摘要：The discriminant analysis of complementary units and repeated sequences of amino acids in an initial sample of 48 different enzymes produces practically useful empirical-functions which allow catalytic sites to be distinguished from non-catalytic sites. The independent variables in the discriminant functions were almost all composed of complementary units of amino acids, that is amino acid sequences whose nucleotide coding sequences were complementary to each other. In order of evaluate the validity of the functions, we applied them to the amino acid sequences of 17 different kinds of enzymes as well as 30 non-enzymes such as receptors, oncoproteins, cytokines, hormones and so on. The functions proved to be effective in predicting not only the catalytic sites of enzymes but also the binding sites of the other proteins. The result suggests that complementary units are evolutionarily conserved as a signal around the active sites of various proteins.
