bio-chembl 0.1.2 → 0.1.3

data/README.md

@@ -1,6 +1,6 @@
 # bio-chembl
 
-[![Build Status](https://secure.travis-ci.org/nakao/bioruby-chembl.png)](http://travis-ci.org/nakao/bioruby-chembl)
+[![Build Status](https://secure.travis-ci.org/nakao/bio-chembl.png)](http://travis-ci.org/nakao/bio-chembl)
 
 [ChEMBL REST Web Service API](https://www.ebi.ac.uk/chembldb/ws) client, parser and container classes. 
 
@@ -8,27 +8,32 @@ REST API address
 
 ```ruby
     BioChEMBL::REST::ChEMBL_URI.status
-     #=> "http://www.ebi.ac.uk/chemblws/status/" 
+     #=> "https://www.ebi.ac.uk/chemblws/status/" 
     BioChEMBL::REST::ChEMBL_URI.compounds("CHEMBL1") 
-     #=> "http://www.ebi.ac.uk/chemblws/compounds/CHEMBL1"
+     #=> "https://www.ebi.ac.uk/chemblws/compounds/CHEMBL1"
     BioChEMBL::REST::ChEMBL_URI.targets("CHEMBL2477") 
-     #=> "http://www.ebi.ac.uk/chemblws/targets/CHEMBL2477"
+     #=> "https://www.ebi.ac.uk/chemblws/targets/CHEMBL2477"
     BioChEMBL::REST::ChEMBL_URI.assays("CHEMBL1217643") 
-     #=> "http://www.ebi.ac.uk/chemblws/assays/CHEMBL1217643"
+     #=> "https://www.ebi.ac.uk/chemblws/assays/CHEMBL1217643"
 ```
 
 Get data in XML
+
 ```ruby     
     api = BioChEMBL::REST.new
     compound = api.compounds("CHEMBL1")
     targst   = api.targets("CHEMBL2477")
     assay    = api.assays("CHEMBL1217643")
 ```
+
 Check the server status
+
 ```ruby
    BioChEMBL::REST.up? #=> true/false
 ```   
+
 REST API client, parser and container: BioChEMBL::Compound
+
 ```ruby
     cpd = BioChEMBL::Compound.find("CHEMBL1")
     cpd.chemblId #=> "CHEMBL1"
@@ -44,7 +49,9 @@ REST API client, parser and container: BioChEMBL::Compound
     xml = BioChEMBL::REST.new.compounds("CHEMBL1") 
     cpd = BioChEMBL::Compound.parse_xml(xml)
 ```
+
 REST API client, parser and container: BioChEMBL::Target
+
 ```ruby       
     target = BioChEMBL::Target.find("CHEMBL1785")
     target.chemblId #=> "CHEMBL1785"
@@ -62,7 +69,9 @@ REST API client, parser and container: BioChEMBL::Target
     xml = BioChEMBL::REST.new.targets("CHEMBL1785")     
     target = BioChEMBL::Target.parse_xml(xml)
 ```
+
 REST API client, parser and container: BioChEMBL::Assay
+
 ```ruby   
     assay = BioChEMBL::Assay.find("CHEMBL1217643")
     assay.chemblId #=> "CHEMBL1217643"
@@ -76,6 +85,7 @@ REST API client, parser and container: BioChEMBL::Assay
 ```
 
 Parser and container: BioChEMBL::Bioactivity
+
 ```ruby
     cpd.bioactivities[0].parent_compound.chemblId
     target.bioactivities[0].target.chemblId
@@ -85,6 +95,7 @@ Parser and container: BioChEMBL::Bioactivity
 ```
 
 Getting Started with Ruby
+
 ```ruby
     require 'bio-chembl'
     # 1. Use UniProt accession to get target details
@@ -140,6 +151,7 @@ Getting Started with Ruby
 	  puts "  #{assay.assayDescription}"
 	end
 ```
+
 Note: this software is under active development!
 
 ## Installation
@@ -171,8 +183,9 @@ The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
 * BioChEMBL::Compound#image method to get the image in png.
 * BioChEMBL::Target.find_by_refesq method.
 * JSON output support (parser and address).
-* ChEMBL RDF support.
+* ChEMBL RDF integration.
 * Local REST API server with local ChEMBL database.
+* Connect Bioactivity#reference to external IDs (PubMed ID/DOI/CiteXplore)
 
 ## Cite
 

data/VERSION

@@ -1 +1 @@
-0.1.2
+0.1.3

data/bio-chembl.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{bio-chembl}
-  s.version = "0.1.2"
+  s.version = "0.1.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Mitsuteru Nakao"]
-  s.date = %q{2012-07-22}
+  s.date = %q{2012-07-23}
   s.description = %q{BioRuby plugin for ChEMBL REST API Client, Parser and Container classes}
   s.email = %q{mitsuteru.nakao@gmail.com}
   s.extra_rdoc_files = [
@@ -34,7 +34,6 @@ Gem::Specification.new do |s|
     "lib/bio-chembl/chemblid.rb",
     "lib/bio-chembl/compound.rb",
     "lib/bio-chembl/datamodel.rb",
-    "lib/bio-chembl/rest_api_server.rb",
     "lib/bio-chembl/rest_client.rb",
     "lib/bio-chembl/target.rb",
     "test/helper.rb",

data/lib/bio-chembl/assay.rb

@@ -5,21 +5,34 @@ require 'bio-chembl/bioactivity.rb'
 
