Adoption of an improved PSO to explore a compound multi-objective energy function in protein structure prediction.

•Modeling protein structure prediction problem as a multi-objective optimization problem.•A physics-based energy function and a knowledge-based energy function are combined to construct a compound three-objective energy function to evaluate a predicted conformation of a protein.•An improved multi-objective particle swarm optimization coupled with two archives is employed to execute conformation space search.•A mechanism based on Pareto non-dominated sorting is designed to tackle the slightly worse solutions properly. It is analogous to other traditional methods based on single-objective optimization.