Biological Sequence with Language Model Prompting: A Survey

2025-03-06

AI Summary

This work addresses key challenges in biomolecular sequence analysis—scarce labeled data, difficulties in multimodal fusion, and high computational costs—by introducing a novel large language model (LLM)-based prompt engineering paradigm. Methodologically, it establishes the first taxonomy of biosequence prompting tailored to DNA, RNA, protein, and drug discovery tasks; designs a cross-modal prompt fusion framework integrating few-shot/zero-shot learning, biology-aware tokenization, multimodal alignment, and domain-knowledge injection. The contributions include breaking reliance on traditional supervised learning, substantially alleviating data scarcity and computational bottlenecks; delivering a unified, interpretable, and accessible methodology that serves as a systematic entry point for bioinformaticians; and advancing practical LLM deployment in precision medicine and synthetic biology. (136 words)

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Prompt Engineering / Prompting
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Large Language models (LLMs) have emerged as powerful tools for addressing challenges across diverse domains. Notably, recent studies have demonstrated that large language models significantly enhance the efficiency of biomolecular analysis and synthesis, attracting widespread attention from academics and medicine. In this paper, we systematically investigate the application of prompt-based methods with LLMs to biological sequences, including DNA, RNA, proteins, and drug discovery tasks. Specifically, we focus on how prompt engineering enables LLMs to tackle domain-specific problems, such as promoter sequence prediction, protein structure modeling, and drug-target binding affinity prediction, often with limited labeled data. Furthermore, our discussion highlights the transformative potential of prompting in bioinformatics while addressing key challenges such as data scarcity, multimodal fusion, and computational resource limitations. Our aim is for this paper to function both as a foundational primer for newcomers and a catalyst for continued innovation within this dynamic field of study.

Problem

• Enhance biomolecular analysis using large language models.
• Apply prompt-based methods to biological sequence tasks.
• Address data scarcity and computational resource challenges.

Innovation

• Prompt-based methods with LLMs for biological sequences
• Prompt engineering for domain-specific bioinformatics tasks
• Addressing data scarcity and computational resource challenges