diff options
Diffstat (limited to 'lib/compound.rb')
| -rw-r--r-- | lib/compound.rb | 20 |
1 files changed, 7 insertions, 13 deletions
diff --git a/lib/compound.rb b/lib/compound.rb index 2a79fd6..049d77b 100644 --- a/lib/compound.rb +++ b/lib/compound.rb @@ -2,10 +2,8 @@ CACTUS_URI="http://cactus.nci.nih.gov/chemical/structure/" module OpenTox - class Compound + class Compound < Substance require_relative "unique_descriptors.rb" - include OpenTox - DEFAULT_FINGERPRINT = "MP2D" field :inchi, type: String @@ -19,9 +17,6 @@ module OpenTox field :sdf_id, type: BSON::ObjectId field :fingerprints, type: Hash, default: {} field :default_fingerprint_size, type: Integer - field :physchem_descriptors, type: Hash, default: {} - field :dataset_ids, type: Array, default: [] - field :features, type: Hash, default: {} index({smiles: 1}, {unique: true}) @@ -293,8 +288,7 @@ module OpenTox training_dataset.compounds.each do |compound| candidate_fingerprint = compound.fingerprint params[:type] sim = (query_fingerprint & candidate_fingerprint).size/(query_fingerprint | candidate_fingerprint).size.to_f - feature_values = training_dataset.values(compound,prediction_feature) - neighbors << {"_id" => compound.id, "features" => {prediction_feature.id.to_s => feature_values}, "tanimoto" => sim} if sim >= params[:min_sim] + neighbors << {"_id" => compound.id, "toxicities" => {prediction_feature.id.to_s => compound.toxicities[prediction_feature.id.to_s]}, "tanimoto" => sim} if sim >= params[:min_sim] end neighbors.sort!{|a,b| b["tanimoto"] <=> a["tanimoto"]} end @@ -335,25 +329,25 @@ module OpenTox 'in' => {'$divide' => ['$$common', {'$subtract' => [{'$add' => [default_fingerprint_size, '$default_fingerprint_size']}, '$$common']}]} }}, '_id' => 1, - 'features' => 1, + 'toxicities' => 1, 'dataset_ids' => 1 }}, {'$match' => {'tanimoto' => {'$gte' => params[:min_sim]}}}, {'$sort' => {'tanimoto' => -1}} ] - $mongo["compounds"].aggregate(aggregate).select{|r| r["dataset_ids"].include? params[:training_dataset_id]} + $mongo["substances"].aggregate(aggregate).select{|r| r["dataset_ids"].include? params[:training_dataset_id]} end - # Convert mg to mmol + # Convert mmol to mg # @return [Float] value in mg def mmol_to_mg mmol mmol.to_f*molecular_weight end - # Convert mmol to mg - # @return [Float] value in mg + # Convert mg to mmol + # @return [Float] value in mmol def mg_to_mmol mg mg.to_f/molecular_weight end |