2020/10/26 by Yong Song, Song, Yong Joon, Dong Jin Ji +7 · 1 citation
Biochemistry, Genetics and Molecular Biology · #Genomics and Phylogenetic Studies #Machine Learning in Bioinformatics #RNA and protein synthesis mechanisms
paper · pdf · doi:10.48550/arxiv.2010.13478
Various methods have been developed to analyze the association between\norganisms and their genomic sequences. Among them, sequence alignment is the\nmost frequently used for comparative analysis of biological genomes. However,\nthe traditional sequence alignment method is considerably complicated in\nproportion to the sequences' length, and it is significantly challenging to\nalign long sequences such as a human genome. Currently, several multiple\nsequence alignment algorithms are available that can reduce the complexity and\nimprove the alignment performance of various genomes. However, there have been\nrelatively fewer attempts to improve the alignment performance of the pairwise\nalignment algorithm. After grasping these problems, we intend to propose a new\nsequence alignment method using deep reinforcement learning. This research\nshows the application method of the deep reinforcement learning to the sequence\nalignment system and the way how the deep reinforcement learning can improve\nthe conventional sequence alignment method.\n