 module BioChEMBL
   
-
-  
-  # ChEMBL Assay
-  #
+  # ChEMBL Assay Data parser and container.
+  #  
   # Data XML
-  # <assay>
-  #  <chemblId>CHEMBL1217643</chemblId>
-  #  <assayType>B</assayType>
-  #  <journal>Bioorg. Med. Chem. Lett.</journal>
-  #  <assayOrganism>Homo sapiens</assayOrganism>
-  #  <assayStrain>Unspecified</assayStrain>
-  #  <assayDescription>Inhibition of human hERG</assayDescription>
-  #  <numBioactivities>1</numBioactivities>
-  # </assay>
   #
+  #  <assay>
+  #    <chemblId>CHEMBL1217643</chemblId>
+  #    <assayType>B</assayType>
+  #    <journal>Bioorg. Med. Chem. Lett.</journal>
+  #    <assayOrganism>Homo sapiens</assayOrganism>
+  #    <assayStrain>Unspecified</assayStrain>
+  #    <assayDescription>Inhibition of human hERG</assayDescription>
+  #    <numBioactivities>1</numBioactivities>
+  #  </assay>
+  #
+  # Usage
+  #
+  #   assay = BioChEMBL::Assay.find("CHEMBL1217643")
+  #   assay.assayType
+  #   assay.assayOrganism
+  #   ba = assay.bioactivities
+  #
+  #   assay = BioChEMBL::Assay.new("CHEMBL1217643")
+  #   assay.assayType #=> nil
+  #   assay.resolve
+  #   assay.assayType #=> "B"
+  #
+  #   xml = BioChEMBL::REST.new.assays("CHEMBL1217643")
+  #   assay = BioChEMBL::Assay.parse_xml(xml)
   # 
   class Assay
     extend BioChEMBL::DataModel
@@ -36,7 +49,7 @@ module BioChEMBL
       
     set_attr_accessors(ATTRIBUTES)
 
-    
+    #  Parse the assay data.
     def self.parse(str)
       case str
       when /^</
@@ -53,6 +66,7 @@ module BioChEMBL
       end  
     end 
     
+    # Parse the assay data in XML format.
     def self.parse_xml(str)
       xml = Nokogiri::XML(str)
       this = new  
@@ -60,25 +74,28 @@ module BioChEMBL
       this
     end 
     
+    # Parse the assay data in JSON format.
     def self.parse_json(str)
       raise NotImplementedError
     end
     
+    # Parse the assay data in RDF format.
     def self.parse_rdf(str)
       raise NotImplementedError
     end
     
+    # Find the assay data by ChEMBL ID via the web service.
     def self.find(chemblId)
       self.parse_xml(REST.new.assays(chemblId))
     end   
     
      
-    # new
+    # Create a blank Assay instance.
     def initialize(chemblId = nil)
       @chemblId = chemblId
     end 
     
-    # Resolve the compound data by given ChEMBL ID
+    # Resolve the assay data by given ChEMBL ID
     def resolve
       resolved = self.class.find(@chemblId)
       ATTRIBUTES.each do |attr|
@@ -86,7 +103,7 @@ module BioChEMBL
       end
     end
     
-    # ChEMBL Bioactivity
+    # Find the Bioactivity data by the assay.
     def bioactivities
       BioChEMBL::Bioactivity.parse_list_xml(REST.new.assays(@chemblId, 'bioactivities'))
     end

data/lib/bio-chembl/bioactivity.rb

@@ -4,32 +4,48 @@ require 'bio-chembl/datamodel.rb'
 
 module BioChEMBL
 
-  # BioChEMBL::Bioactivity
+  # ChEMBL Bioactivity data parser and container.
   #
   # Data XML
-  # <list>
-  #   <bioactivity>
-  #     <parent__cmpd__chemblid>CHEMBL1214402</parent__cmpd__chemblid>
-  #     <ingredient__cmpd__chemblid>CHEMBL1214402</ingredient__cmpd__chemblid>
-  #     <target__chemblid>CHEMBL240</target__chemblid>
-  #     <target__confidence>9</target__confidence>
-  #     <target__name>HERG</target__name>
-  #     <reference>Bioorg. Med. Chem. Lett., (2010) 20:15:4359</reference>
-  #     <name__in__reference>26</name__in__reference>
-  #     <organism>Homo sapiens</organism>
-  #     <bioactivity__type>IC50</bioactivity__type>
-  #     <activity__comment>Unspecified</activity__comment>
-  #     <operator>=</operator>
-  #     <units>nM</units>
-  #     <assay__chemblid>CHEMBL1217643</assay__chemblid>
-  #     <assay__type>B</assay__type>
-  #     <assay__description>Inhibition of human hERG</assay__description>
+  #
+  #  <list>
+  #    <bioactivity>
+  #      <parent__cmpd__chemblid>CHEMBL1214402</parent__cmpd__chemblid>
+  #      <ingredient__cmpd__chemblid>CHEMBL1214402</ingredient__cmpd__chemblid>
+  #      <target__chemblid>CHEMBL240</target__chemblid>
+  #      <target__confidence>9</target__confidence>
+  #      <target__name>HERG</target__name>
+  #      <reference>Bioorg. Med. Chem. Lett., (2010) 20:15:4359</reference>
+  #      <name__in__reference>26</name__in__reference>
+  #      <organism>Homo sapiens</organism>
+  #      <bioactivity__type>IC50</bioactivity__type>
+  #      <activity__comment>Unspecified</activity__comment>
+  #      <operator>=</operator>
+  #      <units>nM</units>
+  #      <assay__chemblid>CHEMBL1217643</assay__chemblid>
+  #      <assay__type>B</assay__type>
+  #       <assay__description>Inhibition of human hERG</assay__description>
   #     <value>5900</value>
-  #   </bioactivity>
-  # </list>
+  #    </bioactivity>
+  #  </list>
   #
   # Usage
-  # 
+  #
+  #   bioactivties = BioChEMBL::Compound(chemlbId).bioactivities  
+  #   bioactivties = BioChEMBL::Target(chemlbId).bioactivities  
+  #   bioactivties = BioChEMBL::Assay(chemlbId).bioactivities  
+  #
+  #   bioactivities.find_all {|x| x.bioactivity__type =~ /IC50/ and x.value.to_i < 100 }.each do |ba|
+  #     assay = ba.assay
+  #     puts "Assay CHEMBLID:  #{assay.chemblId},  #{assay.assayDescription}"
+  #   end
+  #
+  #   bioactivity = bioactivities[0]
+  #   compound = bioactivity.parent_compound
+  #   compound = bioactivity.compound
+  #   assay = bioactivity.assay
+  #   target = bioactivity.target
+  #  
   class Bioactivity
     extend BioChEMBL::DataModel
       
