Advancing bioinformatics with language models: components, applications, and perspectives
Развитие биоинформатики с помощью языковых моделей: компоненты, применения и перспективы
2026-07-01
SCID: 54.1/uq5pekxj
Discuss with AI
bioinformaticsfoundation modelslarge language modelssingle-cell analysistransformer models
Figures from the paper
Abstract (AI)
Large language models (LLMs) are a class of artificial intelligence models based on deep learning, which have great performance in various tasks, especially in natural language processing (NLP). Large language models typically consist of artificial neural networks with numerous parameters, trained on large amounts of unlabeled input using self-supervised or semi-supervised learning. However, their potential for solving bioinformatics problems may even exceed their proficiency in modeling human language. In this review, we will provide a comprehensive overview of the essential components of large language models (LLMs) in bioinformatics, spanning genomics, transcriptomics, proteomics, drug discovery, and single-cell analysis. Key aspects covered include tokenization methods for diverse data types, the architecture of transformer models, the core attention mechanism, and the pre-training processes underlying these models. Additionally, we will introduce currently available foundation models and highlight their downstream applications across various bioinformatics domains. Finally, drawing from our experience, we will offer practical guidance for both LLM users and developers, emphasizing strategies to optimize their use and foster further innovation in the field.
Key Findings
1
Bioinformatics LLM applications are surveyed across genomics, transcriptomics, proteomics, drug discovery, and single-cell analysis.
2
Large language models may have substantial potential for bioinformatics beyond their established proficiency in human-language modeling.
3
Practical guidance is provided for LLM users and developers to optimize deployment and support further innovation in bioinformatics.
4
The review catalogs available foundation models and summarizes their downstream applications across multiple bioinformatics domains.
5
The review explains core bioinformatics LLM components, including tokenization, transformer architectures, attention mechanisms, and pre-training processes.
Research Object
large language models applied to bioinformatics data and tasks across genomics, transcriptomics, proteomics, drug discovery, and single-cell analysis
Research Subject
the components, architectures, pre-training processes, and downstream applications of large language models in bioinformatics
Publication Details
Publication Date
2026-07-01
Journal
Publisher
ISSN
Cited by
1
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
The STRING database in 2023: protein–protein association networks and functional enrichment analyses for any sequenced genome of interest2022
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome2021
DNA language models are powerful predictors of genome-wide variant effects2023
GENA-LM: a family of open-source foundational DNA language models for long sequences2024
DNA language model GROVER learns sequence context in the human genome2024
TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-xbinding analyses2021