Nature Language Model: Deciphering the Language of Nature for Scientific Discovery
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916801925873664 |
|---|---|
| author | Xia, Yingce Jin, Peiran Xie, Shufang He, Liang Cao, Chuan Luo, Renqian Liu, Guoqing Wang, Yue Liu, Zequn Chen, Yuan-Jyue Guo, Zekun Bai, Yeqi Deng, Pan Min, Yaosen Lu, Ziheng Hao, Hongxia Yang, Han Li, Jielan Liu, Chang Zhang, Jia Zhu, Jianwei Bi, Ran Wu, Kehan Zhang, Wei Gao, Kaiyuan Pei, Qizhi Wang, Qian Liu, Xixian Li, Yanting Zhu, Houtian Lu, Yeqing Ma, Mingqian Wang, Zun Xie, Tian Maziarz, Krzysztof Segler, Marwin Yang, Zhao Chen, Zilong Shi, Yu Zheng, Shuxin Wu, Lijun Hu, Chen Dai, Peggy Liu, Tie-Yan Liu, Haiguang Qin, Tao |
| author_facet | Xia, Yingce Jin, Peiran Xie, Shufang He, Liang Cao, Chuan Luo, Renqian Liu, Guoqing Wang, Yue Liu, Zequn Chen, Yuan-Jyue Guo, Zekun Bai, Yeqi Deng, Pan Min, Yaosen Lu, Ziheng Hao, Hongxia Yang, Han Li, Jielan Liu, Chang Zhang, Jia Zhu, Jianwei Bi, Ran Wu, Kehan Zhang, Wei Gao, Kaiyuan Pei, Qizhi Wang, Qian Liu, Xixian Li, Yanting Zhu, Houtian Lu, Yeqing Ma, Mingqian Wang, Zun Xie, Tian Maziarz, Krzysztof Segler, Marwin Yang, Zhao Chen, Zilong Shi, Yu Zheng, Shuxin Wu, Lijun Hu, Chen Dai, Peggy Liu, Tie-Yan Liu, Haiguang Qin, Tao |
| contents | Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation models, researchers have developed foundation models for individual scientific domains, including small molecules, materials, proteins, DNA, RNA and even cells. However, these models are typically trained in isolation, lacking the ability to integrate across different scientific domains. Recognizing that entities within these domains can all be represented as sequences, which together form the "language of nature", we introduce Nature Language Model (NatureLM), a sequence-based science foundation model designed for scientific discovery. Pre-trained with data from multiple scientific domains, NatureLM offers a unified, versatile model that enables various applications including: (i) generating and optimizing small molecules, proteins, RNA, and materials using text instructions; (ii) cross-domain generation/design, such as protein-to-molecule and protein-to-RNA generation; and (iii) top performance across different domains, matching or surpassing state-of-the-art specialist models. NatureLM offers a promising generalist approach for various scientific tasks, including drug discovery (hit generation/optimization, ADMET optimization, synthesis), novel material design, and the development of therapeutic proteins or nucleotides. We have developed NatureLM models in different sizes (1 billion, 8 billion, and 46.7 billion parameters) and observed a clear improvement in performance as the model size increases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07527 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Nature Language Model: Deciphering the Language of Nature for Scientific Discovery Xia, Yingce Jin, Peiran Xie, Shufang He, Liang Cao, Chuan Luo, Renqian Liu, Guoqing Wang, Yue Liu, Zequn Chen, Yuan-Jyue Guo, Zekun Bai, Yeqi Deng, Pan Min, Yaosen Lu, Ziheng Hao, Hongxia Yang, Han Li, Jielan Liu, Chang Zhang, Jia Zhu, Jianwei Bi, Ran Wu, Kehan Zhang, Wei Gao, Kaiyuan Pei, Qizhi Wang, Qian Liu, Xixian Li, Yanting Zhu, Houtian Lu, Yeqing Ma, Mingqian Wang, Zun Xie, Tian Maziarz, Krzysztof Segler, Marwin Yang, Zhao Chen, Zilong Shi, Yu Zheng, Shuxin Wu, Lijun Hu, Chen Dai, Peggy Liu, Tie-Yan Liu, Haiguang Qin, Tao Artificial Intelligence Machine Learning Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation models, researchers have developed foundation models for individual scientific domains, including small molecules, materials, proteins, DNA, RNA and even cells. However, these models are typically trained in isolation, lacking the ability to integrate across different scientific domains. Recognizing that entities within these domains can all be represented as sequences, which together form the "language of nature", we introduce Nature Language Model (NatureLM), a sequence-based science foundation model designed for scientific discovery. Pre-trained with data from multiple scientific domains, NatureLM offers a unified, versatile model that enables various applications including: (i) generating and optimizing small molecules, proteins, RNA, and materials using text instructions; (ii) cross-domain generation/design, such as protein-to-molecule and protein-to-RNA generation; and (iii) top performance across different domains, matching or surpassing state-of-the-art specialist models. NatureLM offers a promising generalist approach for various scientific tasks, including drug discovery (hit generation/optimization, ADMET optimization, synthesis), novel material design, and the development of therapeutic proteins or nucleotides. We have developed NatureLM models in different sizes (1 billion, 8 billion, and 46.7 billion parameters) and observed a clear improvement in performance as the model size increases. |
| title | Nature Language Model: Deciphering the Language of Nature for Scientific Discovery |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.07527 |