•  
  •  
 

Bulletin of Chinese Academy of Sciences (Chinese Version)

Keywords

protein design; new R&D institutions; life sciences; scientific and technical innovation

Document Type

Policy & Management Research

Abstract

The Institute for Protein Design (IPD) at the University of Washington is a pioneering local and state-supported non-profit scientific research institution. Since its establishment in 2012, IPD has seized the opportunity of AI for Science and open science, and continuously enhanced its capabilities of fundamental innovations, breakthrough technologies, and industrial impact. We summarized five factors contributing to IPD’s development, including focusing on the cutting-edge issues of basic scientific research to gain a first-mover advantage and then further expand, integrating AI-enhanced digital tools and solid experimental validations, facilitating the integrated development of innovation and industrial chains, giving full play to the role of strategic scientists, and creating an open and sharing atmosphere for talents. While drawing on its experience, we suggest that China can make use of the new national system to enhance the development of new life sciences R&D institutions in four aspects: strengthening top-level design and institutional frameworks, seizing the opportunities of technological transformation, highlighting market-oriented convergence of innovation elements, and adhering to a people-oriented and lenient environment, in order to support life sciences self-reliance and self-strengthening at higher levels.

First page

1235

Last Page

1244

Language

Chinese

Publisher

Bulletin of Chinese Academy of Sciences

References

1 科技部火炬中心. 2022年新型研发机构发展报告. 北京: 科学技术文献出版社, 2023.Torch Center of the Ministry of Science and Technology of the People’s Republic of China. New R&D Institution Development Report 2022. Beijing: Scientific and Technical Documentation Press, 2023. (in Chinese)

2 胡志民, 贾晓峰, 杨俊涛, 等. 我国生命科学及医学新型研发机构优化建设策略研究. 中国工程科学, 2023, 25(5): 64-71.Hu Z M, Jia X F, Yang J T, et al. Optimal constructing measures of novel research and development institutions in life sciences and medicine in China. Strategic Study of CAE, 2023, 25(5): 64-71. (in Chinese)

3 Institute for Protein Design. Institute for Protein Design Annual Report FY 2022–2023. Seattle: Institute for Protein Design, 2023.

4 Service R F. Proteins by design. Science, 2016, 354: 1520-1521.

5 Service R F. Protein structures for all. Science, 2021, 374: 1426-1427.

6 Marx V. Method of the Year: Protein structure prediction. Nature Methods, 2022, 19: 5-10.

7 Watson J L, Juergens D, Bennett N R, et al. De novo design of protein structure and function with RFdiffusion. Nature, 2023, 620: 1089-1100.

8 Lutz I D, Wang S Z, Norn C, et al. Top-down design of protein architectures with reinforcement learning. Science, 2023, 380: 266-273.

9 Torres S V, Leung P J Y, Venkatesh P, et al. De novo design of high-affinity binders of bioactive helical peptides. Nature, 2024, 626: 435-442.

10 Kuhlman B, Dantas G, Ireton G C, et al. Design of a novel globular protein fold with atomic-level accuracy. Science, 2003, 302: 1364-1368.

11 Gordon S R, Stanley E J, Wolf S, et al. Computational design of an α-gliadin peptidase. Journal of the American Chemical Society, 2012, 134(50): 20513-20520.

12 李国杰. 智能化科研（AI4R）：第五科研范式. 中国科学院院刊, 2024, 39(1): 1-9.Li G J. AI4R: The fifth scientific research paradigm. Bulletin of Chinese Academy of Sciences, 2024, 39(1): 1-9. (in Chinese)

13 Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need// NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: Curran Associates Inc., 2017: 6000-6010.

14 Du Z Y, Su H, Wang W K, et al. The trRosetta server for fast and accurate protein structure prediction. Nature Protocols, 2021, 16(12): 5634-5651.

15 Jumper J, Evans R, Pritzel A, et al. Highly accurate protein structure prediction with AlphaFold. Nature, 2021, 596: 583-589.

16 Baek M, DiMaio F, Anishchenko I, et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science, 2021, 373: 871-876.

17 Dauparas J, Anishchenko I, Bennett N, et al. Robust deep learning-based protein sequence design using ProteinMPNN. Science, 2022, 378: 49-56.

18 Ingraham J, Garg V K, Barzilay R, et al. Generative models for graph-based protein design// NIPS’19: Proceedings of the 33rd International Conference on Neural Information Processing Systems. New York: Curran Associates Inc., 2019: 15820-15831.

19 Eisenstein M. Seven technologies to watch in 2024. Nature, 2024, 625: 844-848.

20 Zhao W J, Wang C. Protein designer David Baker: I like doing things that seem like magic. National Science Review, 2020, 7(8): 1410-1412.

21 Seydel C. The hothouse for protein design. Nature Biotechnology, 2020, 38(7): 779-784.

22 李鑫, 于汉超. 人工智能驱动的生命科学研究新范式. 中国科学院院刊, 2024, 39(1): 50-58. Li X, Yu H C. A new paradigm of life science research driven by artificial intelligence. Bulletin of Chinese Academy of Sciences, 2024, 39(1): 50-58. (in Chinese)

Download
Request a Copy

Share

COinS