What does AI actually change for cancer research? 🤔 My personal answer in the opening keynote of the Nature Conference "Cancer Immunology in the AI Era" in Chongqing: science is a search. We search through an enormous space of possible interventions, mostly by hand and one experiment at a time. AI lets us search that space far more systematically. Immunotherapy shows why this matters. It can cure cancer, yet only about 1 in 8 patients responds to checkpoint inhibitors. Finding the right intervention for each patient is exactly such a search problem. In my talk, "From cell atlases to AI-designed interventions," I showed how we approach it: map cell states eg the tumor immune ecosystem, predict how cells respond to perturbations, and steer cells toward the states we want. I presented recent work from our lab and collaborators, from tumor atlases and a human cytokine dictionary to open benchmarks for perturbation models. Many thanks to Zemin Zhang and the organizing team for a great program, and to Rong Li of Nature Biotechnology for chairing the session. And Chongqing at night, with its skyline above two rivers, is quite a sight. 🌃 #SingleCell #CancerImmunology #AI

🧪🧭 What if we could ask a model which experiment gives us the cells we want? Our new preprint, LabCompass, takes a step in this direction through generative inverse design. For me, this is one of the most exciting directions for the field. Together with many others, we have been working on predicting how cells respond to perturbations. How can we use these models to design experiments that achieve a desired biological outcome? 🎛️ This inverse problem is difficult. Combinations and doses create spaces that cannot be exhaustively screened, and each experiment produces a distribution of cell states. Predictive models are also imperfect, particularly in unexplored regions where we want to discover something new. LabCompass couples a generative model of experimental designs with a forward model of cellular responses. The desired phenotype guides generation in continuous design space, while a learned prior favors plausible designs. Selected candidates are tested experimentally, and the measurements inform the next round. 💡 The method is not tied to a particular virtual cell model. It can work with different differentiable forward models and cellular readouts, and the same trained models can address different phenotypic objectives. 🩸 We demonstrated this in primary human blood stem and progenitor cells. Across the study, we profiled 78 million cells and experimentally validated conditions enriching megakaryocytic, erythroid, monocytic and early lymphoid populations. One result I particularly like: distinct culture recipes produced similar target enrichments. Several solutions to the same biological objective give us alternatives to investigate and develop further. 🔬 The opportunity extends beyond blood and cell culture. We also applied LabCompass to single-cell transcriptomic data from viral infection. I’m excited to explore its potential for other perturbation systems, drug combinations, differentiation and organoids. This raises a question for virtual cell models: alongside prediction accuracy, how effectively can they guide experiments toward desired biological outcomes? If this connects to a problem you are working on, I’d love to hear from you. We’re keen to see how LabCompass transfers to new systems and happy to explore ideas together. A wonderful collaboration with Bertie Göttgens and Nicola Wilson at the Cambridge Stem Cell Institute. Huge credit to joint first authors Licyel Paulas-Condori, Alessandro Palma, Lorenzo Consoli and Juan Antonio Rubio-Lara, and the whole team across both labs! 📄 Preprint: biorxiv.org/content/10.64898… 💻 Code: github.com/theislab/LabCompa… #InverseDesign #VirtualCell #SingleCell