A hybrid EDA for protein folding based on HP model

Protein structure prediction (PSP) is one of the most important problems in computational biology. This paper proposes a novel hybrid estimation of distribution algorithm (EDA) to solve the PSP problem on HP model. First, a composite fitness function containing the information of folding structure core (H-core) is introduced to replace the traditional fitness function of HP model. The proposed fitness function is expected to select better individuals for the probabilistic model of EDA. Second, local search with guided operators is utilized to refine the found solutions for improving the efficiency of EDA. Third, an improved backtracking-based repairing method is proposed to repair invalid individuals sampled by the probabilistic model of EDA. It can significantly reduce the number of backtracking searching operation and the computational cost for a long-sequence protein. Experimental results demonstrate that the proposed method outperform the basic EDA method. At the same time, it is very competitive with other existing algorithms for the PSP problem on lattice HP models.