@@ -54,6 +70,7 @@ module BioChEMBL
         
     set_attr_accessors(ATTRIBUTES)
       
+    # Parse the Bioactivity data.
     def self.parse(str)
       case str
       when /^</
@@ -70,6 +87,7 @@ module BioChEMBL
       end  
     end 
       
+    # Parse the Bioactivity data in XML format.
     def self.parse_xml(str)
       xml = Nokogiri::XML(str)
       this = new
@@ -77,8 +95,8 @@ module BioChEMBL
       this
     end
       
-    # XML
-    # <list><bioactivity> ...
+    # Parse the Bioactivity data list in XML format.
+    # data list: <list><bioactivity/></list>
     def self.parse_list_xml(str)
       xmls = Nokogiri::XML(str)
       xmls.xpath("/list/bioactivity").map do |cpd|
@@ -86,28 +104,40 @@ module BioChEMBL
       end
     end
       
+    # Parse the Bioactivity data in JSON format.
     def self.parse_json(str)
       raise NotImplementedError
     end
       
+    # Parse the Bioactivity data in RDF format.
     def self.parse_rdf(str)
       raise NotImplementedError
     end
     
+    # Link to the parent Compound
     def parent_compound
       require 'bio-chembl/compound.rb'
       BioChEMBL::Compound.find(@parent__cmpd__chemblid)
     end
+
+    # Link to the Compound
+    def compound
+      require 'bio-chembl/compound.rb'
+      BioChEMBL::Compound.find(@ingredient__cmpd__chemblid)
+    end
     
+    # Link to the Target
     def target
       require 'bio-chembl/target.rb'
       BioChEMBL::Target.find(@target__chemblid)
     end
        
+    # Link to the Assay
     def assay
       require 'bio-chembl/assay.rb'
       BioChEMBL::Assay.find(@assay__chemblid)
     end
+    
   end
 
 end

data/lib/bio-chembl/chembl.rb

@@ -7,11 +7,15 @@ require 'nokogiri'
 #
 module BioChEMBL
 
+  # ChEMBL Website
   def self.website
     "https://www.ebi.ac.uk/chembl/"
   end
   
-  # BioChEMBL.to_array(aTarget.synonyms) #=> []
+  # Multi value utility
+  #
+  #   BioChEMBL.to_array(aTarget.synonyms) #=> []
+  #
   def self.to_array(str)
     str.to_s.split('; ')
   end

data/lib/bio-chembl/chemblid.rb

@@ -9,89 +9,116 @@ require 'nokogiri'
 
 module BioChEMBL
       
-  # ChEMBL ID
+  # ChEMBL ID utility String
   #
-  # CHEMBL1
+  # Format
   #
-  # cid = BioChEMBL::ChEMBLID.new("CHEMBL1")
-  # cid.is_compound? #=> true
-  # cid.resolve #=> aBioChEMBL::Compound
+  #   /^CHEMBL\d+$/
+  #
+  # Usage
+  #
+  #   chemblId = BioChEMBL::ChEMBLID.new("CHEMBL1")
+  #   chemblId.is_compound? #=> true
+  #   chemblId.is_target?   #=> false
+  #   compound = chemblId.resolve
+  #
+  #   BioChEMBL::ChEMBLID.validate("CHEMBL1")
   #
   class ChEMBLID < String
     
     attr_accessor :data_type
  
-    def self.validate_chemblId(str)
-      unless str =~ /^CHEMBL\d+$/
-        raise Exception, "Invalid ChEMBL ID."
+    
+    # Checking the format of the ChEMBL ID
+    def self.valid_format?(str)
+      begin
+        self.new(str)
+        true
+      rescue Exception
+        false
       end
     end
-       
+    
+    # ChEMBL ID Validater
+    def validate_chemblId(str)
+      if str =~ /^CHEMBL\d+$/
+        true
+      else
+        raise Exception, "Invalid ChEMBL ID, '#{str}'"
+      end
+    end  
+    private :validate_chemblId
+      
     def initialize(str)
       @data_type = nil
-      self.validate_chemblId(str)
+      validate_chemblId(str)
       super(str)
     end
 
-   
+    # Get the data of the ChEMBL ID (Slow)
     def resolve
-      case @data_type
-      when Compound
-        Compound.find(self.to_s)
-      when Target
-        Target.find(self.to_s)
-      when Assay
-        Assay.find(self.to_s)
+      if @data_type    == Compound
+        return Compound.find(self.to_s)
+      elsif @data_type == Target
+        return Target.find(self.to_s)
+      elsif @data_type == Assay
+        return Assay.find(self.to_s)
       else
-        begin
-          Compound.find(self.to_s)
-        rescue
-        end 
-        begin
-          Target.find(self.to_s)
-        rescue
-        end 
-        begin
-          Assay.find(self.to_s)
-        rescue
+        if    is_compound?
+        elsif is_target?
+        elsif is_assay?
+        end
+        if @data_type == nil
+          raise ArgumentError, "This ChEMBL ID is not exist, #{self.to_s}"
+        else
+          resolve
         end 
       end
     end
     
