HIPS, A HYBRID SELF-ADAPTING EXPERT-SYSTEM FOR NUCLEAR-MAGNETIC-RESONANCE SPECTRUM INTERPRETATION USING GENETIC ALGORITHMS

An automatic system for the interpretation of two-dimensional NMR spec tra of proteins, HIPS, is presented. Several artificial intelligence t echniques are combined to form a flexible, hybrid system that has (lim ited) learning capabilities. Following the structure of the problem, t he system is divided in modules with distinct functionalities. The fir st two modules are rule-based, and can be validated and refined semi-a utomatically using a set of already interpreted spectra. In this way, an optimized ruleset can be obtained to interpret unknown spectra. Res ults indicate a significant effect of training on performance. In the third module, a genetic algorithm is used to tackle a search problem o f huge dimensions in which patterns found in the NMR spectra should be mapped to amino acids in the sequence.