clade>
+                     <name>Dark_DROME</name>
+                     <branch_length>0.18863</branch_length>
+                     <taxonomy>
+                        <code>DROME</code>
+                     </taxonomy>
+                     <sequence>
+                        <domain_architecture length="1421">
+                           <domain from="108" to="397" confidence="2.1E-5">NB-ARC</domain>
+                        </domain_architecture>
+                     </sequence>
+                  </clade>
+               </clade>
+               <clade>
+                  <name>29_AEDAE</name>
+                  <branch_length>0.86398</branch_length>
+                  <taxonomy>
+                     <code>AEDAE</code>
+                  </taxonomy>
+                  <sequence>
+                     <domain_architecture length="423">
+                        <domain from="109" to="421" confidence="9.3E-6">NB-ARC</domain>
+                     </domain_architecture>
+                  </sequence>
+               </clade>
+            </clade>
+            <clade>
+               <name>30_TRICA</name>
+               <branch_length>0.97698</branch_length>
+               <taxonomy>
+                  <code>TRICA</code>
+               </taxonomy>
+               <sequence>
+                  <domain_architecture length="1279">
+                     <domain from="5" to="81" confidence="0.59">CARD</domain>
+                     <domain from="92" to="400" confidence="9.0E-11">NB-ARC</domain>
+                     <domain from="630" to="668" confidence="1.1E-5">WD40</domain>
+                  </domain_architecture>
+               </sequence>
+            </clade>
+         </clade>
+      </clade>
+      <clade>
+         <branch_length>0.18105</branch_length>
+         <confidence type="unknown">89.0</confidence>
+         <clade>
+            <branch_length>0.15891</branch_length>
+            <confidence type="unknown">64.0</confidence>
+            <clade>
+               <branch_length>0.54836</branch_length>
+               <confidence type="unknown">100.0</confidence>
+               <clade>
+                  <branch_length>0.09305</branch_length>
+                  <confidence type="unknown">46.0</confidence>
+                  <clade>
+                     <branch_length>0.21648</branch_length>
+                     <confidence type="unknown">61.0</confidence>
+                     <clade>
+                        <branch_length>0.93134</branch_length>
+                        <confidence type="unknown">100.0</confidence>
+                        <clade>
+                           <name>34_BRAFL</name>
+                           <branch_length>0.093</branch_length>
+                           <taxonomy>
+                              <code>BRAFL</code>
+                           </taxonomy>
+                           <sequence>
+                              <domain_architecture length="752">
+                                 <domain from="49" to="356" confidence="9.0E-6">NB-ARC</domain>
+                              </domain_architecture>
+                           </sequence>
+                        </clade>
+                        <clade>
+                           <name>35_BRAFL</name>
+                           <branch_length>0.08226</branch_length>
+                           <taxonomy>
+                              <code>BRAFL</code>
+                           </taxonomy>
+                           <sequence>
+                              <domain_architecture length="753">
+                                 <domain from="25" to="105" confidence="0.16">DED</domain>
+                                 <domain from="113" to="409" confidence="1.1E-6">NB-ARC</domain>
+                              </domain_architecture>
+                           </sequence>
+                        </clade>
+                     </clade>
+                     <clade>
+                        <name>8_BRAFL</name>
+                        <branch_length>0.58563</branch_length>
+                        <taxonomy>
+                           <code>BRAFL</code>
+                        </taxonomy>
+                        <sequence>
+                           <domain_architecture length="916">
+                              <domain from="58" to="369" confidence="8.4E-7">NB-ARC</domain>
+                           </domain_architecture>
+                        </sequence>
+                     </clade>
+                  </clade>
+                  <clade>
+                     <branch_length>0.28437</branch_length>
+                     <confidence type="unknown">84.0</confidence>
+                     <clade>
+                        <name>20_NEMVE</name>
+                        <branch_length>0.71946</branch_length>
+                        <taxonomy>
+                           <code>NEMVE</code>
+                        </taxonomy>
+                        <sequence>
+                           <domain_architecture length="786">
+                              <domain from="8" to="91" confidence="1.7E-17">DED</domain>
+                              <domain from="8" to="85" confidence="0.37">PAAD_DAPIN</domain>