+    
+    # Is the ChEMBL ID of Compound ?
     def is_compound?
       if @data_type == Compound
         return true
       else
-        if Compound.find(self.to_s)
+        begin
+          Compound.find(self)
           @data_type = Compound
           return true
-        else
+        rescue Exception
           return false  
         end 
       end
     end
-    
+
+
+    # Is the ChEMBL ID of Target ?
     def is_target?
-      if @data_type == Assay
+      if @data_type == Target
         return true
       else
-        if Assay.find(self.to_s)
-          @data_type = Assay
+        begin
+          Target.find(self)
+          @data_type = Target
           return true
-        else
+        rescue Exception
           return false  
         end 
       end    
     end
     
+    
+    # Is the ChEMBL ID of Assay ?
     def is_assay?
       if @data_type == Assay
         return true
       else
-        if Assay.find(self.to_s)
+        begin
+          Assay.find(self)
           @data_type = Assay
           return true
-        else
+        rescue Exception
           return false  
         end 
       end   

data/lib/bio-chembl/compound.rb

@@ -5,32 +5,35 @@ module BioChEMBL
   
   # ChEMBL Compound Data Container and Parser
   #
-  # XML Data string
-  # <compound>
-  #  <chemblId>CHEMBL1</chemblId>
-  #  <knownDrug>No</knownDrug>
-  #  <medChemFriendly>Yes</medChemFriendly>
-  #  <passesRuleOfThree>No</passesRuleOfThree>
-  #  <molecularFormula>C32H32O8</molecularFormula>
-  #  <smiles>COc1ccc2[C@@H]3[C@H](COc2c1)C(C)(C)OC4=C3C(=O)C(=O)C5=C4OC(C)(C)[C@@H]6COc7cc(OC)ccc7[C@H]56</smiles>
-  #  <stdInChiKey>GHBOEFUAGSHXPO-XZOTUCIWSA-N</stdInChiKey>
-  #  <numRo5Violations>1</numRo5Violations>
-  #  <rotatableBonds>2</rotatableBonds>
-  #  <molecularWeight>544.59167</molecularWeight>
-  #  <alogp>3.627</alogp>
-  #  <acdLogp>7.669</acdLogp>
-  #  <acdLogd>7.669</acdLogd>
-  # </compound>
+  # XML Data
+  #
+  #  <compound>
+  #    <chemblId>CHEMBL1</chemblId>
+  #    <knownDrug>No</knownDrug>
+  #    <medChemFriendly>Yes</medChemFriendly>
+  #    <passesRuleOfThree>No</passesRuleOfThree>
+  #    <molecularFormula>C32H32O8</molecularFormula>
+  #    <smiles>COc1ccc2[C@@H]3[C@H](COc2c1)C(C)(C)OC4=C3C(=O)C(=O)C5=C4OC(C)(C)[C@@H]6COc7cc(OC)ccc7[C@H]56</smiles>
+  #    <stdInChiKey>GHBOEFUAGSHXPO-XZOTUCIWSA-N</stdInChiKey>
+  #    <numRo5Violations>1</numRo5Violations>
+  #    <rotatableBonds>2</rotatableBonds>
+  #    <molecularWeight>544.59167</molecularWeight>
+  #    <alogp>3.627</alogp>
+  #    <acdLogp>7.669</acdLogp>
+  #    <acdLogd>7.669</acdLogd>
+  #  </compound>
   #
   # Usage
-  # ```cpd = BioChEMBL::Compound.find("CHEMBL1")
-  #    cpd.chemblId #=> "CHEMLB1"
-  #    cpd.smiles
   #
-  #    cpd2 = BioChEMBL::Compound.find_all_by_smiles(cpd.smile)
+  #  compound = BioChEMBL::Compound.find("CHEMBL1")
+  #  compound.chemblId #=> "CHEMLB1"
+  #  compound.smiles
+  #
+  #  compounds = BioChEMBL::Compound.find_all_by_smiles(compound.smiles)
   #
-  #    cpd3 = BioChEMBL::Compound.parse(xml)
-  # ```
+  #  xml = BioChEMBL::REST.new.compounds("CHEMBL1")
+  #  compound = BioChEMBL::Compound.parse_xml(xml)
+  # 
   class Compound
     extend BioChEMBL::DataModel
 
@@ -56,8 +59,7 @@ module BioChEMBL
     # Values of all attributes are in String.
     set_attr_accessors(ATTRIBUTES)
     
-    #
-    # BioChEMBL::Compound.parse(doc)
+    # Parse the Compound data
     def self.parse(str)
       case str
       when /^</
@@ -74,8 +76,7 @@ module BioChEMBL
       end    
     end 
     
-    # XML 
-    # <compound>
+    # Parse the Compound data in XML format.
     def self.parse_xml(str)
       xml = Nokogiri::XML(str)
       this = new  
@@ -83,8 +84,8 @@ module BioChEMBL
       this
     end 
     
-    # XML
-    # <list><compound> ...
+    # Parse the Compound data list in XML format.
+    # data list: <list><compound/></list>
     def self.parse_list_xml(str)
       xmls = Nokogiri::XML(str)
       xmls.xpath("/list/compound").map do |cpd|
@@ -92,66 +93,61 @@ module BioChEMBL
       end
     end 
 
-    # JSON
+    # Parse the Compound data in JSON format.
     def self.parse_json(str)
       raise NotImplementedError
     end
 
