arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.04718q-bio.GNcs.AI
收藏

知识引导的无标签单细胞RNA测序数据生物标志物识别:一种强化学习视角

Knowledge-Guided Biomarker Identification for Label-Free Single-Cell RNA-Seq Data: A Reinforcement Learning Perspective

Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);DUKE-NUS Medical School, National University of Singapore(新加坡国立大学杜克-国立大学医学学院);University of Chinese Academy of Sciences(中国科学院大学);Institute for Infocomm Research, Agency for Science, Technology, and Research(科技研究局信息与通信研究所);Singapore University of Technology and Design(新加坡科技与设计大学);Information Systems Technology and Design Pillar(信息系统技术与设计学院);University of Science and Technology of China(中国科学技术大学)

Meng Xiao, Weiliang Zhang, Xiaohan Huang, Hengshu Zhu, Min Wu, Xiaoli Li, Yuanchun Zhou

AI总结:

本文提出一种结合集成先验知识与强化学习的迭代基因面板选择方法,用于无标签单细胞RNA测序数据中的生物标志物识别,通过专家行为塑造奖励函数动态优化选择,实验证明其提高了精确性和效率。

摘要:

基因面板选择旨在无标签基因组数据集中识别最具信息量的基因组生物标志物。传统方法依赖于领域专业知识、嵌入式机器学习模型或基于启发式的迭代优化,常常引入偏差和低效,可能掩盖关键的生物学信号。为应对这些挑战,我们提出了一种迭代式基因面板选择策略,该策略利用现有基因选择算法的集成知识来建立初步边界或先验知识,从而引导初始搜索空间。随后,我们通过由专家行为塑造的奖励函数引入强化学习,实现对基因面板的动态优化和定向选择。这种整合减轻了初始边界带来的偏差,同时利用了强化学习的随机适应性。全面的比较实验、案例研究和下游分析证明了我们方法的有效性,突显了其在无标签生物标志物发现中提高的精确性和效率。我们的结果强调了该方法在推进单细胞基因组学数据分析方面的潜力。

英文摘要:

Gene panel selection aims to identify the most informative genomic biomarkers in label-free genomic datasets. Traditional approaches, which rely on domain expertise, embedded machine learning models, or heuristic-based iterative optimization, often introduce biases and inefficiencies, potentially obscuring critical biological signals. To address these challenges, we present an iterative gene panel selection strategy that harnesses ensemble knowledge from existing gene selection algorithms to establish preliminary boundaries or prior knowledge, which guide the initial search space. Subsequently, we incorporate reinforcement learning through a reward function shaped by expert behavior, enabling dynamic refinement and targeted selection of gene panels. This integration mitigates biases stemming from initial boundaries while capitalizing on RL's stochastic adaptability. Comprehensive comparative experiments, case studies, and downstream analyses demonstrate the effectiveness of our method, highlighting its improved precision and efficiency for label-free biomarker discovery. Our results underscore the potential of this approach to advance single-cell genomics data analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