pubchem 0.0.5 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cc1a04a9f940becd4f4eff582d8105d6f3772eed
-  data.tar.gz: 224b9440fe38fcfa39fe9b360a2f32a9e145b27f
+  metadata.gz: 8c55a845631951401782b0af20e268b9181e3ca8
+  data.tar.gz: d70a2f0fddefa25016b76d0442b6c4d8d07b8884
 SHA512:
-  metadata.gz: 6f72420e95796c668a1154877ef5ad2455569e00fbf618ee2ebfc5256433fbcf0cb0471d67ecf2044bce075f0dbf9a59f769610026620936a74dc488fa8a0e22
-  data.tar.gz: 297ba5d561ed323425c6c5804eceb035d17baf2c8865acf7b4bade28ccb544b32dd79a6e9f319c92acc5bdd45e1e0d1a075648779fcd1598104d36db34acc62a
+  metadata.gz: f9a1f1bbcb944abdace6ab61745620c329258072da9d29c6a2d2266d57fe64847dc45a7ec10882b604e8c4988191cb033253280aedf3262d9ff591f75ad1ea84
+  data.tar.gz: 925506e71420d361b5c776233676a37aea0aab3a7694f20f77ca7e991ec96dde527f8b0731a0a8c57e8a51d29b78dbf77b86813f97ba8634187a63a2a746ed38

data/.gitignore

@@ -0,0 +1,4 @@
+pkg
+xml
+!xml/substance_sample.xml
+!xml/compound_sample.xml

data/Gemfile.lock

@@ -0,0 +1,52 @@
+PATH
+  remote: .
+  specs:
+    pubchem (0.1.1)
+      fuzzy-string-match (~> 0.9.7)
+      mechanize (~> 2.7.3)
+      nokogiri (~> 1.6.6.2)
+      ox (~> 2.2.1)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    RubyInline (3.12.4)
+      ZenTest (~> 4.3)
+    ZenTest (4.11.0)
+    domain_name (0.5.24)
+      unf (>= 0.0.5, < 1.0.0)
+    fuzzy-string-match (0.9.7)
+      RubyInline (>= 3.8.6)
+    http-cookie (1.0.2)
+      domain_name (~> 0.5)
+    mechanize (2.7.3)
+      domain_name (~> 0.5, >= 0.5.1)
+      http-cookie (~> 1.0)
+      mime-types (~> 2.0)
+      net-http-digest_auth (~> 1.1, >= 1.1.1)
+      net-http-persistent (~> 2.5, >= 2.5.2)
+      nokogiri (~> 1.4)
+      ntlm-http (~> 0.1, >= 0.1.1)
+      webrobots (>= 0.0.9, < 0.2)
+    mime-types (2.6.1)
+    mini_portile (0.6.2)
+    net-http-digest_auth (1.4)
+    net-http-persistent (2.9.4)
+    nokogiri (1.6.6.2)
+      mini_portile (~> 0.6.0)
+    ntlm-http (0.1.1)
+    ox (2.2.1)
+    unf (0.1.4)
+      unf_ext
+    unf_ext (0.0.7.1)
+    webrobots (0.1.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.10)
+  pubchem!
+
+BUNDLED WITH
+   1.10.3

data/README.markdown

@@ -2,22 +2,18 @@
 
 For getting all that juicy substance and compound data from Pubchem.
 
-## Installation
+Please email me if you end up using this: zachaysan@gmail.com
+
+I'd be interested to hear if open sourcing this helped someone else.
 
-`apt-get install wget`
+## Installation
 
-Or
+`apt-get install wget` or `sudo apt-get install wget`
 
-`sudo apt-get install wget`
+then
 
 `gem install pubchem`
 
 ## Usage
 
-```ruby
-pubchem = Pubchem.new
-
-pubchem.get_ids([16,405], "~/yay.zip")
-
-puts "Do a happy dance!"
-```
+See `example.rb` for how to use Pubchem.

data/example.rb

@@ -1,7 +1,28 @@
+require 'pp'
 require_relative "lib/pubchem"
 
+reader = Reader.new
+reader.read('xml/compound_sample.xml')
+reader.read('xml/substance_sample.xml')
+reader.save("xml/names.xml",
+            "xml/pubchem_substance_ids.xml",
+            "xml/pubchem_compound_ids.xml")
+
+# The first two terms match, the last one replaces a "1H"
+# with a "2H", resulting in a non-match.
+
+terms = [ "COC1=C(C=C2CC3=CC(=C(C=C3CC4=CC(=C(C=C4CC2=C1)OC(=O)C5=CC=NC=C5)OC)OC(=O)C6=CC=NC=C6)OC)OC(=O)C7=CC=NC=E9",
+          "4-methoxy-1H-indole-3-carbaldehyde",
+          "4-methoxy-2H-indole-3-carbaldehyde",
+          "2-amino-4,5-dimethyl-1H-pyrrole-3-carbonitrile" ]
+
+pp reader.match_list_of_names terms
+pp reader.retrieve_compound_ids
+pp reader.pubchem_substance_ids
 pubchem = Pubchem.new
 
