Computing Publications

Publications Home » Abduction and induction for learn...

Abduction and induction for learning models of inhibition in metabolic networks

Alireza Tamaddoni Nezhad, Raphael Chaleil, Antonis Kakas, Stephen Muggleton

Conference or Workshop Paper
Proceedings of the International Conference on Machine Learning and Applications (ICMLA'05)
IEEE Computer Society
DOI 10.1109/ICMLA.2005.6

This paper describes the use of a mixture of abduction and induction for the temporal modelling of the effects of toxins in metabolic networks. Background knowledge is used which describes network topology and functional classes of enzymes. This background knowledge, which represents the present state of understanding, is incomplete. In order to overcome this incompleteness hypotheses are considered which consist of a mixture of specific inhibitions of enzymes (ground facts) together with general (non-ground) rules which predict classes of enzymes likely to be inhibited by the toxin. The foreground examples were derived from in vivo experiments involving NMR analysis of time-varying metabolite concentrations in rat urine following injections of toxin. Hypotheses about inhibition are built using the Inductive Logic Programming system Progol5.0 and predictive accuracy is assessed for both the ground and the non-ground cases.

BibTEX file for the publication built & maintained by Ashok Argent-Katwala.