+                              <domain from="90" to="388" confidence="6.8E-5">NB-ARC</domain>
+                              <domain from="575" to="608" confidence="0.27">TPR_1</domain>
+                              <domain from="657" to="690" confidence="0.22">TPR_2</domain>
+                              <domain from="698" to="731" confidence="4.2E-5">TPR_2</domain>
+                           </domain_architecture>
+                        </sequence>
+                     </clade>
+                     <clade>
+                        <name>21_NEMVE</name>
+                        <branch_length>0.9571</branch_length>
+                        <taxonomy>
+                           <code>NEMVE</code>
+                        </taxonomy>
+                        <sequence>
+                           <domain_architecture length="1563">
+                              <domain from="234" to="317" confidence="2.3E-14">CARD</domain>
+                              <domain from="238" to="318" confidence="0.5">Death</domain>
+                              <domain from="329" to="619" confidence="0.022">NB-ARC</domain>
+                              <domain from="906" to="939" confidence="0.17">TPR_1</domain>
+                              <domain from="1326" to="1555" confidence="3.2E-26">RVT_1</domain>
+                           </domain_architecture>
+                        </sequence>
+                     </clade>
+                  </clade>
+               </clade>
+               <clade>
+                  <name>9_BRAFL</name>
+                  <branch_length>1.09612</branch_length>
+                  <taxonomy>
+                     <code>BRAFL</code>
+                  </taxonomy>
+                  <sequence>
+                     <domain_architecture length="1011">
+                        <domain from="5" to="321" confidence="5.0E-5">NB-ARC</domain>
+                        <domain from="497" to="616" confidence="1.6">BTAD</domain>
+                        <domain from="500" to="533" confidence="5.6E-4">TPR_1</domain>
+                        <domain from="542" to="575" confidence="0.43">TPR_1</domain>
+                        <domain from="626" to="659" confidence="0.0084">TPR_2</domain>
+                        <domain from="708" to="741" confidence="1.9E-4">TPR_2</domain>
+                        <domain from="708" to="739" confidence="1.3">TPR_3</domain>
+                        <domain from="708" to="733" confidence="0.16">TPR_4</domain>
+                        <domain from="833" to="916" confidence="5.6E-14">Death</domain>
+                        <domain from="846" to="868" confidence="0.36">LTXXQ</domain>
+                        <domain from="930" to="1011" confidence="8.3E-17">Death</domain>
+                     </domain_architecture>
+                  </sequence>
+               </clade>
+            </clade>
+            <clade>
+               <branch_length>0.34914</branch_length>
+               <confidence type="unknown">98.0</confidence>
+               <clade>
+                  <branch_length>0.22189</branch_length>
+                  <confidence type="unknown">95.0</confidence>
+                  <clade>
+                     <name>3_BRAFL</name>
+                     <branch_length>0.48766</branch_length>
+                     <taxonomy>
+                        <code>BRAFL</code>
+                     </taxonomy>
+                     <sequence>
+                        <domain_architecture length="2080">
+                           <domain from="116" to="423" confidence="1.4E-12">NB-ARC</domain>
+                           <domain from="620" to="659" confidence="1.4E-6">WD40</domain>
+                           <domain from="663" to="701" confidence="1.4E-8">WD40</domain>
+                           <domain from="705" to="743" confidence="3.0E-11">WD40</domain>
+                           <domain from="747" to="785" confidence="1.1E-8">WD40</domain>
+                           <domain from="788" to="826" confidence="1.6E-5">WD40</domain>
+                           <domain from="830" to="870" confidence="1.3E-4">WD40</domain>
+                           <domain from="874" to="914" confidence="6.2E-9">WD40</domain>
+                           <domain from="919" to="957" confidence="0.0011">WD40</domain>
+                           <domain from="961" to="1000" confidence="1.8E-8">WD40</domain>
+                           <domain from="1013" to="1051" confidence="1.3E-6">WD40</domain>
+                           <domain from="1055" to="1092" confidence="0.096">WD40</domain>
+                           <domain from="1794" to="1853" confidence="3.6E-4">Collagen</domain>
+                        </domain_architecture>
+                     </sequence>
+                  </clade>
+                  <clade>
+                     <name>2_BRAFL</name>
+                     <branch_length>0.65293</branch_length>
+                     <taxonomy>
+                        <code>BRAFL</code>
+                     </taxonomy>
+                     <sequence>
+                        <domain_architecture length="1691">
+                           <domain from="162" to="457" confidence="4.4E-10">NB-ARC</domain>
+                           <domain from="640" to="680" confidence="0.0068">WD40</domain>
