mesh-medical-subject-headings 2.0.6 → 2.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 65d7558eb1ce2fd0321a053021badccd5a8c3843
-  data.tar.gz: 3c8cb444d84df8d11c7e7a625436f56b743b7a24
+  metadata.gz: a2aca8f7e1eceac511966cc2a886258c2bc81c19
+  data.tar.gz: 1c3f83c62564d794239a05084b099dd0160da13b
 SHA512:
-  metadata.gz: 903e6e353b7fa48427e8b5e9f63e43bb8e8882fac4d0830088cea7decf0ca0fe967acb36f8ed55f0087268a480ac85e48ec5369434975a36ae29cdedfadfee7b
-  data.tar.gz: d79445bd35b3530d77ee4a578848dd18da766f2bd23f6797709b2b7fa5776afbdb6f65929c4b6266afaa90d368b99ecc7cbfbd206d6c9fbc4cabfd52127d07f8
+  metadata.gz: b06e343f36965d05b05a4689abfe316430f0b4a069432e51609dbbf15b0426edcbad038f129410b6b20d561617472cec601aa1e14c7589683149ec9a6b08183d
+  data.tar.gz: 7b8dd6e676a376ce773100cec77e7e1ab923492016d375be9af071ac08895bfa5a9e9c4f94e31376ef4a5f2205308638fec9228c940758c85829f58027238b0d

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+#2.1.0 / 2014-07-04
+* [FEATURE] Headings matched with Wikipedia, infobox images and abstracts imported
+
 #2.0.6 / 2014-06-26
 * [BUGFIX] Match on summary links with hyphens in
 

data/Gemfile.lock

@@ -1,15 +1,18 @@
 PATH
   remote: .
   specs:
-    mesh-medical-subject-headings (2.0.6)
+    mesh-medical-subject-headings (2.1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
     metaclass (0.0.4)
+    mini_portile (0.6.0)
     minitest (5.0.8)
     mocha (1.0.0)
       metaclass (~> 0.0.1)
+    nokogiri (1.6.2.1)
+      mini_portile (= 0.6.0)
     rake (10.2.2)
     ruby-prof (0.14.2)
     yard (0.8.7.4)
@@ -22,6 +25,7 @@ DEPENDENCIES
   mesh-medical-subject-headings!
   minitest (~> 5.0.8)
   mocha
+  nokogiri
   rake
   ruby-prof
   yard

data/MESH.gemspec

@@ -24,4 +24,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency 'yard'
   spec.add_development_dependency 'minitest', '~> 5.0.8'
   spec.add_development_dependency 'ruby-prof'
+  spec.add_development_dependency 'nokogiri'
 end

