An Initial Experiment into
Stereochemistry-Based Drug Design Using
Inductive Logic Programming

Stephen Muggleton
David Page
Ashwin Srinivasan
Oxford University Computing Laboratory
Wolfson Building
Parks Road
Oxford, OX1 3QD
United Kingdom


Abstract. Previous applications of Inductive Logic Programming to
drug design have not addressed stereochemistry, or the three-dimensional
aspects of molecules. While some success is possible without 
consideration of stereochemistry, researchers within the pharmaceutical industry
consider stereochemistry to be central to most drug design problems.
This paper reports on an experimental application of the ILP system
P-Progol to stereochemistry-based drug design. The experiment tests
whether P-Progol can identify the structure responsible for the 
activity of ACE (angiotensin-converting enzyme) inhibitors from 28 positive
examples, that is, from 28 molecules that display the activity of ACE
inhibition. ACE inhibitors are a widely-used form of medication for the
treatment of hypertension. It should be stressed that this structure was
already known prior to the experiment and therefore is not a new 
discovery; the experiment was proposed by a researcher within the 
pharmaceutical industry to test the applicability of ILP to stereochemistry-based
drug design. While the result of the experiment is quite positive, one
challenge remains before ILP can be applied to a multitude of drug design problems.
References

1.	A.K. Debnath, R.L Lopez de Compadre, G. Debnath, A.J. Schusterman, and
C. Hansch. Structure-activity relationship of mutagenic aromatic and 
heteroaromatic nitro compounds. correlation with molecular orbital energies and 
hydrophobicity. Journal of Medicinal Chemistry, 34(2):786  797, 1991,
2.	R. King, S. Muggleton, R. Lewis, and M. Sternberg. Drug design by machine 
learning: The use of inductive logic programming to model the structure-activity 
relationships of trimethoprim analogues binding to dihydrofolate reductase. Proceedings
of the National Academy of Sciences, 89(23), 1992.
3.	R. King, S. Muggleton, A. Srinivasan, and M. Sternberg. Structure-activity 
relationships derived by machine learning: the use of atoms and their bond connectives
to predict mutagenicity by inductive logic programming. Proceeding. of the National
Academy of Sciences, 93:438442, 1996.
4.	D. Mayer, C.B. Naylor, I. Motoc, and G.R. Marshall. A unique geometry of the 
active site of angiotensin-converting enzyme consistent with structure-activity studies.
Journal of Computer-Aided Molecular Design, 1:316, 1987.
5.	J. McMurry. Organic Chemistry (4th edition). Brooks/Cole Publishing Company,
Pacific Grove, 1996.
6.	S. Muggleton. Inverse entailment and Progol. New Generation Computing, 13:245
286, 1995.
7.	S. Muggleton and C. Feng. Efficient induction of logic programs. In Proceedings of
the First Conference on Algorithmic Learning Theory, Tokyo, 1990. Ohmsha.
8.	C. Ndellec, C. Rouveirol, H. Ad, F. Bergadano, and B. Tausend. Declarative bias
in ilp. In L. De Raedt, editor, Advances in Inductive Logic Programming, pages
82103. lOS Press, Amsterdam, 1996.
9.	Luc De Raedt. interactive Theory Revision: An Inductive Logic Programming 
Approach. Academic Press, London, 1992.