-pubchem.get_ids([16,405], "~/yay.zip")
+ids = reader.retrieve_substance_ids.map {|k,v| v}
+
+pubchem.get_substance_ids(ids, "yay.zip")
 
 puts "Do a happy dance!"

data/lib/pubchem.rb

@@ -1,4 +1,5 @@
 require 'mechanize'
+require_relative 'pubchem/reader'
 
 class Pubchem
 
@@ -13,9 +14,26 @@ class Pubchem
 
   end
 
+  def get_compound_ids(ids,
+                       filename,
+                       retrieve_mode: :image,
+                       delay: nil)
+
+    self.get_ids(ids, filename, :compound, delay: delay)
+  end
+
+  def get_substance_ids(ids,
+                       filename,
+                       retrieve_mode: :image,
+                       delay: nil)
+
+    self.get_ids(ids, filename, :substance, delay: delay)
+
+  end
+
   def get_ids(ids,
               filename,
-              db: :compound,
+              db,
               retrieve_mode: :image,
               delay: nil)
 
@@ -46,9 +64,9 @@ class Pubchem
 
       ftp_url = ftp_link.to_s
       size = ftp_url.size
-  
+
       # We don't want to allow scary characters into our URL since it is a
-      # security risk, so we only allow lower and upper case letters, numbers, 
+      # security risk, so we only allow lower and upper case letters, numbers,
       # /   forward slashes
       # :   colons
       # .   periods

data/lib/pubchem/reader.rb

@@ -0,0 +1,223 @@
+require 'set'
+require 'nokogiri'
+require 'fuzzystringmatch'
+require 'ox'
+
+class Reader
+
+  attr_accessor :names,
+                :pubchem_substance_ids,
+                :pubchem_compound_ids
+
+  def initialize(names_filename=nil,
+                 pubchem_substance_ids_filename=nil,
+                 pubchem_compound_ids_filename=nil)
+
+    @fuzzy_matcher = FuzzyStringMatch::JaroWinkler
+                     .create( :native )
+
+    return if initialize_from_files( names_filename,
+                                     pubchem_substance_ids_filename,
+                                     pubchem_compound_ids_filename )
+
+    @names = Hash.new { |h,k| h[k] = Set.new }
+
+    @pubchem_substance_ids = Hash.new { |h,k| h[k] = Set.new }
+    @pubchem_compound_ids = Hash.new  { |h,k| h[k] = Set.new }
+
+  end
+
+  def initialize_from_files(names_filename,
+                            pubchem_substance_ids_filename,
+                            pubchem_compound_ids_filename)
+
+    filenames = [ names_filename,
+                  pubchem_substance_ids_filename,
+                  pubchem_compound_ids_filename ]
+
+    return nil unless filenames.any?
+    raise "Both filenames required" unless filenames.all?
+
+    @names = Ox.load_file(names_filename)
+    @pubchem_substance_ids = Ox.load_file(pubchem_substance_ids_filename)
+    @pubchem_compound_ids = Ox.load_file(pubchem_compound_ids_filename)
+
+  end
+
+  def save(names_filename,
+           pubchem_substance_ids_filename,
+           pubchem_compound_ids_filename)
+
+    Ox.to_file(names_filename, @names, indent: 0)
+    Ox.to_file(pubchem_substance_ids_filename, @pubchem_substance_ids, indent: 0)
+    Ox.to_file(pubchem_compound_ids_filename, @pubchem_compound_ids, indent: 0)
+
+  end
+
+  def read(xml_filepath, type: nil)
+
+    filepath = File.basename(xml_filepath)
+    if type.nil? and filepath.downcase.start_with? "compound"
+      type = :compound
+    elsif type.nil? and filepath.downcase.start_with? "substance"
+      type = :substance
+    else
+      raise "Cannot infer pubchem type"
+    end
+
+    f = File.open(xml_filepath)
+    doc = Nokogiri::XML(f)
+    f.close
+    @current_type = type.to_s
+    case type
+    when :compound
+      doc.css("PC-Compounds PC-Compound").each do |compound|
+        self.parse_compound(compound)
+      end
+    when :substance
+      doc.css("PC-Substances PC-Substance").each do |substance|
+        self.parse_substance(substance)
+      end
+    else
+      raise "Unknown type"
+    end
+
+  end
+
+  def parse_compound(compound)
+
+    @pubchem_id = compound.css("PC-Compound_id
+                                PC-CompoundType
+                                PC-CompoundType_id
+                                PC-CompoundType_id_cid").text.to_i
+
+    compound.css("PC-Compound_props").each do |property|
+      self.parse_property(property)
+    end
+
+  end
+
+  def parse_substance(substance)
+
+
+    @pubchem_id = substance.css("PC-Substance_sid
+                                 PC-ID
+                                 PC-ID_id").text.to_i
+
+    substance.css("PC-Substance_synonyms
+                   PC-Substance_synonyms_E").each do |substance_synonym|
+      self.add_name(substance_synonym.text)
+    end
+
+  end
+
+  def parse_property(property)
+
+    property.css("PC-InfoData").each do |info_data|
+      parse_info_data(info_data)
+    end
+
+  end
+
+  def parse_info_data(info_data)
+
+    urn_label = info_data.css("PC-InfoData_urn
+                               PC-Urn
+                               PC-Urn_label").first.text
+    name = nil
+    case urn_label
+    when "SMILES"
+      name = info_data.css("PC-InfoData_value
+                            PC-InfoData_value_sval").first.text
+    when"IUPAC Name"
+      name = info_data.css("PC-InfoData_value
+                            PC-InfoData_value_sval").first.text
+    end
+
+    self.add_name(name)
+  end
+
+  def add_name(name)
+    return if name.nil? || name.empty?
+
+    # Speed up lookups with sorted names
+    @names[self.short_code(name)].add name
+
+    if @current_type == "substance"
+      @pubchem_substance_ids[name].add @pubchem_id
+    elsif @current_type == "compound"
+      @pubchem_compound_ids[name].add @pubchem_id
+    else
+      raise "Unknown substance"
+    end
+
+  end
+
+  def fuzzy_name_lookup(lookup_name, threshold)
+
+    closest_distance = 0.0
+    closest_name = nil
+
+    # Optimistically check for exact name match
+    exact_match = self.short_code(lookup_name).include? lookup_name
+
+    return @pubchem_ids[lookup_name] if exact_match
+    return nil if threshold == 1.0
+
+    @names[self.short_code(lookup_name)].each do |name|
+
+      distance = @fuzzy_matcher.getDistance(lookup_name, name)
+
+      if distance > closest_distance
+        closest_name = name
+        closest_distance = distance
+      end
+
+    end
+
+    return closest_name if closest_distance > 0.99
+
+  end
+
+  def match_list_of_names(names, threshold=0.99)
+    @matched_names = names.inject({}) do |acc, name|
+      acc[name] = self.fuzzy_name_lookup(name, threshold)
+      acc
+    end
+  end
+
+  def retrieve_ids(collection)
+    msg = "@matched_names required, see #{self.class}#match_list_of_names"
+
+    raise msg unless @matched_names
+
+    @matched_names.inject({}) do |acc, name|
+      input_name = name[0]
+      matched_name = name[1]
+
+      if matched_name
+        ids = collection[matched_name]
+        if ids.size > 1
+          puts "WARNING: Multiple matching sets"
+        end
+        collection_id = collection[matched_name].first
+        acc[input_name] = collection_id if collection_id
+      end
+
+      acc
+    end
+  end
+
+  def retrieve_substance_ids
+    self.retrieve_ids(@pubchem_substance_ids)
+  end
+
+  def retrieve_compound_ids
+    self.retrieve_ids(@pubchem_compound_ids)
+  end
+
+  def short_code(name)
+    name[0..2].downcase
+  end
+
+end

