Generalized biological foundation model with unified nucleic acid and protein language

Abstract The language of biology, encoded in DNA, RNA and proteins, forms the foundation of life but remains challenging to decode owing to its complexity. Traditional computational methods often struggle to integrate information across these molecules, limiting a comprehensive understanding of biological systems. Advances in natural language processing with pre-trained models offer possibilities for interpreting biological language. Here we introduce LucaOne, a pre-trained foundation model trained on nucleic acid and protein sequences from 169,861 species. Through large-scale data integration and semi-supervised learning, LucaOne shows an understanding of key biological principles, such as DNA–protein translation. Using few-shot learning, it effectively comprehends the central dogma of molecular biology and performs competitively on tasks involving DNA, RNA or protein inputs. Our results highlight the potential of unified foundation models to address complex biological questions, providing an adaptable framework for bioinformatics research and enhancing the interpretation of life’s complexity.

Authors

Institutions

Publication Details

Journal
Nature Machine Intelligence
Published
2025-06-18
DOI
https://doi.org/10.1038/s42256-025-01044-4
Citations
20
Primary Topic
RNA and protein synthesis mechanisms
Type
article
Field-Weighted Citation Impact
16.12
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Generalized biological foundation model with unified nucleic acid and protein language

Yanhong Wei, Yi Liu, Jieping Ye, Yongtao Shan et al.
20 citations
Nature Machine Intelligence
RNA and protein synthesis mechanisms
16.12
article

Generalized biological foundation model with unified nucleic acid and protein language

Yanhong Wei, Yi Liu, Jieping Ye, Yongtao Shan, Yuanfei Pan, Pan Fang, Zhenyu Zeng, Yihao Chen, Yichang Chen, Zhan Zhou, Edward C. Holmes, Jun Li, Feng Zhu, Zhaorong Li, Yong He, Yuelong Shu, Mǎng Shī
article en
20 citations

Abstract

Abstract The language of biology, encoded in DNA, RNA and proteins, forms the foundation of life but remains challenging to decode owing to its complexity. Traditional computational methods often struggle to integrate information across these molecules, limiting a comprehensive understanding of biological systems. Advances in natural language processing with pre-trained models offer possibilities for interpreting biological language. Here we introduce LucaOne, a pre-trained foundation model trained on nucleic acid and protein sequences from 169,861 species. Through large-scale data integration and semi-supervised learning, LucaOne shows an understanding of key biological principles, such as DNA–protein translation. Using few-shot learning, it effectively comprehends the central dogma of molecular biology and performs competitively on tasks involving DNA, RNA or protein inputs. Our results highlight the potential of unified foundation models to address complex biological questions, providing an adaptable framework for bioinformatics research and enhancing the interpretation of life’s complexity.

Nature Machine IntelligenceVol. 7(6)
The University of Sydney (AU), Sun Yat-sen University (CN), City University of Hong Kong (HK), Chinese Academy of Medical Sciences & Peking Union Medical College (CN), Fudan University (CN), Taronga Conservation Society Australia (AU), Second Affiliated Hospital of Zhejiang University (CN), Institute of Infection and Immunity (CA), Alibaba Group (China) (CN), Zhejiang University (CN)
Quality Education
Openalex Percentile: Top 1%
RNA and protein synthesis mechanisms
16.12
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.