A key element of bioinformatics research is the extraction of meaningful information from large experimental data sets. Various approaches, including statistical and graph theoretical methods, data mining, and computational pattern recognition, have been applied to this task with varying degrees of success. Using a suite of classifiers combined with evolutionary algorithms for parameter adjustment and feature extraction, we present a set of hybrid algorithms that employ simultaneous feature selection and extraction to isolate salient features from large medical and other biological data sets.

We have previously shown that a genetic algorithm coupled with a k-nearest-neighbors classifier performs well in extracting information about protein-water binding from X-ray crystallographic protein structure data. Here, the effectiveness of several new hybrid classifiers in feature selection and classification is demonstrated for this and other bioinformatic, medical, and scientific data sets.