Song Yong-Joon, Ji Dong Jin, Seo Hyein, Han Gyu-Bum, Cho Dong-Ho
School of Electrical EngineeringKorea Advanced Institute of Science and Technology Daejeon 305-701 South Korea.
IEEE Open J Eng Med Biol. 2021 Jan 29;2:36-43. doi: 10.1109/OJEMB.2021.3055424. eCollection 2021.
Various methods have been developed to analyze the association between organisms and their genomic sequences. Among them, sequence alignment is the most frequently used method for comparative analysis of biological genomes. We intend to propose a novel pairwise sequence alignment method using deep reinforcement learning to break out the old pairwise alignment algorithms. We defined the environment and agent to enable reinforcement learning in the sequence alignment system. This novel method, named DQNalign, can immediately determine the next direction by observing the subsequences within the moving window. DQNalign shows superiority in the dissimilar sequence pairs that have low identity values. And theoretically, we confirm that DQNalign has a low dimension for the sequence length in view of the complexity. This research shows the application method of deep reinforcement learning to the sequence alignment system and how deep reinforcement learning can improve the conventional sequence alignment method.
已经开发出各种方法来分析生物体与其基因组序列之间的关联。其中，序列比对是生物基因组比较分析中最常用的方法。我们打算提出一种使用深度强化学习的新型成对序列比对方法，以突破旧的成对比对算法。我们定义了环境和智能体，以便在序列比对系统中进行强化学习。这种名为DQNalign的新方法可以通过观察移动窗口内的子序列立即确定下一个方向。DQNalign在具有低同一性值的不相似序列对中表现出优越性。并且从理论上讲，鉴于复杂性，我们确认DQNalign对于序列长度具有低维度。这项研究展示了深度强化学习在序列比对系统中的应用方法，以及深度强化学习如何改进传统的序列比对方法。
