From 611bac891177f8d9185d45486dd574b6ef4d1912 Mon Sep 17 00:00:00 2001 From: Christoph Helma Date: Mon, 9 May 2016 15:11:46 +0200 Subject: nanoparticle models fixed --- lib/dataset.rb | 8 ++++---- lib/import.rb | 6 +++--- lib/model.rb | 1 + lib/nanoparticle.rb | 37 +++++++++++++++++++++---------------- lib/regression.rb | 2 +- 5 files changed, 30 insertions(+), 24 deletions(-) (limited to 'lib') diff --git a/lib/dataset.rb b/lib/dataset.rb index 86800c6..9738c1f 100644 --- a/lib/dataset.rb +++ b/lib/dataset.rb @@ -62,12 +62,12 @@ module OpenTox training_cids = training_idxs.collect{|i| substance_ids[i]} chunk = [training_cids,test_cids].collect do |cids| dataset = self.class.create(:substance_ids => cids, :feature_ids => feature_ids, :source => self.id ) - dataset.compounds.each do |compound| - compound.dataset_ids << dataset.id - compound.toxicities.each do |feature_id,data| + dataset.substances.each do |substance| + substance.dataset_ids << dataset.id + substance.toxicities.each do |feature_id,data| data[dataset.id.to_s] = data[self.id.to_s] # copy data entries end - compound.save + substance.save end dataset end diff --git a/lib/import.rb b/lib/import.rb index 11cb367..dfe5e2d 100644 --- a/lib/import.rb +++ b/lib/import.rb @@ -40,10 +40,10 @@ module OpenTox datasets[bundle_uri].substance_ids << nanoparticle.id nanoparticle["dataset_ids"] << datasets[bundle_uri].id end + bundle = datasets[np["bundles"].keys.first].id if np["bundles"].size == 1 study["effects"].each do |effect| effect["result"]["textValue"] ? klass = NominalFeature : klass = NumericFeature # TODO parse core/coating - # TODO parse proteomics, they come as a large textValue #$logger.debug File.join(np["compound"]["URI"],"study") effect["conditions"].delete_if { |k, v| v.nil? } # parse proteomics data @@ -53,7 +53,7 @@ module OpenTox :name => identifier, :category => "Proteomics", ) - nanoparticle.parse_ambit_value feature, value + nanoparticle.parse_ambit_value feature, value, bundle end else feature = klass.find_or_create_by( @@ -62,7 +62,7 @@ module OpenTox :category => study["protocol"]["topcategory"], :conditions => effect["conditions"] ) - nanoparticle.parse_ambit_value feature, effect["result"] + nanoparticle.parse_ambit_value feature, effect["result"], bundle end end nanoparticle.save diff --git a/lib/model.rb b/lib/model.rb index 5b094fb..070248a 100644 --- a/lib/model.rb +++ b/lib/model.rb @@ -76,6 +76,7 @@ module OpenTox prediction = {} if neighbors.collect{|n| n["_id"]}.include? compound.id + me = neighbors.select{|n| n["_id"] == compound.id}.first database_activities = neighbors.select{|n| n["_id"] == compound.id}.first["toxicities"][prediction_feature.id.to_s][training_dataset_id.to_s].uniq prediction[:database_activities] = database_activities prediction[:warning] = "#{database_activities.size} compounds have been removed from neighbors, because they have the same structure as the query compound." diff --git a/lib/nanoparticle.rb b/lib/nanoparticle.rb index 9bf419d..b79981d 100644 --- a/lib/nanoparticle.rb +++ b/lib/nanoparticle.rb @@ -9,10 +9,14 @@ module OpenTox field :proteomics, type: Hash, default: {} def nanoparticle_neighbors params - Dataset.find(params[:training_dataset_id]).nanoparticles.collect{|np| np["tanimoto"] = 1; np} + dataset = Dataset.find(params[:training_dataset_id]) + Dataset.find(params[:training_dataset_id]).nanoparticles.collect do |np| + np["tanimoto"] = 1 + np unless np.toxicities.empty? + end.compact end - def add_feature feature, value + def add_feature feature, value, dataset_id case feature.category when "P-CHEM" physchem_descriptors[feature.id.to_s] ||= [] @@ -23,51 +27,52 @@ module OpenTox proteomics[feature.id.to_s] << value proteomics[feature.id.to_s].uniq! when "TOX" - toxicities[feature.id.to_s] ||= [] + toxicities[feature.id.to_s] ||= {} + toxicities[feature.id.to_s][dataset_id.to_s] ||= [] # TODO generic way of parsing TOX values if feature.name == "7.99 Toxicity (other) ICP-AES" and feature.unit == "mL/ug(Mg)" - toxicities[feature.id.to_s] << -Math.log10(value) + toxicities[feature.id.to_s][dataset_id.to_s] << -Math.log10(value) else - toxicities[feature.id.to_s] << value + toxicities[feature.id.to_s][dataset_id.to_s] << value end - toxicities[feature.id.to_s].uniq! + toxicities[feature.id.to_s][dataset_id.to_s].uniq! else warn "Unknown feature type '#{feature.category}'. Value '#{value}' not inserted." end end - def parse_ambit_value feature, v + def parse_ambit_value feature, v, dataset_id v.delete "unit" # TODO: ppm instead of weights if v.keys == ["textValue"] - add_feature feature, v["textValue"] + add_feature feature, v["textValue"], dataset_id elsif v.keys == ["loValue"] - add_feature feature, v["loValue"] + add_feature feature, v["loValue"], dataset_id elsif v.keys.size == 2 and v["errorValue"] - add_feature feature, v["loValue"] + add_feature feature, v["loValue"], dataset_id warn "Ignoring errorValue '#{v["errorValue"]}' for '#{feature.name}'." elsif v.keys.size == 2 and v["loQualifier"] == "mean" - add_feature feature, v["loValue"] + add_feature feature, v["loValue"], dataset_id warn "'#{feature.name}' is a mean value. Original data is not available." elsif v.keys.size == 2 and v["loQualifier"] #== ">=" warn "Only min value available for '#{feature.name}', entry ignored" elsif v.keys.size == 2 and v["upQualifier"] #== ">=" warn "Only max value available for '#{feature.name}', entry ignored" elsif v.keys.size == 3 and v["loValue"] and v["loQualifier"].nil? and v["upQualifier"].nil? - add_feature feature, v["loValue"] + add_feature feature, v["loValue"], dataset_id warn "loQualifier and upQualifier are empty." elsif v.keys.size == 3 and v["loValue"] and v["loQualifier"] == "" and v["upQualifier"] == "" - add_feature feature, v["loValue"] + add_feature feature, v["loValue"], dataset_id warn "loQualifier and upQualifier are empty." elsif v.keys.size == 4 and v["loValue"] and v["loQualifier"].nil? and v["upQualifier"].nil? - add_feature feature, v["loValue"] + add_feature feature, v["loValue"], dataset_id warn "loQualifier and upQualifier are empty." elsif v.size == 4 and v["loQualifier"] and v["upQualifier"] and v["loValue"] and v["upValue"] - add_feature feature, [v["loValue"],v["upValue"]].mean + add_feature feature, [v["loValue"],v["upValue"]].mean, dataset_id warn "Using mean value of range #{v["loValue"]} - #{v["upValue"]} for '#{feature.name}'. Original data is not available." elsif v.size == 4 and v["loQualifier"] == "mean" and v["errorValue"] warn "'#{feature.name}' is a mean value. Original data is not available. Ignoring errorValue '#{v["errorValue"]}' for '#{feature.name}'." - add_feature feature, v["loValue"] + add_feature feature, v["loValue"], dataset_id elsif v == {} # do nothing else warn "Cannot parse Ambit eNanoMapper value '#{v}' for feature '#{feature.name}'." diff --git a/lib/regression.rb b/lib/regression.rb index b8a7e5f..691f903 100644 --- a/lib/regression.rb +++ b/lib/regression.rb @@ -10,7 +10,7 @@ module OpenTox neighbors.each do |row| sim = row["tanimoto"] sim ||= 1 # TODO: sim f nanoparticles - if row["toxicities"][params[:prediction_feature_id].to_s] + if row["toxicities"][params[:prediction_feature_id].to_s] and row["toxicities"][params[:prediction_feature_id].to_s][params[:training_dataset_id].to_s] row["toxicities"][params[:prediction_feature_id].to_s][params[:training_dataset_id].to_s].each do |act| weighted_sum += sim*act sim_sum += sim -- cgit v1.2.3