Using reinforcement learning in genome assembly: in-depth analysis of a Q-learning assembler.

IF 3.9 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY
Frontiers in bioinformatics Pub Date : 2025-08-20 eCollection Date: 2025-01-01 DOI:10.3389/fbinf.2025.1633623
Kleber Padovani, Rafael Cabral Borges, Roberto Xavier, André Carlos Carvalho, Anna Reali, Annie Chateau, Ronnie Alves
{"title":"Using reinforcement learning in genome assembly: in-depth analysis of a Q-learning assembler.","authors":"Kleber Padovani, Rafael Cabral Borges, Roberto Xavier, André Carlos Carvalho, Anna Reali, Annie Chateau, Ronnie Alves","doi":"10.3389/fbinf.2025.1633623","DOIUrl":null,"url":null,"abstract":"<p><p>Genome assembly remains an unsolved problem, and de novo strategies (i.e., those run without a reference) are relevant but computationally complex tasks in genomics. Although de novo assemblers have been previously successfully applied in genomic projects, there is still no \"best assembler\", and the choice and setup of assemblers still rely on bioinformatics experts. Thus, as with other computationally complex problems, machine learning has emerged as an alternative (or complementary) way to develop accurate, fast and autonomous assemblers. Reinforcement learning has proven promising for solving complex activities without supervision, such as games, and there is a pressing need to understand the limits of this approach to \"real-life\" problems, such as the DNA fragment assembly problem. In this study, we analyze the boundaries of applying machine learning via reinforcement learning (RL) for genome assembly. We expand upon the previous approach found in the literature to solve this problem by carefully exploring the learning aspects of the proposed intelligent agent, which uses the Q-learning algorithm. We improved the reward system and optimized the exploration of the state space based on pruning and in collaboration with evolutionary computing (>300% improvement). We tested the new approaches on 23 environments. Our results suggest the unsatisfactory performance of the approaches, both in terms of assembly quality and execution time, providing strong evidence for the poor scalability of the studied reinforcement learning approaches to the genome assembly problem. Finally, we discuss the existing proposal, complemented by attempts at improvement that also proved insufficient. In doing so, we contribute to the scientific community by offering a clear mapping of the limitations and challenges that should be taken into account in future attempts to apply reinforcement learning to genome assembly.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"5 ","pages":"1633623"},"PeriodicalIF":3.9000,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12405310/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in bioinformatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fbinf.2025.1633623","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Genome assembly remains an unsolved problem, and de novo strategies (i.e., those run without a reference) are relevant but computationally complex tasks in genomics. Although de novo assemblers have been previously successfully applied in genomic projects, there is still no "best assembler", and the choice and setup of assemblers still rely on bioinformatics experts. Thus, as with other computationally complex problems, machine learning has emerged as an alternative (or complementary) way to develop accurate, fast and autonomous assemblers. Reinforcement learning has proven promising for solving complex activities without supervision, such as games, and there is a pressing need to understand the limits of this approach to "real-life" problems, such as the DNA fragment assembly problem. In this study, we analyze the boundaries of applying machine learning via reinforcement learning (RL) for genome assembly. We expand upon the previous approach found in the literature to solve this problem by carefully exploring the learning aspects of the proposed intelligent agent, which uses the Q-learning algorithm. We improved the reward system and optimized the exploration of the state space based on pruning and in collaboration with evolutionary computing (>300% improvement). We tested the new approaches on 23 environments. Our results suggest the unsatisfactory performance of the approaches, both in terms of assembly quality and execution time, providing strong evidence for the poor scalability of the studied reinforcement learning approaches to the genome assembly problem. Finally, we discuss the existing proposal, complemented by attempts at improvement that also proved insufficient. In doing so, we contribute to the scientific community by offering a clear mapping of the limitations and challenges that should be taken into account in future attempts to apply reinforcement learning to genome assembly.

Abstract Image

Abstract Image

Abstract Image

在基因组组装中使用强化学习:对q学习组装器的深入分析。
基因组组装仍然是一个未解决的问题,而de novo策略(即那些在没有参考的情况下运行的策略)是基因组学中相关但计算复杂的任务。尽管de novo组装器已经成功地应用于基因组项目中,但目前还没有“最佳组装器”,组装器的选择和设置仍然依赖于生物信息学专家。因此,与其他计算复杂的问题一样,机器学习已经成为开发准确、快速和自主组装器的一种替代(或补充)方式。强化学习已经被证明可以在没有监督的情况下解决复杂的活动,比如游戏,并且迫切需要了解这种方法在“现实生活”问题上的局限性,比如DNA片段组装问题。在本研究中,我们分析了通过强化学习(RL)在基因组组装中应用机器学习的边界。我们扩展了先前在文献中发现的方法,通过仔细探索所提出的智能代理的学习方面来解决这个问题,该智能代理使用q -学习算法。我们改进了奖励系统,优化了基于修剪的状态空间探索,并与进化计算协作(改进了300%)。我们在23个环境中测试了这些新方法。我们的研究结果表明,这些方法在组装质量和执行时间方面的性能都不令人满意,这为所研究的基因组组装问题的强化学习方法的可扩展性差提供了强有力的证据。最后,我们讨论现有的建议,并加以改进的尝试,但这些尝试也证明是不够的。通过这样做,我们为科学界提供了一个清晰的局限性和挑战的地图,这些局限性和挑战应该在未来尝试将强化学习应用于基因组组装时加以考虑。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
2.60
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信