-    # RDF
+    # Parse the Compound data in RDF format.
     def self.parse_rdf(str)
       raise NotImplementedError
     end   
     
     
-    # Compound.find(chemblId)
-    # Find a compound data by a ChEMBL ID
+    # Find the Compound data by the ChEMBL ID
     def self.find(chemblId)
       self.parse_xml(REST.new.compounds(chemblId))
     end 
 
-    # Compound.find_by_smiles(smiles)
-    # Find a compound data by a SMILES
+    # Find the Compound data (first one) by the SMILES
     def self.find_by_smiles(smiles)
       self.find_all_by_smiles(smiles).first
     end 
 
-    # Compound.find_all_by_smiles(smiles)
-    # Find compounds by a SMILES.
+    # Find the Compounds by the SMILES.
     def self.find_all_by_smiles(smiles)
       self.parse_list_xml(REST.new.compounds_smiles(smiles))
     end 
 
-    # Compound.find_by_stdinchikey(stdinchikey)
-    # Find a compound data by a StdInChiKey
+    # Find the Compound data by the StdInChiKey
     def self.find_by_stdinchikey(stdinchikey)
       self.parse_xml(REST.new.compounds_stdinchikey(stdinchikey))
     end 
 
-    # Compound.find_all_by_substructure(smiles)
-    # Substructure Search by a SMILES
+    # Find the Compounds with Substructure Search by the SMILES
     def self.find_all_by_substructure(smiles)
       self.parse_list_xml(REST.new.compounds_substructure(smiles))
     end 
     
-    # Compound.find_similarity(smiles_with_similarity)
-    # Search compounds by a SMILES with similarity
+    # Find the Compounds by the SMILES with similarity
+    # 70% similarity:  smiles + "/70"
     def self.find_all_by_similarity(smiles_with_similarity)
       self.parse_list_xml(REST.new.compounds_similarity(smiles_with_similarity))
     end 
 
     
-    # new
     def initialize(chemblId = nil)
       @chemblId = chemblId
     end 
     
-    # Resolve the compound data by given ChEMBL ID
+    # Resolve the Compound data by the ChEMBL ID
     def resolve
       resolved = self.class.find(@chemblId)
       ATTRIBUTES.each do |attr|
         eval "@#{attr} = resolved.#{attr}"
       end
     end
+    
   end
   
 end

data/lib/bio-chembl/datamodel.rb

@@ -3,17 +3,18 @@ require 'nokogiri'
 
 module BioChEMBL
   
-  # BioChEMBL::DataModel
+  # ChEMBL database data common utilities
   #
   module DataModel
     
+    # Set attr_accessor of ATTRIBUTES
     def set_attr_accessors(attributes)
       attributes.each do |attr|
         eval "attr_accessor :#{attr}"
       end
     end
     
-   
+   # Set the values from XML data on the instance variables.
     def set_attr_values(attributes)
       attributes.map do |attr|
         "this.#{attr} = xml.xpath('/#{self.to_s.split('::').last.downcase}/#{attr}').text"

data/lib/bio-chembl/rest_client.rb

@@ -11,6 +11,23 @@ require 'bio-chembl/bioactivity.rb'
 
 module BioChEMBL
   
+  # ChEMBL REST Web service API Client.
+  #
+  # Usage
+  # 
+  #  # URI
+  #  BioChEMBL::REST::ChEMBL_URI.status
+  #  BioChEMBL::REST::ChEMBL_URI.compounds("CHEMBL1")
+  #
+  #  # Low-level client
+  #  client = BioChEMBL::REST.new
+  #  client.status
+  #  client.compounds("CHEMBL1")
+  #
+  #  # Check REST API status
+  #  BioChEMBL::REST.up? #=> true/false
+  #
+  #
   class REST
     
     HOST_NAME = "www.ebi.ac.uk"
@@ -18,23 +35,31 @@ module BioChEMBL
     BASE_URI = "https://" + HOST_NAME + "/" + API_ROOT
     
     
-    # BioChEMBL::REST::ChEMBL_URI module
+    # ChEMBL REST Web Service URI generator
     #
+    # [ChEMBL Web Services](https://www.ebi.ac.uk/chembldb/ws)
+    # 
     module ChEMBL_URI
+
       # 
       def self.address(path)
         "#{BASE_URI}/#{path}"
       end
      
       
-      # BioChEMBL::REST::ChEMBL_URI.status 
+      # Check API status 
       def self.status
         # Example URL: http://www.ebi.ac.uk/chemblws/status/
         address("status/")
       end
       
