A Reinforcement Learning Approach for Solving the Fragment Assembly Problem

Abstract

The DNA fragment assembly is a very complex optimization problem important within many fields including bioinformatics and computational biology. The problem is NP-hard, that is why many computational techniques including computational intelligence algorithms were designed for finding good solutions for this problem. Since DNA fragment assembly is a crucial part of any sequencing project, researchers are still focusing on developing better assemblers. In this paper we aim at proposing a new reinforcement learning based model for solving the fragment assembly problem. We are particularly focusing on the DNA fragment assembly problem. Our model is based on a Q-learning agent-based approach. The experimental evaluation confirms a good performance of the proposed model and indicates the potential of our proposal.