AI-powered virtual tissues from spatial proteomics for clinical diagnostics and biomedical discovery

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wenckstern, Johann, Jain, Eeshaan, Cheng, Yexiang, von Querfurth, Benedikt, Vasilev, Kiril, Pariset, Matteo, Cheng, Phil F., Liakopoulos, Petros, Michielin, Olivier, Wicki, Andreas, Gut, Gabriele, Bunne, Charlotte
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911309892681728
author Wenckstern, Johann
Jain, Eeshaan
Cheng, Yexiang
von Querfurth, Benedikt
Vasilev, Kiril
Pariset, Matteo
Cheng, Phil F.
Liakopoulos, Petros
Michielin, Olivier
Wicki, Andreas
Gut, Gabriele
Bunne, Charlotte
author_facet Wenckstern, Johann
Jain, Eeshaan
Cheng, Yexiang
von Querfurth, Benedikt
Vasilev, Kiril
Pariset, Matteo
Cheng, Phil F.
Liakopoulos, Petros
Michielin, Olivier
Wicki, Andreas
Gut, Gabriele
Bunne, Charlotte
contents Spatial proteomics technologies have transformed our understanding of complex tissue architecture in cancer but present unique challenges for computational analysis. Each study uses a different marker panel and protocol, and most methods are tailored to single cohorts, which limits knowledge transfer and robust biomarker discovery. Here we present Virtual Tissues (VirTues), a general-purpose foundation model for spatial proteomics that learns marker-aware, multi-scale representations of proteins, cells, niches and tissues directly from multiplex imaging data. From a single pretrained backbone, VirTues supports marker reconstruction, cell typing and niche annotation, spatial biomarker discovery, and patient stratification, including zero-shot annotation across heterogeneous panels and datasets. In triple-negative breast cancer, VirTues-derived biomarkers predict anti-PD-L1 chemo-immunotherapy response and stratify disease-free survival in an independent cohort, outperforming state-of-the-art biomarkers derived from the same datasets and current clinical stratification schemes.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06039
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI-powered virtual tissues from spatial proteomics for clinical diagnostics and biomedical discovery
Wenckstern, Johann
Jain, Eeshaan
Cheng, Yexiang
von Querfurth, Benedikt
Vasilev, Kiril
Pariset, Matteo
Cheng, Phil F.
Liakopoulos, Petros
Michielin, Olivier
Wicki, Andreas
Gut, Gabriele
Bunne, Charlotte
Quantitative Methods
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Spatial proteomics technologies have transformed our understanding of complex tissue architecture in cancer but present unique challenges for computational analysis. Each study uses a different marker panel and protocol, and most methods are tailored to single cohorts, which limits knowledge transfer and robust biomarker discovery. Here we present Virtual Tissues (VirTues), a general-purpose foundation model for spatial proteomics that learns marker-aware, multi-scale representations of proteins, cells, niches and tissues directly from multiplex imaging data. From a single pretrained backbone, VirTues supports marker reconstruction, cell typing and niche annotation, spatial biomarker discovery, and patient stratification, including zero-shot annotation across heterogeneous panels and datasets. In triple-negative breast cancer, VirTues-derived biomarkers predict anti-PD-L1 chemo-immunotherapy response and stratify disease-free survival in an independent cohort, outperforming state-of-the-art biomarkers derived from the same datasets and current clinical stratification schemes.
title AI-powered virtual tissues from spatial proteomics for clinical diagnostics and biomedical discovery
topic Quantitative Methods
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2501.06039