-      # BioChEMBL::REST::ChEMBL_URI.compounds()       
-      # compounds("CHEMBL1")
+      # Get compound by ChEMBLID
+      #   BioChEMBL::REST::ChEMBL_URI.compounds("CHEMBL1")  
+      # Get image of a ChEMBL compound by ChEMBLID     
+      #   BioChEMBL::REST::ChEMBL_URI.compounds("CHEMBL1", 'image')       
+      #   BioChEMBL::REST::ChEMBL_URI.compounds("CHEMBL1", 'image', {'dimensions' => 200})   
+      # Get individual compound bioactivities    
+      #   BioChEMBL::REST::ChEMBL_URI.compounds("CHEMBL1", 'bioactivities')       
       def self.compounds(chemblId = nil, arg = nil, params = nil)
         if chemblId and arg == nil and params == nil 
         # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/compounds/CHEMBL1
@@ -52,28 +77,41 @@ module BioChEMBL
           raise Exception, "Undefined address. ID: #{chemblId}, arg: #{arg}, params: #{params.inspect}"
         end
       end
-      # BioChEMBL::REST::ChEMBL_URI.compounds_stdinchikey()
+      
+      # Get compound by Standard InChiKey
+      #   BioChEMBL::REST::ChEMBL_URI.compounds_stdinchikey(stdinchikey)
       def self.compounds_stdinchikey(stdinchikey)
         # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/compounds/stdinchikey/QFFGVLORLPOAEC-SNVBAGLBSA-N
         address("compounds/stdinchikey/#{stdinchikey}")
       end 
-      # BioChEMBL::REST::ChEMBL_URI.compounds_smiles()
+      
+      # Get list of compounds matching Canonical SMILES
+      #  BioChEMBL::REST::ChEMBL_URI.compounds_smiles(smiles)
       def self.compounds_smiles(smiles)
         # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/compounds/smiles/COc1ccc2[C@@H]3[C@H](COc2c1)C(C)(C)OC4=C3C(=O)C(=O)C5=C4OC(C)(C)[C@@H]6COc7cc(OC)ccc7[C@H]56
         address("compounds/smiles/#{smiles}")
       end
-      # BioChEMBL::REST::ChEMBL_URI.compounds_substructure()
+      
+      # Get list of compounds containing the substructure represented by a given Canonical SMILES
+      #  BioChEMBL::REST::ChEMBL_URI.compounds_substructure(smiles)
       def self.compounds_substructure(smiles)
         # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/compounds/substructure/COc1ccc2[C@@H]3[C@H](COc2c1)C(C)(C)OC4=C3C(=O)C(=O)C5=C4OC(C)(C)[C@@H]6COc7cc(OC)ccc7[C@H]56
         address("compounds/substructure/#{smiles}")
       end
-      # BioChEMBL::REST::ChEMBL_URI.compounds_similarity()
+      
+      # Get list of compounds similar to the one represented by a given Canonical SMILES, at a given cutoff percentage
+      #  BioChEMBL::REST::ChEMBL_URI.compounds_similarity(smiles + "/" + cutoff)
       def self.compounds_similarity(smiles)
         # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/compounds/similarity/COc1ccc2[C@@H]3[C@H](COc2c1)C(C)(C)OC4=C3C(=O)C(=O)C5=C4OC(C)(C)[C@@H]6COc7cc(OC)ccc7[C@H]56/70
         address("compounds/similarity/#{smiles}")
       end
   
-      # BioChEMBL::REST::ChEMBL_URI.targets()
+      # Get target by ChEMBLID
+      #  BioChEMBL::REST::ChEMBL_URI.targets(chemblId)
+      # Get individual target bioactivities
+      #  BioChEMBL::REST::ChEMBL_URI.targets(chemblId, 'bioactivities')
+      # Get all targets
+      #  BioChEMBL::REST::ChEMBL_URI.targets
       def self.targets(chemblId = nil, arg = nil)
         if chemblId and arg == nil
           # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/targets/CHEMBL2477
@@ -88,18 +126,25 @@ module BioChEMBL
           raise Exception, "Undefined."
         end
       end
-      # BioChEMBL::REST::ChEMBL_URI.targets_uniprot()
+      
+      # Get target by UniProt Accession Identifier
+      #  BioChEMBL::REST::ChEMBL_URI.targets_uniprot(uniprot_id)
       def self.targets_uniprot(uniprot_id)
         # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/targets/uniprot/Q13936
         address("targets/uniprot/#{uniprot_id}")
       end 
-      # BioChEMBL::REST::ChEMBL_URI.targets_refseq()
+      
+      # Get target by RefSeq Accession Identifier
+      #  BioChEMBL::REST::ChEMBL_URI.targets_refseq(refseq_id)
       def self.targets_refseq(refseq_id)
         # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/targets/refseq/NP_001128722
         address("targets/refseq/#{refseq_id}")
       end
       
-      # BioChEMBL::REST::ChEMBL_URI.assays()
+      # Get assay by ChEMBLID
+      #  BioChEMBL::REST::ChEMBL_URI.assays(chemblId)
+      # Get individual assay bioactivities
+      #  BioChEMBL::REST::ChEMBL_URI.assays(chemblId, 'bioactivities')
       def self.assays(chemblId, arg = nil)
         if chemblId and arg == nil
           # Example URL (XML Output): http://www.ebi.ac.uk/chemblws/assays/CHEMBL1217643
@@ -114,12 +159,12 @@ module BioChEMBL
     end
     
 
-    # BioChEMBL::REST.website
+    # The ChEMBL REST Web services website
     def self.website
       "https://www.ebi.ac.uk/chembldb/index.php/ws"
     end
 
-    # BioChEMBL::REST.usage
+    # Usage
     def self.usage    
       ["a = Bio::DB::ChEMBL::REST.new",
        "a.status => https://www.ebi.ac.uk/chembldb/index.php/ws#serviceStatus",
@@ -128,7 +173,8 @@ module BioChEMBL
        ].join("\n")
     end
     
-    # BioChEMBL::REST.up? #=> true/false
+    # Check the API status
+    #  BioChEMBL::REST.up? #=> true/false
     def self.up?
       if new.status == "UP"
         true
@@ -138,7 +184,6 @@ module BioChEMBL
     end
 
     
-    # new
     def initialize(uri = BASE_URI)
       uri = URI.parse(uri) unless uri.kind_of?(URI)
       @header = {
@@ -150,7 +195,7 @@ module BioChEMBL
     # If true, shows debug information to $stderr.
     attr_accessor :debug
 
-    # get HTTP GET URL
+    # get the HTTP GET URL
     def get(url)
       easy = Curl::Easy.new(url) do |c|
         @header.each do |k,v|
@@ -161,7 +206,7 @@ module BioChEMBL
       easy
     end
     
