Prediction of enzyme family classes

Classes of newly found enzyme sequences are usually determined either by biochemical analysis of eukaryotic and prokaryotic genomes or by microarray chips. These experimental methods are both time-consuming and costly. With the explosion of protein sequences entering into databanks, it is highly desirable to explore the feasibility of selectively classifying newly found enzyme sequences into their respective enzyme classes by means of an automated method. This is indeed important because knowing which family or subfamily an enzyme belongs to may help deduce its catalytic mechanism and specificity, giving clues to the relevant biological function. In this study, a bioinformatical analysis was conducted for 2640 oxidoreductases classified into 16 subclasses according to the different types of substrates they act on during the catalytic process. Although it is an extremely complicated problem and might involve the knowledge of 3-dimensional structure as well as many other physical chemistry factors, some quite promising results have been obtained indicating that the family or subfamily of an enzyme is predictable to a considerable degree by means of sequence-based approach alone if a good training dataset can be established.