diff options
| -rw-r--r-- | .gitignore | 2 | ||||
| -rw-r--r-- | lib/compound.rb | 12 | ||||
| -rw-r--r-- | lib/dataset.rb | 42 | ||||
| -rw-r--r-- | lib/opentox.rb | 4 |
4 files changed, 51 insertions, 9 deletions
@@ -3,3 +3,5 @@ Gemfile.lock .bundle pkg/* *~ +.yardoc/ +doc/ diff --git a/lib/compound.rb b/lib/compound.rb index d33c48e..89bf840 100644 --- a/lib/compound.rb +++ b/lib/compound.rb @@ -91,14 +91,18 @@ module OpenTox RestClientWrapper.get("#{CACTUS_URI}#{inchi}/names").split("\n") end + # @return [String] PubChem Compound Identifier (CID), derieved via restcall to pubchem def cid pug_uri = "http://pubchem.ncbi.nlm.nih.gov/rest/pug/" @cid ||= RestClientWrapper.post(File.join(pug_uri, "compound", "inchi", "cids", "TXT"),{:inchi => inchi}).strip end + # @todo def chebi + raise_internal_error "not yet implemented" end + # @return [String] ChEMBL database compound id, derieved via restcall to chembl def chemblid # https://www.ebi.ac.uk/chembldb/ws#individualCompoundByInChiKey uri = "http://www.ebi.ac.uk/chemblws/compounds/smiles/#{smiles}.json" @@ -190,11 +194,11 @@ module OpenTox # Keys: matching smarts, values: number of non-unique hits, or 1 # @param [Array] smarts_array Array with Smarts strings # @param use_hits [Boolean] Whether non-unique hits or 1 should be produced - # @return [Array] Array with matching Smarts strings - # @example { + # @return [Hash] Hash with matching Smarts as keys, nr-of-hits/1 as values + # @example # compound = Compound.from_name("Benzene") - # compound.match(['cc','cN']) # returns { 'cc' => 12, 'cN' => 0 } - # } + # compound.match(['cc','cN'],true) # returns { 'cc' => 12 }, 'cN' is not included because it does not match + # compound.match(['cc','cN'],false) # returns { 'cc' => 1 } def match_hits(smarts_array, use_hits=true) obconversion = OpenBabel::OBConversion.new obmol = OpenBabel::OBMol.new diff --git a/lib/dataset.rb b/lib/dataset.rb index 19d05c9..9efae20 100644 --- a/lib/dataset.rb +++ b/lib/dataset.rb @@ -15,7 +15,8 @@ module OpenTox end # Get data (lazy loading from dataset service) - + # overrides {OpenTox#metadata} to only load the metadata instead of the whole dataset + # @return [Hash] the metadata def metadata force_update=false if @metadata.empty? or force_update uri = File.join(@uri,"metadata") @@ -29,6 +30,7 @@ module OpenTox @metadata end + # @return [Array] feature objects (NOT uris) def features force_update=false if @features.empty? or force_update uri = File.join(@uri,"features") @@ -38,6 +40,7 @@ module OpenTox @features end + # @return [Array] compound objects (NOT uris) def compounds force_update=false if @compounds.empty? or force_update uri = File.join(@uri,"compounds") @@ -47,6 +50,8 @@ module OpenTox @compounds end + # @return [Array] with two dimensions, + # first index: compounds, second index: features, values: compound feature values def data_entries force_update=false if @data_entries.empty? or force_update sparql = "SELECT ?cidx ?fidx ?value FROM <#{uri}> WHERE { @@ -105,6 +110,9 @@ module OpenTox compounds.select{|f| f.uri == uri}.first end + # for prediction result datasets + # assumes that there are features with title prediction and confidence + # @return [Array] of Hashes with keys { :compound, :value ,:confidence } (compound value is object not uri) def predictions predictions = [] prediction_feature = nil @@ -128,15 +136,23 @@ module OpenTox predictions end - # Adding data (@features and @compounds are also writable) + # Adding data methods + # (Alternatively, you can directly change @features and @compounds) + # Create a dataset from file (csv,sdf,...) + # @param filename [String] + # @return [String] dataset uri def upload filename, wait=true uri = RestClientWrapper.put(@uri, {:file => File.new(filename)}, {:subjectid => @subjectid}) wait_for_task uri if URI.task?