Romualdo Benigni1, Alessandro Giuliani. 1. Laboratory of Comparative Toxicology and Ecotoxicology, Istituto Superiore di Sanita, Viale Regina Elena 299, 00161 Rome, Italy. rbenigni@iss.it
Abstract
MOTIVATION: Chemical carcinogenicity is of primary interest, because it drives much of the current regulatory actions regarding new and existing chemicals, and its experimental determination involves time-consuming and expensive animal testing. Both academia and private companies are actively trying to develop SAR and QSAR models. This paper reviews the new Predictive Toxicology Challenge (PTC) results, by putting them into the context of previous attempts. RESULTS: A marked dependency of the prediction ability of the different algorithms on the training sets was observed, pointing to a still insufficient coverage of the chemical carcinogens 'universe'. A theoretical treatment of the possible developments of the Artificial Intelligence approaches is sketched.
MOTIVATION: Chemical carcinogenicity is of primary interest, because it drives much of the current regulatory actions regarding new and existing chemicals, and its experimental determination involves time-consuming and expensive animal testing. Both academia and private companies are actively trying to develop SAR and QSAR models. This paper reviews the new Predictive Toxicology Challenge (PTC) results, by putting them into the context of previous attempts. RESULTS: A marked dependency of the prediction ability of the different algorithms on the training sets was observed, pointing to a still insufficient coverage of the chemical carcinogens 'universe'. A theoretical treatment of the possible developments of the Artificial Intelligence approaches is sketched.
Authors: Peter H Hagedorn; Victor Yakimov; Søren Ottosen; Susanne Kammler; Niels F Nielsen; Anja M Høg; Maj Hedtjärn; Michael Meldgaard; Marianne R Møller; Henrik Orum; Troels Koch; Morten Lindow Journal: Nucleic Acid Ther Date: 2013-08-16 Impact factor: 5.486