-    # 
+    # HTTP responce handling
     def prepare_return_value(response)
       if @debug then
         $stderr.puts "ChEMBL: #{response.inspect}"
@@ -180,12 +225,12 @@ module BioChEMBL
       end
     end
     
-    # uri
+    # URI
     def uri
       ChEMBL_URI
     end
 
-    # address
+    # Address
     def address(path)
       "#{BASE_URI}/#{path}"
     end
@@ -194,6 +239,7 @@ module BioChEMBL
     
     # API methods
     
+    # Generic request builder and evaluator
     def get_body(method, args = [])
       code = case args.size
       when 0
@@ -213,49 +259,58 @@ module BioChEMBL
     end
     private :get_body
     
-    # 
+    # Resolve the calling method name
     def current_method_name
       caller(1).first.scan(/`(.*)'/)[0][0].to_s
     end 
     private :current_method_name
     
-    
+    # Check API status
     def status
       get_body(current_method_name)
     end
 
+    # Evaluate Compound methods
     def compounds(chemblId = nil, action = nil, params = nil)
       get_body(current_method_name, [chemblId, action, params])
     end
     
+    # Evaluate Compound StdInchiKey method
     def compounds_stdinchikey(stdinchikey)
       get_body(current_method_name, [stdinchikey])
     end
      
+    # Evaluate Compound SMILES method
     def compounds_smiles(smiles)
       get_body(current_method_name, [smiles])
     end
     
+    # Evaluate Compound SubStructure method
     def compounds_substructure(smiles)
       get_body(current_method_name, [smiles])
     end
     
+    # Evaluate Compound Similarity method
     def compounds_similarity(smiles)
       get_body(current_method_name, [smiles])
     end
 
+    # Evaluate Target Methods
     def targets(chemblId = nil, action = nil)
       get_body(current_method_name, [chemblId, action])
     end
     
+    # Evaluate Target UniProt method
     def targets_uniprot(uniprot_id)
       get_body(current_method_name, [uniprot_id])
     end
      
+    # Evaluate Target RefSeq method
     def targets_refseq(refseq_id)
       get_body(current_method_name, [refseq_id])
     end
 
+    # Evaluate Assay methods
     def assays(chemblId = nil, action = nil)
       get_body(current_method_name, [chemblId, action])
     end

data/lib/bio-chembl/target.rb

@@ -4,20 +4,31 @@ require 'bio-chembl/bioactivity.rb'
 
 module BioChEMBL
   
-  # ChEMBL Target
+  # ChEMBL Target parser and container.
   #
   # Data XML
-  # <target>
-  #  <chemblId>CHEMBL1785</chemblId>
-  #  <targetType>PROTEIN</targetType>
-  #  <preferredName>Endothelin receptor ET-B</preferredName>
-  #  <proteinAccession>P24530</proteinAccession>
-  #  <synonyms>Endothelin B receptor; Endothelin receptor non-selective type; ET-B; ET-BR</synonyms>
-  #  <organism>Homo sapiens</organism>
-  #  <description>Endothelin B receptor</description>
-  #  <geneNames>EDNRB; ETRB</geneNames>
-  # </target>
   #
+  #  <target>
+  #    <chemblId>CHEMBL1785</chemblId>
+  #    <targetType>PROTEIN</targetType>
+  #    <preferredName>Endothelin receptor ET-B</preferredName>
+  #    <proteinAccession>P24530</proteinAccession>
+  #    <synonyms>Endothelin B receptor; Endothelin receptor non-selective type; ET-B; ET-BR</synonyms>
+  #    <organism>Homo sapiens</organism>
+  #    <description>Endothelin B receptor</description>
+  #    <geneNames>EDNRB; ETRB</geneNames>
+  #  </target>
+  #
+  # Usage
+  # 
+  #  target = BioChEMBL::Target.find("CHEMBL1785")
+  #  target.geneNames
+  #  BioChEMBL.to_array(target.geneNames)[0] #=> "EDNRB"
+  #  
+  #  bioactivities = target.bioactivities
+  #   
+  #  target = BioChEMBL::Target.find_by_uniprot("P24530")
+  # 
   class Target
     extend BioChEMBL::DataModel
     
@@ -34,6 +45,7 @@ module BioChEMBL
 
     set_attr_accessors(ATTRIBUTES)
     
+    # Parse the Target data.
     def self.parse(str)
       case str
       when /^</
@@ -50,6 +62,7 @@ module BioChEMBL
       end 
     end 
     
+    # Parse the Target data in XML format.
     def self.parse_xml(str)
       xml = Nokogiri::XML(str)
       this = new  
@@ -57,8 +70,8 @@ module BioChEMBL
       this
     end 
 
-    # XML
-    # <list><target> ...
+    # Parse the Target data list in XML format.
+    # data lsit: <list><target/></list>
     def self.parse_list_xml(str)
       xmls = Nokogiri::XML(str)
       xmls.xpath("/list/target").map do |cpd|
@@ -66,38 +79,44 @@ module BioChEMBL
       end
     end
     
+    # Parse the Target data in JSON format.
     def self.parse_json(str)
       raise NotImplementedError
     end
 
+    # Parse the Target data in RDF format.
     def self.parse_rdf(str)
       raise NotImplementedError
     end   
     
+    # Find the Target data by the ChEMBL ID.
     def self.find(chemblId)
       self.parse_xml(REST.new.targets(chemblId))
     end
     
+    # Find the Target data by the UniProt ID.
     def self.find_by_uniprot(uniprot_id)
       self.parse_xml(REST.new.targets_uniprot(uniprot_id))      
     end
 
+    # Find the Target data by the RefSeq ID.
     def self.find_by_refseq(refseq_id)
       self.parse_xml(REST.new.targets_refseq(refseq_id))            
     end
     
