Hybrid Learning Algorithm in Neural Network System for Enzyme Classification

Nucleic acid and protein sequences store a wealth of informationwhich ultimately determines their functions and characteristics. Protein sequences classification deals with the assignment ofsequences to known categories based on homology detectionproperties. In this paper, we developed a hybrid learning algorithm inneural network system called Neural Network Enzyme Classification (NNEC) to classify an enzyme found in Protein Data Bank (PDB) to agiven family of enzymes. NNEC was developed based on MultilayerPerceptron with hybrid learning algorithm combining the geneticalgorithm (GA) and Backpropagation (BP), where one of them acts asan operator in the other. Here, BP is used as a mutation-like-operatorof the general GA search template. The proposed hybrid model wastested with different topologies of network architecture, especially indetermining the number of hidden nodes. The precision results arequite promising in classifying the enzyme accordingly