Logo[ ILPnet2 | Library | Newsletter | CSCW | Education | End-User Club | Events | Nodes | Systems | Applications | Members only ]

Knowledge discovery in biological and chemical domains

S. Muggleton. In H. Motoda, editor, Proceedings of the first Conference on Discovery Science, Berlin, 1998. More behind this link.. Springer-Verlag. Abstract of keynote talk

Abstract

This talk will review the results of the last few years' academic pilot studies involving the application of ILP to the prediction of protein secondary structure, mutagenicity, structure activity , pharmacophore discovery and protein fold analysis. While predictive accuracy is the central performance measure of data analytical techniques which generate procedural knowledge (neural nets, decision trees, etc.), the performance of an ILP system is determined both by accuracy and degree of stereo-chemical insight provided. ILP hypotheses can be easily stated in English and exemplified diagrammatically. This allows cross-checking with the relevant biological and chemical literature. Most importantly it allows for expert involvement in human background knowledge refinement and for final dissemination of discoveries to the wider scientific community. In several of the comparative trials presented ILP systems provided significant chemical and biological insights where other data analysis techniques did not.

In his statement of the importance of this line of research to the Royal Society Sternberg emphasised the aspect of joint human-computer collaboration in scientific discoveries. Science is an activity of human societies. It is our belief that computer-based scientific discovery must support strong integration into existing the social environment of human scientific communities. The discovered knowledge must add to and build on existing science. The author believes that the ability to incorporate background knowledge and re-use learned knowledge together with the comprehensibility of the hypotheses, have marked out ILP as a particularly effective approach for scientific knowledge discovery.

BibTeX entry.

Other publications


S H Muggleton, stephen@cs.york.ac.uk. Last modified on Wednesday 9 April 2003 at 18:31. © 2003 ILPnet2