Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large Language Models for Bioinformatics

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

TL;DR

This survey analyzes the accelerating integration of large language models and BioLMs in bioinformatics, spanning genomics, proteomics, metabolomics, drug discovery, and clinical applications. It presents a framework for understanding LLM foundations, training paradigms, and domain-specific datasets, while outlining a spectrum of applications from DNA/RNA analysis to protein design and vaccine development. The paper introduces Life Active Factors (LAFs) as a unifying concept to harmonize sequence, structure, and function across biological scales and discusses key challenges including data quality, privacy, interpretability, and scalability. It also highlights milestones such as AlphaFold3 and domain-specific protein and genome LLMs, and outlines future directions toward multimodal fusion, efficient training regimes, and responsible deployment with real-world impact in precision medicine and public health.

Abstract

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.

Large Language Models for Bioinformatics

TL;DR

This survey analyzes the accelerating integration of large language models and BioLMs in bioinformatics, spanning genomics, proteomics, metabolomics, drug discovery, and clinical applications. It presents a framework for understanding LLM foundations, training paradigms, and domain-specific datasets, while outlining a spectrum of applications from DNA/RNA analysis to protein design and vaccine development. The paper introduces Life Active Factors (LAFs) as a unifying concept to harmonize sequence, structure, and function across biological scales and discusses key challenges including data quality, privacy, interpretability, and scalability. It also highlights milestones such as AlphaFold3 and domain-specific protein and genome LLMs, and outlines future directions toward multimodal fusion, efficient training regimes, and responsible deployment with real-world impact in precision medicine and public health.

Abstract

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.
Paper Structure (50 sections, 1 figure)

This paper contains 50 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Background of Language Models and Foundation Models in Bioinformatics
  3. Foundations of Language Models and Bioinformatics Overview
  4. Basics of Large Language Models and Foundations Models
  5. Bioinformatics Applications and Challenges
  6. Training Methods and Models
  7. Bioinformatics-Specific Datasets
  8. Model Evolution and Key Milestones
  9. Applications in Bioinformatics Problems
  10. Genome Level
  11. LLM for DNA Analysis
  12. LLM for RNA Analysis
  13. Gene Products Level
  14. Epigenomics
  15. Protein Level
  16. ...and 35 more sections

Figures (1)

  • Figure 1: The applications of the methodology of LLMs in bioinformatics tasks.