The predictive toxicology evaluation challenge
IJCAI'97 Proceedings of the 15th international joint conference on Artifical intelligence - Volume 1
A Note on Two Simple Transformations for Improving the Efficiency of an ILP System
ILP '00 Proceedings of the 10th International Conference on Inductive Logic Programming
Demand-Driven Construction of Structural Features in ILP
ILP '01 Proceedings of the 11th International Conference on Inductive Logic Programming
MCS '01 Proceedings of the Second International Workshop on Multiple Classifier Systems
Mining graphs with constraints on symmetry and diameter
WAIM'10 Proceedings of the 2010 international conference on Web-age information management
Good and bad practices in propositionalisation
AI*IA'05 Proceedings of the 9th conference on Advances in Artificial Intelligence
| Hi-index | 0.00 |
Constructing "good" models for chemical carcinogenesis was identified in IJCAI-97 as providing a substantial challenge to "knowledge discovery" programs. Attention was drawn to a comparative exercise which called for predictions on the outcome of 30 rodent carcinogenicity bioassays. This-the Predictive Toxicology Evaluation (or PTE) Challenge - was seen to provide AI programs with an opportunity to participate in an enterprise of scientific merit, and a yardstick for comparison against strong competition. Here we provide an assessment of the machine learning (ML) submissions made. Models submitted are assessed on: (1) their accuracy, in comparison to models developed with expert collaboration; and (2) their explanatory value for toxicology. The principal findings were: (a) using structural information available from a standard modelling package, layman-devised features, and outcomes of established biological tests, results from MLderived models were at least as good as those with expert-derived techniques. This was surprising; (b) the combined use of structural and biological features by ML-derived models was unusual, and suggested new avenues for toxicology modelling. This was also unexpected; and (c) significant effort was required to interpret the output of even the most "symbolic" of ML-derived models. Much of this could have been alleviated with measures for converting the results into a more "toxicology-friendly" form. As it stands, their absence is sufficient to prevent a whole-hearted acceptance of these promising methods by toxicologists. This suggests that ML techniques have been able to respond -not fully, but nevertheless substantially -to the PTE Challenge.