Automated Structural Classification of Proteins by Using Decision Trees and Structural Protein Features

Abstract

The protein function is tightly related to classification of proteins in hierarchical levels where proteins share same or similar functions. One of the most relevant protein classification schemes is the structural classification of proteins (SCOP). The SCOP scheme has one negative drawback; due to its manual classification methods, the dynamic of classification of new proteins is much slower than the dynamic of discovering novel protein structures in the protein data bank (PDB). In this work, we propose two approaches for automated protein classification. We extract protein descriptors from the structural coordinates stored in the PDB files. Then we apply C4.5 algorithm to select the most appropriate descriptor features for protein classification based on the SCOP hierarchy. We propose novel classification approach by introducing a bottom-up classification flow, and a multi-level classification approach. The results show that these approaches are much faster than other similar algorithms with comparable accuracy.