data/bin/extract_wikipedia_abstracts

@@ -0,0 +1,111 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/MESH'
+require 'json'
+require 'nokogiri'
+
+class Wikidoc < Nokogiri::XML::SAX::Document
+
+  def initialize(links_by_uri)
+    super()
+    @links_by_uri = links_by_uri
+  end
+
+  def start_element name, attrs = []
+    @elements ||= []
+    @elements.push(name)
+    if name == 'doc'
+      @current_title = ''
+      @current_abstract = ''
+      @current_url = ''
+    end
+  end
+
+  def characters string
+    if @elements.last == 'title'
+      @current_title = string
+    elsif @elements.last == 'abstract'
+      @current_abstract = string
+    elsif @elements.last == 'url'
+      @current_url = string
+    end
+  end
+
+  def end_element name
+    if name == 'doc' && @links_by_uri[@current_url]
+      STDERR.print '.'
+      @links_by_uri[@current_url].each do |l|
+        title = @current_title.gsub(/^Wikipedia: /, '')
+        l[:title] = title
+        l[:abstract] = @current_abstract
+        # puts l
+      end
+    elsif name == 'doc'
+      STDERR.print '-'
+    end
+    @elements.pop
+  end
+
+end
+
+filename = File.expand_path("../../data/mesh_data_2014/d2014.wikipedia.bin.gz", __FILE__)
+gzipped_file = File.open(filename)
+file = Zlib::GzipReader.new(gzipped_file)
+
+unique_id = nil
+mh = nil
+wikipedia_links = []
+by_uri = {}
+headings = []
+
+file.each_line do |line|
+
+  case
+
+    when line.match(/^\*NEWRECORD$/)
+      unless unique_id.nil?
+        hash = {
+          ui: unique_id,
+          mh: mh,
+          wikipedia_links: wikipedia_links
+        }
+
+        headings << hash
+
+        wikipedia_links.each do |wl|
+          by_uri[wl[:link]] ||= []
+          by_uri[wl[:link]] << wl
+        end
+
+        wikipedia_links = []
+        unique_id = nil
+        mh = nil
+      end
+
+    when matches = line.match(/^UI = (.*)/)
+      unique_id = matches[1]
+
+    when matches = line.match(/^MH = (.*)/)
+      mh = matches[1]
+
+    when matches = line.match(/^WK = (.*)/)
+      score, link, image = matches[1].split ';'
+      hash = {score: score, link: link.strip}
+      hash[:image] = image.strip unless image.nil?
+      wikipedia_links << hash
+  end
+
+end
+
+parser = Nokogiri::XML::SAX::Parser.new(Wikidoc.new(by_uri))
+parser.parse(File.open(ARGV[0]))
+
+headings.each do |h|
+  puts '*NEWRECORD'
+  puts "UI = #{h[:ui]}"
+  puts "MH = #{h[:mh]}"
+  h[:wikipedia_links].each do |wl|
+    puts "WK = #{wl.to_json}"
+  end
+  puts ''
+end

data/bin/match_wikipedia

@@ -0,0 +1,53 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/MESH'
+require 'net/http'
+require 'nokogiri'
+require 'uri'
+
+mesh_tree = MESH::Tree.new
+
+def sluggify(name)
+  CGI.escape(name.downcase.gsub(/\s/, '_').capitalize)
+end
+
+count = 0
+mesh_tree.each do |h|
+  count += 1
+
+  candidates = {}
+  images = {}
+  h.entries.each do |e|
+
+    slug = sluggify(e)
+    uri = URI.parse("http://en.wikipedia.org/wiki/#{slug}")
+    response = Net::HTTP.get_response(uri)
+    if response.code == '200'
+      doc = Nokogiri::HTML(response.body)
+      # heading = doc.css('#firstHeading > span')
+      canonical = doc.xpath('/html/head/link[@rel="canonical"]/@href')
+      candidates[canonical.text] ||= 0
+      candidates[canonical.text] += 1
+      img_node = doc.xpath('(//table[@class="infobox"]//img)[1]/@src')
+      images[canonical.text] ||= img_node.text unless img_node.nil?
+    end
+
+    sleep 0.1
+  end
+
+  best_candidates = candidates.reduce({}) { |h, (k, v)| (h[v] ||= []) << k; h }.max
+  if best_candidates && !best_candidates.empty?
+    score, candidates = best_candidates
+    puts "UI = #{h.unique_id}"
+    puts "MH = #{h.original_heading}"
+    puts "ENTRIES = #{h.entries.join(' -- ')}"
+    candidates.each do |c|
+      puts "WK = #{score}; #{c}"
+      puts "WI = #{images[c]}" unless images[c].nil? || images[c].empty?
+    end
+    puts ''
+    STDOUT.flush
+  end
+
+
+end

data/bin/translate

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/MESH'
+
+mesh_tree = MESH::Tree.new
+tr = MESH::Translator.new(MESH::Translator.enus_to_engb)
+
+mesh_tree.each do |h|
+  puts "*NEWRECORD"
+  puts "MH = #{tr.translate(h.original_heading)}"
+  puts "MS = #{tr.translate(h.summary)}"
+  h.entries.each { |e| puts "ENTRY = #{tr.translate(e)}" }
+  puts "UI = #{h.unique_id}"
+  puts ''
+end

data/lib/MESH.rb

@@ -1,6 +1,8 @@
+require 'json'
 require 'zlib'
 require 'MESH/version'
 require 'MESH/tree'
 require 'MESH/heading'
 require 'MESH/translator'
 require 'MESH/classifier'
+require 'MESH/semantic_types'