(uri) and wait metadata true @uri end - + + # @param compound [OpenTox::Compound] + # @param feature [OpenTox::Feature] + # @param value [Object] (will be converted to String) + # @return [Array] data_entries def add_data_entry compound, feature, value @compounds << compound unless @compounds.collect{|c| c.uri}.include?(compound.uri) row = @compounds.collect{|c| c.uri}.index(compound.uri) @@ -152,8 +168,15 @@ module OpenTox end # TODO: remove? might be dangerous if feature ordering is incorrect + # MG: I would not remove this because add_data_entry is very slow (4 times searching in arrays) + # @param row [Array] + # @example + # d = Dataset.new + # d.features << Feature.new(a) + # d.features << Feature.new(b) + # d << [ Compound.new("c1ccccc1"), feature-value-a, feature-value-b ] def << row - compound = row.shift + compound = row.shift # removes the compound from the array bad_request_error "Dataset features are empty." unless @features bad_request_error "Row size '#{row.size}' does not match features size '#{@features.size}'." unless row.size == @features.size bad_request_error "First column is not a OpenTox::Compound" unless compound.class == OpenTox::Compound @@ -163,6 +186,8 @@ module OpenTox # Serialisation + # converts dataset to csv format including compound smiles as first column, other column headers are feature titles + # @return [String] def to_csv CSV.generate do |csv| csv << ["SMILES"] + features.collect{|f| f.title} @@ -277,6 +302,11 @@ module OpenTox # Methods for for validation service + # create a new dataset with the specified compounds and features + # @param compound_indices [Array] compound indices (integers) + # @param feats [Array] features objects + # @param metadata [Hash] + # @return [OpenTox::Dataset] def split( compound_indices, feats, metadata, subjectid=nil) bad_request_error "Dataset.split : Please give compounds as indices" if compound_indices.size==0 or !compound_indices[0].is_a?(Fixnum) @@ -328,6 +358,9 @@ module OpenTox @index_map[dataset.uri][compound_index] end + # returns the inidices of the compound in the dataset + # @param compound [OpenTox::Compound] + # @return [Array] compound index (position) of the compound in the dataset, array-size is 1 unless multiple occurences def compound_indices( compound ) unless defined?(@cmp_indices) and @cmp_indices.has_key?(compound) @cmp_indices = {} @@ -343,6 +376,7 @@ module OpenTox @cmp_indices[compound] end + # returns compound feature value using the compound-index and the feature_uri def data_entry_value(compound_index, feature_uri) data_entries(true) if @data_entries.empty? col = @features.collect{|f| f.uri}.index feature_uri diff --git a/lib/opentox.rb b/lib/opentox.rb index 0e44426..95dca04 100644 --- a/lib/opentox.rb +++ b/lib/opentox.rb @@ -167,15 +167,17 @@ module OpenTox end end + # @return [String] converts object to turtle-string def to_turtle # redefined to use prefixes (not supported by RDF::Writer) prefixes = {:rdf => "http://www.w3.org/1999/02/22-rdf-syntax-ns#"} ['OT', 'DC', 'XSD', 'OLO'].each{|p| prefixes[p.downcase.to_sym] = eval("RDF::#{p}.to_s") } create_rdf - RDF::Writer.for(:turtle).buffer(:prefixes => prefixes) do |writer| + RDF::Turtle::Writer.for(:turtle).buffer(:prefixes => prefixes) do |writer| writer << @rdf end end + # @return [String] converts OpenTox object into html document (by first converting it to a string) def to_html to_turtle.to_html end |