Representational/Efficiency Issues In Toxicological Knowledge Discovery

Bernhard Pfahringer, Eva Gottmann, Stefan Kramer, Christoph Helma

We tackle the problem of automatic detection of Structure- Activity relationships by means of Inductive Logic Programming (ILP). We describe an algorithm for constructing features from background knowledge (stochastic propositionalization - SP) and an abstract level representation for chemical compounds.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.