1 files changed, 23 insertions, 0 deletions
diff --git a/models/mutagenicity/download/merge.rb b/models/mutagenicity/download/merge.rb
new file mode 100644
index 0000000..51f2f5e
--- /dev/null
+++ b/models/mutagenicity/download/merge.rb
@@ -0,0 +1,23 @@
+#!/usr/bin/env ruby
+
+      # merge datasets
+      hansen = Dataset.from_csv_file File.join(parts,"hansen.csv")
+      efsa = Dataset.from_csv_file File.join(parts,"efsa.csv")
+      kazius = Dataset.from_sdf_file File.join(parts,"cas_4337.sdf")
+      datasets = [hansen,efsa,kazius]
+      map = {"mutagen" => "mutagenic", "nonmutagen" => "non-mutagenic"}
+      dataset = Dataset.merge datasets: datasets, features: datasets.collect{|d| d.bioactivity_features.first}, value_maps: [nil,nil,map], keep_original_features: false, remove_duplicates: true
+      dataset.merged_features.first.name = "Mutagenicity"
+      File.open(File.join(DATA,"Mutagenicity-Salmonella_typhimurium.csv"),"w+"){|f| f.puts dataset.to_training_csv}
+      meta = {
+        :species => "Salmonella typhimurium",
+        :endpoint => "Mutagenicity",
+        :source => [kazius_url,hansen_url,efsa_url].join(", "),
+        :qmrf => { "group": "QMRF 4.10. Mutagenicity", "name": "OECD 471 Bacterial Reverse Mutation Test"},
+      }
+      File.open(File.join(DATA,"Mutagenicity-Salmonella_typhimurium.json"),"w+"){|f| f.puts meta.to_json}
+      
+      # cleanup
+      datasets << dataset
+      datasets.each{|d| d.delete }
+      File.join(DATA,"Mutagenicity-Salmonella_typhimurium.csv")