Prediction of the carcinogenicity in rodents of chemicals currently being tested by the US National Toxicology Program: structure-activity correlations

Abstract
CASE, an artificial intelligence structure-activity relational system, was used to predict the carcinogenicity of a group of chemicals currently being tested in rodent bioassays by the US National Toxicology Program. The ‘learning set’ for the CASE predictions consisted of the results of previous 252 rodent carcinogenicity bioassays.