论文部分内容阅读
The Enzyme Commission (EC) classification system is widely used in chemistry and biology and is maintained by the Nomenclature Committee of the International Union of Biochemistry and Molecular Biology (NC-IUBMB).Enzymes are classified into six main classes ; each main class is reclassified into several subclasses ; a subclass is classified into subsubclasses.In this EC system, each enzyme has its unique EC number: EC a.b.c.d, where "a" refers to the six main classes of enzymes ; "b" indicates the subclasses ; "c" represents the subsubclasses ; "d" is the serial number of the enzyme in its subsubclass.This method of enzyme classification is based on several criteria, such as reaction types, substrates, transferred groups, and acceptor groups.In this work, several computational models for classification of reactions catalyzed by hydrolases and oxidoreductases were developed using three different computational methods.The overall breaking and making of bonds of reactions were considered.Six physicochemical properties for the reacting bond in the substrate of each enzymatic reaction were calculated to describe the characteristics of each reaction.The 311 reactions catalyzed by hydrolases (EC 3.b.c.d) and the 651 reactions catalyzed by oxidoreductases (EC 1.b.c.d) were classified by Kohonens Self-Organizing Map (SOM), by a support vector machine (SVM), and by hierarchical clustering analysis (HCA).For the 31l reactions catalyzed by hydrolases, the classification accuracy of 95.8% by a SOM and 97.7% by an SVM was achieved.For the 651 reactions catalyzed by oxidoreductases, the classification accuracy was 93.4% and 96.3% by a SOM and a SVM, respectively.The similarities of reactions reflected by the physicochemical effects of reacting bonds were compared with the traditional Enzyme Commission (EC) classification system .