Incorporating a multiobjective knowledge-based energy function into differential evolution for protein structure prediction

Despite the rapid development of computer techniques and the unremitting efforts of researchers, the protein structure prediction (PSP) problem remains challenging in computational biology and bioinformatics. In this study, we model the PSP problem as a multiobjective optimization problem and propose a free modeling approach called MODE-K to solve this problem. Our efforts center on two aspects. First, we use a knowledge-based energy function called RWplus as the evaluation criterion. This function is decomposed into two terms: a distance-dependent energy term and an orientation-dependent energy term. Second, we employ a multiobjective differential evolution coupled with an external archive to perform conformation space searching. After conformation space searching, a cluster method is introduced to select the final predicted structure from a set of decoy structures. We use eighteen test proteins to verify the performance of the proposed approach. The experimental results demonstrate the effectiveness of the proposed approach and indicate that incorporating knowledge-based energy functions into multiobjective approaches to solve the PSP problem is promising.