data/lib/MESH/heading.rb

@@ -2,7 +2,7 @@ module MESH
   class Heading
 
     include Comparable
-    attr_accessor :unique_id, :tree_numbers, :roots, :parents, :children, :useful, :descriptor_class, :default_locale
+    attr_accessor :unique_id, :tree_numbers, :roots, :parents, :children, :useful, :descriptor_class, :default_locale, :semantic_types, :wikipedia_links
     attr_reader :linkified_summary
 
     def <=> other
@@ -107,6 +107,7 @@ module MESH
       @tree = tree
       @useful = true
       @tree_numbers = []
+      @semantic_types = []
       @roots = []
       @parents = []
       @children = []
@@ -114,6 +115,7 @@ module MESH
       @original_heading = {}
       @natural_language_name = {}
       @summary = {}
+      @wikipedia_links = []
     end
 
 

data/lib/MESH/semantic_types.rb

@@ -0,0 +1,146 @@
+module MESH
+  class SemanticTypes
+
+    def self.[](key)
+      Types[key]
+    end
+
+    Types = {
+      'T001' => 'Organism',
+      'T002' => 'Plant',
+      'T003' => 'Alga',
+      'T004' => 'Fungus',
+      'T005' => 'Virus',
+      'T006' => 'Rickettsia or Chlamydia',
+      'T007' => 'Bacterium',
+      'T008' => 'Animal',
+      'T009' => 'Invertebrate',
+      'T010' => 'Vertebrate',
+      'T011' => 'Amphibian',
+      'T012' => 'Bird',
+      'T013' => 'Fish',
+      'T014' => 'Reptile',
+      'T015' => 'Mammal',
+      'T016' => 'Human',
+      'T017' => 'Anatomical Structure',
+      'T018' => 'Embryonic Structure',
+      'T019' => 'Congenital Abnormality',
+      'T020' => 'Acquired Abnormality',
+      'T021' => 'Fully Formed Anatomical Structure',
+      'T022' => 'Body System',
+      'T023' => 'Body Part, Organ, or Organ Component',
+      'T024' => 'Tissue',
+      'T025' => 'Cell',
+      'T026' => 'Cell Component',
+      'T028' => 'Gene or Genome',
+      'T029' => 'Body Location or Region',
+      'T030' => 'Body Space or Junction',
+      'T031' => 'Body Substance',
+      'T032' => 'Organism Attribute',
+      'T033' => 'Finding',
+      'T034' => 'Laboratory or Test Result',
+      'T037' => 'Injury or Poisoning',
+      'T038' => 'Biologic Function',
+      'T039' => 'Physiologic Function',
+      'T040' => 'Organism Function',
+      'T041' => 'Mental Process',
+      'T042' => 'Organ or Tissue Function',
+      'T043' => 'Cell Function',
+      'T044' => 'Molecular Function',
+      'T045' => 'Genetic Function',
+      'T046' => 'Pathologic Function',
+      'T047' => 'Disease or Syndrome',
+      'T048' => 'Mental or Behavioral Dysfunction',
+      'T049' => 'Cell or Molecular Dysfunction',
+      'T050' => 'Experimental Model of Disease',
+      'T051' => 'Event',
+      'T052' => 'Activity',
+      'T053' => 'Behavior',
+      'T054' => 'Social Behavior',
+      'T055' => 'Individual Behavior',
+      'T056' => 'Daily or Recreational Activity',
+      'T057' => 'Occupational Activity',
+      'T058' => 'Health Care Activity',
+      'T059' => 'Laboratory Procedure',
+      'T060' => 'Diagnostic Procedure',
+      'T061' => 'Therapeutic or Preventive Procedure',
