Virtual Cells and Digital Twins: Multi-Scale and Multi-Modal AI for Biomedicine

Abstract The complexity of cancer demands understanding biological processes across scales, from molecular interactions to tissue architecture. This talk explores how artificial intelligence enables the creation of digital twins at both cellular and tissue levels, with the aim to predict cellular phenotypes, function and their responses to perturbations such as cancer therapies. Concretely, I will introduce the Virtual Tissues (VirTues) platform, a foundation model framework that transforms how we analyze multiplexed tissue data and seamlessly integrates molecular, cellular, and tissue-scale information to increase diagnostic precision and biological understanding in personalized oncology. VirTues employs a multi-modal vision transformer architecture designed to learn from heterogeneous, high-dimensional datasets spanning different biological markers, measurement characteristics, and variable clinical annotations. While existing approaches often focus on H&E–stained slides, our framework incorporates highly multiplexed imaging techniques that capture hundreds of proteins within single tissue sections. Through unsupervised learning and a multi-scale neural network architecture, VirTues unifies these diverse data sources into a coherent virtual tissue space. As a result, new patient biopsy samples can be automatically mapped into this common representation. This enables integrative analyses of morphological, molecular and spatial complexity while facilitating clinically relevant predictions. To bridge insights from the analysis of patient samples with personalized treatment, we employ generative models trained on large biomedical datasets. These models predict treatment responses of biopsied cells from metastatic melanoma patients by revealing patterns of signaling pathway modulation associated with driver mutations and metastasis sites. Together, these approaches enable a multi-scale understanding of cancer biology and treatment response, advancing the development of personalized therapies guided by comprehensive digital twins of patients.

Biography Assistant professor at EPFL in the School of Computer and Communication Sciences (IC) and School of Life Sciences (SV) and a member of the Swiss Institute for Experimental Cancer Research (ISREC). Before, she was a PostDoc at Genentech and Stanford with Aviv Regev and Jure Leskovec and in 2023 completed a PhD in Computer Science at ETH Zurich working with Andreas Krause and Marco Cuturi. During her graduate studies, she was a visiting researcher at the Broad Institute of MIT and Harvard hosted by Anne Carpenter and Shantanu Singh and worked with Stefanie Jegelka at MIT. Her research aims to advance personalized medicine by utilizing machine learning and large-scale biomedical data. Charlotte Bunne’s interdisciplinary research has won several (best paper) awards. Charlotte has been a Fellow of the German National Academic Foundation and is a recipient of the ETH Medal.