data/lib/pubchem/version.rb

@@ -1,3 +1,3 @@
 module Pubchem
-  VERSION = "0.0.5"
+  VERSION = "0.1.1"
 end

data/pubchem.gemspec

@@ -22,6 +22,9 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_runtime_dependency "mechanize", "~> 2.7.3"
+  spec.add_runtime_dependency "nokogiri", "~> 1.6.6.2"
+  spec.add_runtime_dependency "fuzzy-string-match", "~> 0.9.7"
+  spec.add_runtime_dependency "ox", "~> 2.2.1"
 
   spec.add_development_dependency "bundler", "~> 1.10"
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pubchem
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.1.1
 platform: ruby
 authors:
 - Zach Aysan
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-09-17 00:00:00.000000000 Z
+date: 2015-09-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
@@ -24,6 +24,48 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 2.7.3
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.6.6.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.6.6.2
+- !ruby/object:Gem::Dependency
+  name: fuzzy-string-match
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.9.7
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.9.7
+- !ruby/object:Gem::Dependency
+  name: ox
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.2.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.2.1
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -44,22 +86,25 @@ description: |2-
                            their form. This helps with that!
 email:
 - zachaysan@gmail.com
-executables:
-- ".gitkeep"
+executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".gitignore"
 - Gemfile
+- Gemfile.lock
 - README.markdown
 - Rakefile
 - bin/console
 - bin/setup
 - example.rb
-- exe/.gitkeep
 - lib/pubchem.rb
+- lib/pubchem/reader.rb
 - lib/pubchem/version.rb
 - pubchem.gemspec
 - run
+- xml/compound_sample.xml
+- xml/substance_sample.xml
 homepage: https://github.com/zachaysan/pubchem
 licenses:
 - MIT