# A new hybrid genetic algorithm for protein structure prediction on the 2D triangular lattice

## TL;DR

This paper introduces a hybrid genetic algorithm combining genetic algorithms, tabu search, and local search to improve protein structure prediction on 2D triangular lattice models, demonstrating superior solution quality over existing methods.

## Contribution

A novel hybrid heuristic algorithm for protein structure prediction that integrates three optimization techniques to enhance solution quality on lattice models.

## Key findings

- The proposed algorithm outperforms state-of-the-art methods on benchmark instances.
- Experimental results show improved solution quality.
- The hybrid approach effectively explores the search space.

## Abstract

The flawless functioning of a protein is essentially linked to its own three-dimensional structure. Therefore, the prediction of a protein structure from its amino acid sequence is a fundamental problem in many fields that draws researchers attention. This problem can be formulated as a combinatorial optimization problem based on simplified lattice models such as the hydrophobic-polar model. In this paper, we propose a new hybrid algorithm combining three different well-known heuristic algorithms: genetic algorithm, tabu search strategy and local search algorithm in order to solve the PSP problem. Regarding the assessment of suggested algorithm, an experimental study is included, where we considered the quality of the produced solution as the main quality criterion. Furthermore, we compared the suggested algorithm with state-of-the-art algorithms using a selection of well-studied benchmark instances.