Abstract
Multiple sequence alignment methods refer to a series of algorithmic solutions for the alignment of evolutionary-related sequences while taking into account evolutionary events such as mutations, insertions, deletions, and rearrangements under certain conditions. In this article, we propose a method with Q-learning based on the Actor-Critic model for sequence alignment. We transform the sequence alignment problem into an agent's autonomous learning process. In this process, the reward of the possible next action taken is calculated, and the cumulative reward of the entire process is calculated. The results show that the method we propose is better than the gene algorithm and the dynamic programming method.
- S. Makigaki and T. Ishida. 2020. Sequence alignment using machine learning for accurate template-based protein structure prediction. Bioinformatics 36, 1 (2020), 104–111.Google ScholarCross Ref
- S. B. Needleman and C. D. Wunsch. 1970. A general method applicable to the search for similarities in the amino acid sequence of two proteins. Journal of Molecular Biology 48 (1970) 443–453.Google ScholarCross Ref
- J. D. Thompson, D. G. Higgins, and T. J. Gibson. 1994. Improved sensitivity of profile searched through the use of sequence weights and gap excision. Computer Applications in the Biosciences 10 (1994) 19–29.Google Scholar
- C. Notredame, D. G. Higgins, and J. Heringa. 2000. T-Coffee: A novel method for fast and accurate multiple sequence alignment. Journal of Molecular Biology 02 (2000), 205–217.Google ScholarCross Ref
- K. M. Chao, J. Zhang, J. Ostell, et al. 1995. A local alignment tool for very long DNA sequences [J]. Comput Appl Biosci 11, 2 (1995), 147–153.Google Scholar
- X. Lei, J. Sun, X. Xu, and L. Guo. 2010. Artificial bee colony algorithm for solving multiple sequence alignment. In Proceedings of the 5th IEEE International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA’10). 337–342.Google Scholar
- C. Mirabello and B. Wallner. 2019. rawMSA: End-to-end deep learning using raw multiple sequence alignments. PLoS One 14, 8 (2019), e0220182.Google ScholarCross Ref
- B. Rost and C. Sander. 1993. Prediction of protein secondary structure at better than 70% accuracy. Journal of Molecular Biology 232, 2 (1993), 584–599.Google ScholarCross Ref
- J. A. Cuff and G. J. Barton. 2000. Application of multiple sequence alignment profiles to improve protein secondary structure prediction. Proteins: Structure, Function, and Bioinformatics 40, 3 (2000), 502–511.Google ScholarCross Ref
- J. D. Thompson, B. Linard, O. Lecompte O, and O. Poch. 2011. A comprehensive benchmark study of multiple sequence alignment methods: Current challenges and future perspectives. PLoS One 6, 3 (2011), e18093.Google ScholarCross Ref
- C. Kemena and C. Notredame. 2009. Upcoming challenges for multiple sequence alignment methods in the high-throughput era. Bioinformatics 25 (2009), 2455–2465. Google ScholarDigital Library
- S. Kumar and A. Filipski, 2007. Multiple sequence alignment: In pursuit of homologous DNA positions. Genome Research 17 (2007), 127–135.Google ScholarCross Ref
- B. Morgenstern, S. J. Prohaska, D. Pöhler, and P. F. Stadler. 2006. Multiple sequence alignment with user-defined anchor points. Algorithms for Molecular Biology 1 (2006), 6. Google ScholarDigital Library
- C. Notredame. 2002. Recent progress in multiple sequence alignment: A survey. Pharmacogenomics 3, 1 (2002), 131–144.Google ScholarCross Ref
- S. F. Altschul and D. J. Lipman. 1989. Trees, stars, and multiple biological sequence alignment. SIAM Journal on Applied Mathematics 49, (1989), 197–209. Google ScholarDigital Library
- C. B. Do and K. Katoh. 2008. Protein multiple sequence alignment. Methods in Molecular Biology 484 (2008), 379–413.Google ScholarCross Ref
Index Terms
- Sequence Alignment with Q-Learning Based on the Actor-Critic Model
Recommendations
Backward Q-learning: The combination of Sarsa algorithm and Q-learning
Reinforcement learning (RL) has been applied to many fields and applications, but there are still some dilemmas between exploration and exploitation strategy for action selection policy. The well-known areas of reinforcement learning are the Q-learning ...
Supervised Advantage Actor-Critic for Recommender Systems
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data MiningCasting session-based or sequential recommendation as reinforcement learning (RL) through reward signals is a promising research direction towards recommender systems (RS) that maximize cumulative profits. However, the direct use of RL algorithms in the ...
Evaluation of reinforcement learning techniques
IITM '10: Proceedings of the First International Conference on Intelligent Interactive Technologies and MultimediaReinforcement learning is became one of the most important approaches to machine intelligence. Now RL is widely use by different research field as intelligent control, robotics and neuroscience. It provides us possible solution within unknown ...
Comments