D. Bahler and D. Bristol
This paper presents :esnlts from an ongoing effort in applying a variety of induction-based methods to the problem of predicting the biological activity of noncongeneric (structutally dissimilar) chemicals. It describes initial experiments, the longterm goal of which is to assist toxicologists, cancer researchers, regulators, and others to predict the toxic effects of chemical compounds. We describe a series of experiments in tree and rule induction from a set of example chemicals whose carcinogenlcity has been determined from long-term animal studies1 and compare the resulting classification accuracy with eight published human and computer predictions for a common set of 44 test chemicals. The accuracy of out system is compatable to the most accurate human expert prediction yet published, and exceeds that of any of the computer-based predictions in the literature. The induced rules provide confirmation of current expert heuristic knowledge in this domain. These early results show that an inductive approach has excellent potential in predictive toxicology.