+                           <domain from="684" to="722" confidence="1.6E-8">WD40</domain>
+                           <domain from="726" to="764" confidence="6.0E-9">WD40</domain>
+                           <domain from="827" to="865" confidence="6.9E-10">WD40</domain>
+                           <domain from="868" to="906" confidence="1.2E-6">WD40</domain>
+                           <domain from="910" to="950" confidence="0.0080">WD40</domain>
+                           <domain from="954" to="994" confidence="0.0016">WD40</domain>
+                           <domain from="999" to="1037" confidence="4.9E-6">WD40</domain>
+                           <domain from="1042" to="1080" confidence="6.3E-8">WD40</domain>
+                           <domain from="1100" to="1138" confidence="1.9E-8">WD40</domain>
+                           <domain from="1142" to="1178" confidence="1.4">WD40</domain>
+                           <domain from="1577" to="1615" confidence="4.3E-4">WD40</domain>
+                        </domain_architecture>
+                     </sequence>
+                  </clade>
+               </clade>
+               <clade>
+                  <name>19_NEMVE</name>
+                  <branch_length>0.57144</branch_length>
+                  <taxonomy>
+                     <code>NEMVE</code>
+                  </taxonomy>
+                  <sequence>
+                     <domain_architecture length="1649">
+                        <domain from="99" to="174" confidence="4.6E-7">DED</domain>
+                        <domain from="181" to="503" confidence="8.0E-13">NB-ARC</domain>
+                        <domain from="696" to="734" confidence="1.4E-8">WD40</domain>
+                        <domain from="738" to="776" confidence="2.9E-9">WD40</domain>
+                        <domain from="780" to="818" confidence="3.8E-10">WD40</domain>
+                        <domain from="822" to="860" confidence="6.4E-9">WD40</domain>
+                        <domain from="864" to="902" confidence="2.1E-10">WD40</domain>
+                        <domain from="906" to="944" confidence="1.3E-8">WD40</domain>
+                        <domain from="948" to="986" confidence="1.2E-8">WD40</domain>
+                        <domain from="990" to="1028" confidence="9.4E-8">WD40</domain>
+                        <domain from="1032" to="1070" confidence="6.0E-8">WD40</domain>
+                        <domain from="1074" to="1112" confidence="2.6E-4">WD40</domain>
+                        <domain from="1364" to="1597" confidence="1.9">SGL</domain>
+                        <domain from="1442" to="1480" confidence="9.7E-7">WD40</domain>
+                        <domain from="1527" to="1565" confidence="1.2">WD40</domain>
+                        <domain from="1568" to="1606" confidence="1.1E-6">WD40</domain>
+                     </domain_architecture>
+                  </sequence>
+               </clade>
+            </clade>
+         </clade>
+         <clade>
+            <branch_length>0.43438</branch_length>
+            <confidence type="unknown">92.0</confidence>
+            <clade>
+               <branch_length>0.92214</branch_length>
+               <confidence type="unknown">100.0</confidence>
+               <clade>
+                  <name>37_BRAFL</name>
+                  <branch_length>0.21133</branch_length>
+                  <taxonomy>
+                     <code>BRAFL</code>
+                  </taxonomy>
+                  <sequence>
+                     <domain_architecture length="1793">
+                        <domain from="6" to="89" confidence="9.6E-13">CARD</domain>
+                        <domain from="118" to="202" confidence="4.5E-9">CARD</domain>
+                        <domain from="206" to="491" confidence="0.0011">NB-ARC</domain>
+                        <domain from="238" to="388" confidence="0.0043">NACHT</domain>
+                     </domain_architecture>
+                  </sequence>
+               </clade>
+               <clade>
+                  <name>36_BRAFL</name>
+                  <branch_length>0.16225</branch_length>
+                  <taxonomy>
+                     <code>BRAFL</code>
+                  </taxonomy>
+                  <sequence>
+                     <domain_architecture length="918">
+                        <domain from="9" to="93" confidence="1.6E-9">CARD</domain>
+                        <domain from="98" to="403" confidence="0.0019">NB-ARC</domain>
+                     </domain_architecture>
+                  </sequence>
+               </clade>
+            </clade>
+            <clade>
+               <name>33_BRAFL</name>
+               <branch_length>0.8363</branch_length>
+               <taxonomy>
+                  <code>BRAFL</code>
+               </taxonomy>
+               <sequence>
+                  <domain_architecture length="1212">
+                     <domain from="5" to="87" confidence="4.7E-12">Death</domain>
+                     <domain from="154" to="465" confidence="2.0E-6">NB-ARC</domain>
+                  </domain_architecture>
+               </sequence>
+            </clade>
+         </clade>
+      </clade>
+   </clade>
+</phylogeny>
+</phyloxml>