arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.06271q-bio.QMcs.AIcs.CE
收藏

面向生物信息学的大语言模型

Large Language Models for Bioinformatics

School of Computing, University of Georgia(佐治亚大学计算学院);University of Texas at Arlington(德克萨斯大学阿灵顿分校);Department of Statistics, University of Georgia(佐治亚大学统计系);Department of Epidemiology and Biostatistics, University of Georgia(佐治亚大学流行病学与生物统计系);UNC Chapel Hill(北卡罗来纳大学教堂山分校);Mayo Clinic(梅奥诊所);School of Computer and Cyber Sciences, Augusta University(奥古斯塔大学计算机与网络科学学院)
Wei Ruan, Yanjun Lyu, Jing Zhang, Jiazhang Cai, Peng Shu, Yang Ge, Yao Lu, Shang Gao, Yue Wang, Peilong Wang, Lin Zhao, Tao Wang, Yufang Liu, Luyang Fang, Ziyu … 展开作者

Wei Ruan, Yanjun Lyu, Jing Zhang, Jiazhang Cai, Peng Shu, Yang Ge, Yao Lu, Shang Gao, Yue Wang, Peilong Wang, Lin Zhao, Tao Wang, Yufang Liu, Luyang Fang, Ziyu Liu, Zhengliang Liu, Yiwei Li, Zihao Wu, Junhao Chen, Hanqi Jiang, Yi Pan, Zhenyuan Yang, Jingyuan Chen, Shizhe Liang, Wei Zhang, Terry Ma, Yuan Dou, Jianli Zhang, Xinyu Gong, Qi Gan, Yusong Zou, Zebang Chen, Yuanxin Qian, Shuo Yu, Jin Lu, Kenan Song, Xianqiao Wang, Andrea Sikora, Gang Li, Xiang Li, Quanzheng Li, Yingfeng Wang, Lu Zhang, Yohannes Abate, Lifang He, Wenxuan Zhong, Rongjie Liu, Chao Huang, Wei Liu, Ye Shen, Ping Ma, Hongtu Zhu, Yajun Yan, Dajiang Zhu, Tianming Liu

AI总结:

该综述系统梳理了生物信息学专用大语言模型BioLMs的演化、分类、训练方法与应用场景,分析其现存挑战,并指明未来发展方向,为相关研究与临床应用提供参考。

摘要:

随着大语言模型(LLM)技术的快速发展以及生物信息学专用语言模型(BioLMs)的出现,人们越来越需要对当前的研究格局、计算特性和多样化应用进行全面分析。本综述旨在满足这一需求,对BioLMs展开系统梳理,重点聚焦其演化历程、分类方式与独有特征,同时详细考察训练方法、数据集与评估框架。我们探究了BioLMs在疾病诊断、药物发现、疫苗研发等关键领域的广泛应用,凸显其在生物信息学中的影响力与变革潜力。我们明确了BioLMs固有的核心挑战与局限,包括数据隐私与安全问题、可解释性缺陷、训练数据与模型输出的偏差,以及领域适配的复杂性。最后,我们点明了新兴趋势与未来方向,为研究人员和临床工作者提供宝贵参考,助力推动BioLMs发展以适配更复杂的生物与临床应用场景。

英文摘要:

With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide-ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications.

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。

↑