An operational perturbation proteomics-based virtual cell model.

R. Sun Liujia Qian Yong-Ge Li Tong Liu Hong-Han Cheng Xue-Dong Zhang Xue-Ya Zhou Yue-Cheng Zhan Guang-Mei Zhang Zheng-Chao Luo Kun-Peng Ma Chun-Long Wu Dong-Chen Ji Zhang-Zhi Xue Hong-Xue Meng Yu-Hang Xiang Ding-Wei Lei Qian-He Zhou Wen-Bin Hu Yu-Han Deng Ling-Ling Tan Qi Xiao Zhi-Wei Liu Lei Zeng Li-Qin Qian Xu-Dan Zheng Qiong Hu Nian-Zi Luo W. E Peijie Zhou Han Wen Y. Zhu Tian-Nan Guo

Sep 2026 · Nature · 1 citation · 46 references

Medicine

TL;DR

This work generated more than 38 million temporal protein-abundance measurements from systematically perturbed breast cancer cell lines, and developed ProteinTalks, a virtual cell model that achieves higher performance than the selected benchmark implementations under the evaluated protocols.

DOI PubMed Semantic Scholar

View source

Similar papers

Open access Aug 2026

A knowledge-driven framework for predicting single-cell responses for unprofiled drugs

An artificial intelligence framework that integrates biological mechanism knowledge to predict how cells respond to chemical perturbation, improving generalization to untested drugs and prioritizing cancer drug candidates in virtual screening is introduced.

Jinghao Feng, Zi-Heng Zhao, Xiaoman Zhang et al. · Nature Machine Intelligence · 2 citations

Open access Aug 2026

Single-cell foundation models benefit from cross-modal training: adding proteomics data beats parameter scaling

It is shown that with the right training recipe, heterogeneous proteomics data can improve the learned representations of single-cell RNAseq samples, demonstrating strong out-of-distribution generalization and suggesting that multimodal pretraining is a promising path toward more informative biological foundation model...

Maximilien Burq, Peter Cimermancic, Charlie Kim et al. · bioRxiv · 1 citation

Review Aug 2026

Artificial Intelligence in Druggable Protein Identification: Data-driven Multidimensional Representations and the Evolution of Predictive Models.

This review systematically summarizes the latest research progress in druggable protein prediction algorithms, providing a comprehensive analysis across three dimensions: data resources, feature engineering, and predictive models.

Hong-Qi Zhang, Hong-Ling Wang, Shang-Hua Liu et al. · Current Drug Targets · 0 citations

Open access Aug 2026

A pretrained unified model enables cellular functional profile prediction and multi-objective virtual drug screening

Cells are characterized by molecular states, coordinated molecular interactions, regulatory programs, and responses to perturbations. Systematic mapping of these cellular functional profiles across biological contexts remains experimentally costly and fragmented. Here we present InsilicoCell, a pretrained multi-modal,...

Ruoqiao Chen, Li Huang, Yu Qiao et al. · bioRxiv · 0 citations

Sep 2026

Integrated computational framework for drug repurposing in metastatic prostate cancer using transcriptomic meta-analysis, machine learning, and molecular modeling.

CDK1 was identified as a promising therapeutic target, and Tucatinib emerged as the most promising repurposing candidate, warranting further clinical validation.

J. Rafiee, Seyedeh Tahereh Arabi Baygi, S. H. Aghaee-Bakhtiari · Computational biology and ch... · 0 citations

Review Open access Sep 2026

Network biology to artificial intelligence: building the next generation of predictive drug discovery

Artificial intelligence-driven systems biology approaches could contribute to the development of dynamic, patient-specific computational representations of biological systems, potentially accelerating precision medicine and transforming drug discovery from empirical experimentation toward predictive, mechanism-guided t...

Kumar Selvarajoo · Frontiers in Immunology · 0 citations