An operational perturbation proteomics-based virtual cell model

  • Nature. 2026 Oct;658(8137):1066-1076. doi: 10.1038/s41586-026-11001-9.
Rui Sun  #  1  2  3 ,  Liujia Qian  #  1  2  3 ,  Yongge Li  #  4 ,  Tong Liu  #  5  6 ,  Honghan Cheng  1  2  3 ,  Xuedong Zhang  1  2  3 ,  Xueya Zhou  4  7 ,  Yuecheng Zhan  8 ,  Guangmei Zhang  1  2  3 ,  Zhengchao Luo  4  9 ,  Kunpeng Ma  1  2  3 ,  Chunlong Wu  1  2  3 ,  Dongchen Ji  10 ,  Zhangzhi Xue  1  2  3 ,  Hongxue Meng  11 ,  Yuhang Xiang  12 ,  Dingwei Lei  4  13 ,  Qianhe Zhou  10 ,  Wenbin Hu  8 ,  Yuhan Deng  10 ,  Lingling Tan  8 ,  Qi Xiao  1  2  3 ,  Zhiwei Liu  1  2  3 ,  Lei Zeng  1  2  3 ,  Liqin Qian  1  2  3 ,  Xuan Zheng  1  2  3 ,  Qiong Hu  1  2  3 ,  Nianzi Luo  1  2  3 ,  Weinan E  7  14 ,  Peijie Zhou  15  16  17  18 ,  Han Wen  19  20  21  22 ,  Yi Zhu  23  24  25 ,  Tiannan Guo  26  27  28
Affiliations
  • 1. Affiliated Hangzhou First People's Hospital, State Key Laboratory of Medical Proteomics, School of Medicine, School of Future Biomedicine, Westlake University, Hangzhou, China.
  • 2. Westlake Center for Intelligent Proteomics, Westlake Laboratory of Life Sciences and Biomedicine, Hangzhou, China.
  • 3. Research Center for Industries of the Future, School of Life Sciences, Westlake University, Hangzhou, China.
  • 4. DP Technology Co., Ltd, Beijing, China.
  • 5. Department of Surgical Oncology, Harbin Medical University Cancer Hospital, Harbin, China.
  • 6. NHC Key Laboratory of Cell Transplantation, The First Affiliated Hospital of Harbin Medical University, Harbin, China.
  • 7. Center for Machine Learning Research, Peking University, Beijing, China.
  • 8. Westlake Omics Co., Ltd, Hangzhou, China.
  • 9. Department of Big Data and Biomedical AI, College of Future Technology, Peking University, Beijing, China.
  • 10. Department of Breast Surgery, Harbin Medical University Cancer Hospital, Harbin, China.
  • 11. Department of Pathology, Harbin Medical University Cancer Hospital, Harbin, China.
  • 12. Department of Pathology, School of Basic Medical Sciences, Harbin Medical University, Harbin, China.
  • 13. Department of Biomedical Engineering, College of Future Technology, Peking University, Beijing, China.
  • 14. School of Mathematical Sciences, Peking University, Beijing, China.
  • 15. Center for Machine Learning Research, Peking University, Beijing, China. [email protected].
  • 16. AI for Science Institute, Beijing, China. [email protected].
  • 17. Center for Quantitative Biology, Peking University, Beijing, China. [email protected].
  • 18. National Engineering Laboratory for Big Data Analysis and Applications, Beijing, China. [email protected].
  • 19. DP Technology Co., Ltd, Beijing, China. [email protected].
  • 20. AI for Science Institute, Beijing, China. [email protected].
  • 21. Beijing Advanced Center of RNA Biology (BEACON), Peking University, Beijing, China. [email protected].
  • 22. State Key Laboratory of Medical Proteomics, Beijing, China. [email protected].
  • 23. Affiliated Hangzhou First People's Hospital, State Key Laboratory of Medical Proteomics, School of Medicine, School of Future Biomedicine, Westlake University, Hangzhou, China. [email protected].
  • 24. Westlake Center for Intelligent Proteomics, Westlake Laboratory of Life Sciences and Biomedicine, Hangzhou, China. [email protected].
  • 25. Research Center for Industries of the Future, School of Life Sciences, Westlake University, Hangzhou, China. [email protected].
  • 26. Affiliated Hangzhou First People's Hospital, State Key Laboratory of Medical Proteomics, School of Medicine, School of Future Biomedicine, Westlake University, Hangzhou, China. [email protected].
  • 27. Westlake Center for Intelligent Proteomics, Westlake Laboratory of Life Sciences and Biomedicine, Hangzhou, China. [email protected].
  • 28. Research Center for Industries of the Future, School of Life Sciences, Westlake University, Hangzhou, China. [email protected].
  • # Contributed equally.
Abstract

Artificial intelligence-empowered virtual cell models represent an emerging approach for in silico drug discovery1-3, yet most existing approaches lack large-scale, time-resolved perturbation proteomics data and interpretable frameworks for predicting therapeutic responses. Here we generated more than 38 million temporal protein-abundance measurements from systematically perturbed Breast Cancer cell lines, and developed ProteinTalks, a virtual cell model. Central to ProteinTalks is the synergy of this large-scale dynamic proteomic resource and the model architecture, enabling a new pretraining framework that learns transferable dynamical latent representations from temporal proteome trajectories. By modelling how proteins respond conditionally to different perturbations, this approach enables the model to function as an operational tool for diverse drug discovery tasks: predicting drug efficacy and synergy, discovering new drug combinations, probing proteins associated with drug resistance, stratifying patient responses and prioritizing drug candidates for patient organoids. It also shows robust transferability, extending beyond cell lines to patient-derived organoids and clinical biopsies, generally achieving higher performance than the selected benchmark implementations under the evaluated protocols. Together, ProteinTalks shows how scalable pretraining of transferable dynamic representations enables operational, dynamics-aware, proteomics-based virtual cell models to advance in silico drug discovery.

Products