+44 1223 790975
Scientific Tracks Abstracts: Drug Design
Obtaining satisfactory results with neural networks depends on the availability of large data samples. The use of small training sets generally reduces performance. We focus on the neuro-fuzzy prediction of biological activities of HIV-1 protease inhibitory compounds when inferring from small training sets. We propose two computational intelligence prediction techniques that are suitable for small training sets, at the expense of some computational overhead. Both techniques are based on the FAMR model. The FAMR is a Fuzzy ARTMAP (FAM) incremental learning system used for classification and probability estimation. During the learning phase, each sample pair is assigned a relevance factor proportional to the importance of that pair. The two proposed algorithms are: 1) The GA-FAMR algorithm, which is new, consists of two stages: a) optimizing the relevances assigned to the training data and b) training the FAMR. 2) The Ordered FAMR is derived from a known algorithm. Instead of optimizing relevances, it optimizes the order of data presentation. In our experiments, we compare these two algorithms with an algorithm not based on the FAM, the FS-GA-FNN. We conclude that when inferring from small training sets, both techniques are efficient, in terms of generalization capability and execution time. The computational overhead introduced is compensated by better accuracy. Finally, the proposed techniques are used to predict the biological activities of newly designed potential HIV-1 protease inhibitors.
Levente Fabry-Asztalos received the Ph.D degree in chemistry from Washington State University. He was a postdoctoral researcher at the University of Wisconsin-Madison. He is currently an Associate Professor at Central Washington University. His main research interests are the design and synthesis of small molecule inhibitor scaffolds against therapeutically important enzymes and the prediction of inhibitor properties using computational intelligence techniques.