+      'T062' => 'Research Activity',
+      'T063' => 'Molecular Biology Research Technique',
+      'T064' => 'Governmental or Regulatory Activity',
+      'T065' => 'Educational Activity',
+      'T066' => 'Machine Activity',
+      'T067' => 'Phenomenon or Process',
+      'T068' => 'Human-caused Phenomenon or Process',
+      'T069' => 'Environmental Effect of Humans',
+      'T070' => 'Natural Phenomenon or Process',
+      'T071' => 'Entity',
+      'T072' => 'Physical Object',
+      'T073' => 'Manufactured Object',
+      'T074' => 'Medical Device',
+      'T075' => 'Research Device',
+      'T077' => 'Conceptual Entity',
+      'T078' => 'Idea or Concept',
+      'T079' => 'Temporal Concept',
+      'T080' => 'Qualitative Concept',
+      'T081' => 'Quantitative Concept',
+      'T082' => 'Spatial Concept',
+      'T083' => 'Geographic Area',
+      'T085' => 'Molecular Sequence',
+      'T086' => 'Nucleotide Sequence',
+      'T087' => 'Amino Acid Sequence',
+      'T088' => 'Carbohydrate Sequence',
+      'T089' => 'Regulation or Law',
+      'T090' => 'Occupation or Discipline',
+      'T091' => 'Biomedical Occupation or Discipline',
+      'T092' => 'Organization',
+      'T093' => 'Health Care Related Organization',
+      'T094' => 'Professional Society',
+      'T095' => 'Self-help or Relief Organization',
+      'T096' => 'Group',
+      'T097' => 'Professional or Occupational Group',
+      'T098' => 'Population Group',
+      'T099' => 'Family Group',
+      'T100' => 'Age Group',
+      'T101' => 'Patient or Disabled Group',
+      'T102' => 'Group Attribute',
+      'T103' => 'Chemical',
+      'T104' => 'Chemical Viewed Structurally',
+      'T109' => 'Organic Chemical',
+      'T110' => 'Steroid',
+      'T111' => 'Eicosanoid',
+      'T114' => 'Nucleic Acid, Nucleoside, or Nucleotide',
+      'T115' => 'Organophosphorus Compound',
+      'T116' => 'Amino Acid, Peptide, or Protein',
+      'T118' => 'Carbohydrate',
+      'T119' => 'Lipid',
+      'T120' => 'Chemical Viewed Functionally',
+      'T121' => 'Pharmacologic Substance',
+      'T122' => 'Biomedical or Dental Material',
+      'T123' => 'Biologically Active Substance',
+      'T124' => 'Neuroreactive Substance or Biogenic Amine',
+      'T125' => 'Hormone',
+      'T126' => 'Enzyme',
+      'T127' => 'Vitamin',
+      'T129' => 'Immunologic Factor',
+      'T130' => 'Indicator, Reagent, or Diagnostic Aid',
+      'T131' => 'Hazardous or Poisonous Substance',
+      'T167' => 'Substance',
+      'T168' => 'Food',
+      'T169' => 'Functional Concept',
+      'T170' => 'Intellectual Product',
+      'T171' => 'Language',
+      'T184' => 'Sign or Symptom',
+      'T185' => 'Classification',
+      'T190' => 'Anatomical Abnormality',
+      'T191' => 'Neoplastic Process',
+      'T192' => 'Receptor',
+      'T194' => 'Archaeon',
+      'T195' => 'Antibiotic',
+      'T196' => 'Element, Ion, or Isotope',
+      'T197' => 'Inorganic Chemical',
+      'T200' => 'Clinical Drug',
+      'T201' => 'Clinical Attribute'
+    }
+
+  end
+end

