Nature Cancer Cancer Research

The deep learning framework Hist2Prot infers single-cell spatial proteomics from histology to predict biomarkers and clinical outcomes

Jiansong Fan, Sen Yang, Erqiang Hu, Jianhong An, Qiang Liu, Naijia Liu, Mingwei Ma, Michael Prystowsky, Tianxu Lv, Si Yong Yeo, Yuting Ren, Yuan Liu, Lihua Li, Yuan Li, Qi Sun, Pengjiang Qian, Le Lu, Wenjun Deng, Xiang Pan, Shanye Yin
Springer Nature · 2026-11-13 · DOI 10.1038/s43018-026-01270-8
⬢ Cited by: 0 Crossref

Abstract

Nature Cancer, Published online: 13 November 2026; doi:10.1038/s43018-026-01270-8 Fan et al. propose an artificial intelligence model to infer spatial proteomic patterns at the single-cell level from routine hematoxylin and eosin slides to predict molecular biomarkers, prognosis and immunotherapy response in multiple cohorts.

Read at publisher →