-    # bioactivities => [aBioactivity, ...]
+    # Get the bioactivity data list.
     def bioactivities
       BioChEMBL::Bioactivity.parse_list_xml(REST.new.targets(chemblId, 'bioactivities'))
     end
     
-    # Resolve the target data by given ChEMBL ID => aTarget
+    # Resolve the Target data by the ChEMBL ID
     def resolve
       resolved = self.class.find(@chemblId)
       ATTRIBUTES.each do |attr|
         eval "@#{attr} = resolved.#{attr}"
       end
     end
+    
   end
 
 end

data/test/test_bio-chembl-chemblid.rb

@@ -10,27 +10,60 @@ class TestBioChemblChembId < Test::Unit::TestCase
   end
   
   def test_chemblid
-    assert_equal(@chemblid.class, BioChEMBL::ChEMBLID)
-    assert_equal(@chemblid, "CHEMBL1")
-    assert_equal(@chemblid.data_type, nil)
+    assert_equal(BioChEMBL::ChEMBLID, @chemblid.class)
+    assert_equal("CHEMBL1", @chemblid)
+    assert_equal(nil, @chemblid.data_type)
   end
   
   def test_invalid_chembl_id
     assert_raise(Exception) {
-      BioChEMBL::CHEMBLID.new("CHEMBLCHEMBL1")
+      BioChEMBL::ChEMBLID.new("CHEMBLCHEMBL1")
     }
   end
   
+  def test_chemblid_validate
+    assert_equal(true, BioChEMBL::ChEMBLID.valid_format?(@str))
+    assert_equal(false, BioChEMBL::ChEMBLID.valid_format?("CHEMBLCHEMBL1"))
+  end
+  
+  def test_resolve
+    compound = @chemblid.resolve
+    assert_equal(BioChEMBL::Compound, @chemblid.data_type)
+    assert_equal(@chemblid, compound.chemblId)
+    assert_equal("COc1ccc2[C@@H]3[C@H](COc2c1)C(C)(C)OC4=C3C(=O)C(=O)C5=C4OC(C)(C)[C@@H]6COc7cc(OC)ccc7[C@H]56", compound.smiles)
+  end
+
+  def test_resolve_target
+    target = BioChEMBL::ChEMBLID.new("CHEMBL1785").resolve
+    assert_equal(BioChEMBL::Target, target.class)
+    assert_equal("CHEMBL1785", target.chemblId)
+    assert_equal("PROTEIN", target.targetType)
+  end
+
+  def test_resolve_assay
+    assay = BioChEMBL::ChEMBLID.new("CHEMBL1217643").resolve
+    assert_equal(BioChEMBL::Assay, assay.class)
+    assert_equal("CHEMBL1217643", assay.chemblId)
+    assert_equal("B", assay.assayType)
+  end
+  
+  def test_resolve_invalid
+    assert_raise(ArgumentError) {
+      dummy = BioChEMBL::ChEMBLID.new("CHEMBL11111111111111217643").resolve
+    }
+  end
+
+  
   def test_chemblid_is_compound?
-    assert_equal(@chemblid.is_compound?, true)
-    assert_equal(@chemblid.data_type, Compound)
+    assert_equal(true, @chemblid.is_compound?)
+    assert_equal(BioChEMBL::Compound, @chemblid.data_type)
   end
   
   def test_chemblid_is_target?
-    assert_equal(@chemblid.is_target?, false)    
+    assert_equal(false, @chemblid.is_target?)    
   end
 
   def test_chemblid_is_assay?
-    assert_equal(@chemblid.is_assay?, false)    
+    assert_equal(false, @chemblid.is_assay?)    
   end
 end

data/test/test_bio-chembl-chemblid.sh

@@ -1,3 +1,2 @@
-
 cd /Users/mitsuteru/Applications/biogems/bioruby-chembl/
-/opt/local/bin/ruby1.9 -I lib -I test test/test_bio-chembl-chemblid.rb
+/opt/local/bin/ruby1.9 -I lib -I test test/test_bio-chembl-chemblid.rb

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: bio-chembl
 version: !ruby/object:Gem::Version 
-  hash: 31
+  hash: 29
   prerelease: false
   segments: 
   - 0
   - 1
-  - 2
-  version: 0.1.2
+  - 3
+  version: 0.1.3
 platform: ruby
 authors: 
 - Mitsuteru Nakao
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-07-22 00:00:00 +09:00
+date: 2012-07-23 00:00:00 +09:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -167,7 +167,6 @@ files:
 - lib/bio-chembl/chemblid.rb
 - lib/bio-chembl/compound.rb
 - lib/bio-chembl/datamodel.rb
-- lib/bio-chembl/rest_api_server.rb
 - lib/bio-chembl/rest_client.rb
 - lib/bio-chembl/target.rb
 - test/helper.rb

data/lib/bio-chembl/rest_api_server.rb

@@ -1,40 +0,0 @@
-require 'cgi'
-require 'uri'
-require 'nokogiri'
-
-
-module BioChEMBL
-  class REST
-    # serv = BioChEMBL::REST::Server.new
-    #    
-    class Server
-      def initialize
-        
-      end
-      
-      # serv.query(:status)
-      # serv.query(:compounds, 'CHEML1')
-      def query(action, args, options)
-      end
-      
-      # /compounds/CHEMBL1
-      def compounds(chemblId)
-      end
-      # /compounds/CHEMBL1/image
-      def compounds_image(chemblId)
-      end
-      # /compounds/CHEMBL1/bioactivities
-      def comopunds_bioactivities(chemblId)
-      end
-      
-    end
-    
-  end
-  
-  class DB
-    class Query
-      def initialize
-      end
-    end
-  end
-end