data/lib/MESH/tree.rb

@@ -24,7 +24,7 @@ module MESH
 
         case
 
-          when matches = line.match(/^\*NEWRECORD$/)
+          when line.match(/^\*NEWRECORD$/)
             unless current_heading.unique_id.nil?
               current_heading.entries.sort!
               @headings << current_heading
@@ -56,6 +56,9 @@ module MESH
           when matches = line.match(/^DC = (.*)/)
             current_heading.descriptor_class = @@descriptor_classes[matches[1].to_i]
 
+          when matches = line.match(/^ST = (.*)/)
+            current_heading.semantic_types << MESH::SemanticTypes[matches[1]]
+
           when matches = line.match(/^MH = (.*)/)
             mh = matches[1]
             current_heading.set_original_heading(mh)
@@ -107,7 +110,7 @@ module MESH
 
         case
 
-          when matches = line.match(/^\*NEWRECORD$/)
+          when line.match(/^\*NEWRECORD$/)
             unless unique_id.nil?
               entries.sort!
               entries.uniq!
@@ -147,6 +150,45 @@ module MESH
       @locales << locale
     end
 
+    def load_wikipedia
+      return if @wikipedia_loaded
+      filename = File.expand_path("../../../data/mesh_data_2014/d2014.wikipedia.bin.gz", __FILE__)
+      gzipped_file = File.open(filename)
+      file = Zlib::GzipReader.new(gzipped_file)
+
+      unique_id = nil
+      wikipedia_links = []
+      file.each_line do |line|
+
+        case
+
+          when line.match(/^\*NEWRECORD$/)
+            unless unique_id.nil?
+              if heading = find(unique_id)
+                wikipedia_links.each do |wl|
+                  wl[:score] = (wl[:score].to_f / heading.entries.length.to_f).round(2)
+                end
+                heading.wikipedia_links = wikipedia_links
+              end
+
+              wikipedia_links = []
+              unique_id = nil
+            end
+
+          when matches = line.match(/^UI = (.*)/)
+            unique_id = matches[1]
+
+          when matches = line.match(/^WK = (.*)/)
+            hash = JSON.parse(matches[1], symbolize_names: true)
+            wikipedia_links << hash
+
+        end
+
+      end
+      @wikipedia_loaded = true
+    end
+
+
     def linkify_summaries &block
       @headings.each do |h|
         h.linkify_summary &block

data/lib/MESH/version.rb

@@ -1,3 +1,3 @@
 module Mesh
-  VERSION = "2.0.6"
+  VERSION = "2.1.0"
 end

data/test/mesh_core_test.rb

@@ -105,6 +105,16 @@ module MESH
       assert_equal :check_tag, mh.descriptor_class
     end
 
+    def test_have_the_correct_semantic_type
+      mh = @mesh_tree.find('D000224')
+      assert_equal ['Disease or Syndrome'], mh.semantic_types
+      mh = @mesh_tree.find('D005260')
+      assert_equal ['Organism Attribute'], mh.semantic_types
+      mh = @mesh_tree.find('D014148')
+      assert_equal ['Organic Chemical', 'Pharmacologic Substance'], mh.semantic_types
+
+    end
+
     def test_have_the_correct_original_heading
       mh = @mesh_tree.find('D000224')
       assert_equal 'Addison Disease', mh.original_heading
@@ -219,6 +229,95 @@ module MESH
       assert_equal expected_entries_en.sort, mh.entries(:en_gb)
     end
 
