Scholarlink

<p>Large language models (LLMs) have transformed natural language processing with their improved performance compared with previous methods and have shown great potential to be adopted in other fields. The sequential nature of genomics data, such as deoxyribonucleic acid (DNA), ribonucleic acid (RNA), and proteins, makes it akin to human natural language, supporting the application of LLMs. Currently, LLMs have only been applied to genomic research for about four years but have already achieved significant advances in many challenging and important problems. This review summarizes the recent progress of applying LLMs in genomic research, including developing biological foundation models for protein, DNA, and RNA, as well as specialized models for interaction prediction, single-cell analysis, and structure prediction. The review discusses the challenges and potentials of adopting new advancements in LLMs for genomic applications and proposes several practical projects for integrating LLMs into genomics teaching and learning.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-Empowered Genome Decoding: Applications of Large Language Models in Genomics

  • 期刊论文

  • 发表日期：

    2025年3月1日

查看全文
  • Shaopeng Li,
  • Weiliang Fan,
  • Yu Zhou

摘要

Large language models (LLMs) have transformed natural language processing with their improved performance compared with previous methods and have shown great potential to be adopted in other fields. The sequential nature of genomics data, such as deoxyribonucleic acid (DNA), ribonucleic acid (RNA), and proteins, makes it akin to human natural language, supporting the application of LLMs. Currently, LLMs have only been applied to genomic research for about four years but have already achieved significant advances in many challenging and important problems. This review summarizes the recent progress of applying LLMs in genomic research, including developing biological foundation models for protein, DNA, and RNA, as well as specialized models for interaction prediction, single-cell analysis, and structure prediction. The review discusses the challenges and potentials of adopting new advancements in LLMs for genomic applications and proposes several practical projects for integrating LLMs into genomics teaching and learning.