+    def test_have_a_single_wikipedia_link
+
+      expected = {
+        'D000001' => 'http://en.wikipedia.org/wiki/A23187',
+        'D000005' => 'http://en.wikipedia.org/wiki/Abdomen',
+        'D000082' => 'http://en.wikipedia.org/wiki/Paracetamol'
+      }
+
+      expected.each do |id, expected_link|
+        mh = @mesh_tree.find(id)
+        assert_equal 1, mh.wikipedia_links.length
+        assert_equal expected_link, mh.wikipedia_links[0][:link]
+      end
+
+    end
+
+    def test_have_a_single_wikipedia_score
+      expected = {
+        'D000001' => 0.5,
+        'D000005' => 1.0,
+        'D000082' => 0.35
+      }
+
+      expected.each do |id, expected_score|
+        mh = @mesh_tree.find(id)
+        assert_equal 1, mh.wikipedia_links.length
+        assert_equal expected_score, mh.wikipedia_links[0][:score]
+      end
+
+    end
+
+    def test_have_a_single_wikipedia_image
+      expected = {
+        'D000001' => 'http://upload.wikimedia.org/wikipedia/commons/thumb/1/17/A23187.png/220px-A23187.png',
+        'D000005' => 'http://upload.wikimedia.org/wikipedia/commons/thumb/3/3b/Abdomen_%28PSF%29.jpg/250px-Abdomen_%28PSF%29.jpg',
+        'D000082' => 'http://upload.wikimedia.org/wikipedia/commons/thumb/2/29/Paracetamol-skeletal.svg/150px-Paracetamol-skeletal.svg.png'
+      }
+
+      expected.each do |id, expected_image|
+        mh = @mesh_tree.find(id)
+        assert_equal 1, mh.wikipedia_links.length
+        assert_equal expected_image, mh.wikipedia_links[0][:image]
+      end
+    end
+
+    def test_have_a_single_wikipedia_abstract
+      expected = {
+        'D000001' => '| CAS_number = 52665-69-7',
+        'D000005' => 'The abdomen (less formally called the belly, stomach, or tummy), in vertebrates such as mammals, constitutes the part of the body between the thorax (chest) and pelvis. The region enclosed by the abdomen is termed the abdominal cavity.',
+        'D000082' => '| MedlinePlus = a681004'
+      }
+
+      expected.each do |id, expected_abstract|
+        mh = @mesh_tree.find(id)
+        assert_equal 1, mh.wikipedia_links.length
+        assert_equal expected_abstract, mh.wikipedia_links[0][:abstract]
+      end
+    end
+
+    def test_have_more_than_one_wikipedia_link
+      mh = @mesh_tree.find('D000100')
+      expected = %w(
+        http://en.wikipedia.org/wiki/Sodium_acetrizoate
+        http://en.wikipedia.org/wiki/Acetrizoic_acid
+      )
+      assert_equal expected, mh.wikipedia_links.map { |l| l[:link] }
+    end
+
+    def test_have_more_than_one_wikipedia_score
+      mh = @mesh_tree.find('D000100')
+      expected = [0.09, 0.09]
+      assert_equal expected, mh.wikipedia_links.map { |l| l[:score] }
+    end
+
+    def test_have_more_than_one_wikipedia_image
+      mh = @mesh_tree.find('D000100')
+      expected = %w(
+        http://upload.wikimedia.org/wikipedia/commons/thumb/4/4d/Sodium_acetrizoate.svg/150px-Sodium_acetrizoate.svg.png
+        http://upload.wikimedia.org/wikipedia/commons/thumb/2/26/Acetrizoic_acid.png/220px-Acetrizoic_acid.png
+      )
+      assert_equal expected, mh.wikipedia_links.map { |l| l[:image] }
+    end
+
+    def test_have_more_than_one_wikipedia_abstract
+      mh = @mesh_tree.find('D000100')
+      expected = ['| CAS_number = 129-63-5', '| CAS_number = 85-36-9']
+      assert_equal expected, mh.wikipedia_links.map { |l| l[:abstract] }
+    end
+
     def test_have_the_correct_parent
       mh = @mesh_tree.find('D000001')
       assert_equal 1, mh.parents.length
@@ -578,6 +677,7 @@ module MESH
     def setup
       @@mesh_tree ||= MESH::Tree.new
       @@mesh_tree.load_translation(:en_gb)
+      @@mesh_tree.load_wikipedia
       @mesh_tree = @@mesh_tree
       @example_text ||= 'Leukaemia in Downs Syndrome
 Overview

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: mesh-medical-subject-headings
 version: !ruby/object:Gem::Version
-  version: 2.0.6
+  version: 2.1.0
 platform: ruby
 authors:
 - Rob Styles
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-26 00:00:00.000000000 Z
+date: 2014-07-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -94,6 +94,20 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A ruby gem containing MeSH subject headings (https://www.nlm.nih.gov/mesh/)
   for use in classifying and entity recognition.
 email:
@@ -111,14 +125,19 @@ files:
 - MESH.gemspec
 - README.md
 - Rakefile
+- bin/extract_wikipedia_abstracts
+- bin/match_wikipedia
+- bin/translate
 - data/mesh_data_2014/c2014.bin.gz
 - data/mesh_data_2014/d2014.bin.gz
 - data/mesh_data_2014/d2014.en_gb.bin.gz
+- data/mesh_data_2014/d2014.wikipedia.bin.gz
 - data/mesh_data_2014/mtrees2014.bin.gz
 - data/mesh_data_2014/q2014.bin.gz
 - lib/MESH.rb
 - lib/MESH/classifier.rb
 - lib/MESH/heading.rb
+- lib/MESH/semantic_types.rb
 - lib/MESH/translator.rb
 - lib/MESH/tree.rb
 - lib/MESH/version.rb