{"slug":"ai","tag":"ai","variants":["ai"],"description":"People, companies, institutions and technologies working on artificial intelligence in cancer care.","count":30,"kinds":{"person":7,"institution":4,"company":18,"technology":1},"related":[{"slug":"protein-design","tag":"protein-design","shared":6},{"slug":"virtual-cell","tag":"virtual-cell","shared":4},{"slug":"pathology","tag":"pathology","shared":3},{"slug":"screening","tag":"screening","shared":3},{"slug":"breast","tag":"breast","shared":2},{"slug":"biomarkers","tag":"biomarkers","shared":1},{"slug":"chemistry","tag":"chemistry","shared":1},{"slug":"digital-pathology","tag":"digital-pathology","shared":1},{"slug":"foundation-models","tag":"foundation-models","shared":1},{"slug":"germany","tag":"germany","shared":1},{"slug":"infrastructure","tag":"infrastructure","shared":1},{"slug":"prostate","tag":"prostate","shared":1}],"records":[{"id":"daniel-spratt","kind":"person","name":"Daniel E. Spratt","route":"/people/daniel-spratt/","tldr":"Radiation oncologist who built AI models from trial slides to decide which prostate cancer patients need hormone therapy."},{"id":"kristina-lang","kind":"person","name":"Kristina Lång","route":"/people/kristina-lang/","tldr":"Led MASAI, the first randomised trial of AI-supported mammography screening, which found more cancers with half the radiologist workload."},{"id":"constance-lehman","kind":"person","name":"Constance D. Lehman","route":"/people/constance-lehman/","tldr":"Breast radiologist who co-developed the Mirai AI model that predicts breast cancer risk from a mammogram."},{"id":"faisal-mahmood","kind":"person","name":"Faisal Mahmood","route":"/people/faisal-mahmood/","tldr":"Built UNI and CONCH, the pathology foundation models that let AI read whole-slide images across cancer types."},{"id":"thomas-fuchs","kind":"person","name":"Thomas J. Fuchs","route":"/people/thomas-fuchs/","tldr":"Trained the first clinical-grade AI on tens of thousands of slides, leading to the first FDA-authorised AI pathology product."},{"id":"jakob-nikolas-kather","kind":"person","name":"Jakob Nikolas Kather","route":"/people/jakob-nikolas-kather/","tldr":"Showed that deep learning can read genetic features like microsatellite instability directly from routine pathology slides."},{"id":"regina-barzilay","kind":"person","name":"Regina Barzilay","route":"/people/regina-barzilay/","tldr":"Computer scientist who built Mirai and Sybil, AI models that predict breast and lung cancer risk years before diagnosis."},{"id":"arc-institute","kind":"institution","name":"Arc Institute","route":"/institutions/arc-institute/","tldr":"The Arc Institute is a well-funded nonprofit research institute building 'virtual cell' AI models and the datasets to train them."},{"id":"institute-for-protein-design","kind":"institution","name":"Institute for Protein Design (University of Washington)","route":"/institutions/institute-for-protein-design/","tldr":"David Baker's institute, where de novo protein design and the RFdiffusion models come from (Nobel Prize in Chemistry 2024)."},{"id":"providence-health","kind":"institution","name":"Providence Health & Services","route":"/institutions/providence-health/","tldr":"Providence is a 51-hospital US health system whose 1.3 billion pathology tiles trained Prov-GigaPath with Microsoft."},{"id":"yale-school-of-medicine","kind":"institution","name":"Yale School of Medicine / Yale Cancer Center","route":"/institutions/yale-school-of-medicine/","tldr":"Home of the Cell2Sentence single-cell language models built with Google, and an NCI-designated comprehensive cancer centre."},{"id":"google-deepmind","kind":"company","name":"Google DeepMind (and Google Research)","route":"/companies/google-deepmind/","tldr":"Google DeepMind built AlphaFold, AlphaMissense, AlphaGenome and Med-Gemini, the reference models for structure, variants, and medical multimodal reasoning."},{"id":"microsoft-research","kind":"company","name":"Microsoft (Research and Health AI)","route":"/companies/microsoft-research/","tldr":"Microsoft co-developed Prov-GigaPath and BiomedCLIP and is the compute partner for Paige's Virchow2."},{"id":"nvidia","kind":"company","name":"NVIDIA","route":"/companies/nvidia/","tldr":"Supplies the GPUs and the BioNeMo framework most biological foundation models are trained on, and co-developed Evo 2 with Arc."},{"id":"evolutionaryscale","kind":"company","name":"EvolutionaryScale","route":"/companies/evolutionaryscale/","tldr":"Spun out of Meta's protein team; makes the ESM3 protein language model that generated a new fluorescent protein."},{"id":"vevo-therapeutics","kind":"company","name":"Vevo Therapeutics","route":"/companies/vevo-therapeutics/","tldr":"Produced Tahoe-100M, the largest single-cell drug-perturbation atlas, and trains models on it."},{"id":"bioptimus","kind":"company","name":"Bioptimus","route":"/companies/bioptimus/","tldr":"French startup behind H-optimus-0, an open 1.1-billion-parameter pathology foundation model."},{"id":"aignostics","kind":"company","name":"Aignostics","route":"/companies/aignostics/","tldr":"Aignostics is the Berlin pathology AI company that built the Atlas foundation model with Mayo Clinic."},{"id":"kaiko-ai","kind":"company","name":"kaiko.ai","route":"/companies/kaiko-ai/","tldr":"Dutch-Swiss company releasing open pathology foundation models (Midnight) and evaluation tooling (eva)."},{"id":"histai","kind":"company","name":"HistAI","route":"/companies/histai/","tldr":"HistAI, of Miami, released Hibou-B and Hibou-L in 2024, open vision transformer models for pathology trained on more than a million slides and published under the Apache 2.0 licence, which allows commercial use. Whether permissively licensed open models reach regulated clinical products or stay research tools is the open question."},{"id":"chai-discovery","kind":"company","name":"Chai Discovery","route":"/companies/chai-discovery/","tldr":"Makes Chai-1 and Chai-2, open-weight structure models used for antibody and binder design."},{"id":"xaira-therapeutics","kind":"company","name":"Xaira Therapeutics","route":"/companies/xaira-therapeutics/","tldr":"Launched in 2024 with over $1 billion to build AI-native drug discovery from Baker-lab protein design."},{"id":"lila-sciences","kind":"company","name":"Lila Sciences","route":"/companies/lila-sciences/","tldr":"Lila Sciences is Flagship Pioneering's 'scientific superintelligence' company, combining AI with autonomous labs, with life science as a first domain."},{"id":"cradle-bio","kind":"company","name":"Cradle","route":"/companies/cradle-bio/","tldr":"Cradle is a protein-engineering AI platform used by pharma to optimise antibodies and enzymes."},{"id":"profluent-bio","kind":"company","name":"Profluent","route":"/companies/profluent-bio/","tldr":"Profluent uses protein language models to design new gene editors (OpenCRISPR-1) and antibodies."},{"id":"latent-labs","kind":"company","name":"Latent Labs","route":"/companies/latent-labs/","tldr":"Founded by an AlphaFold co-developer to make protein design programmable; released Latent-X in 2025."},{"id":"genesis-molecular-ai","kind":"company","name":"Genesis Molecular AI (formerly Genesis Therapeutics)","route":"/companies/genesis-molecular-ai/","tldr":"Genesis Molecular AI does small-molecule discovery on its GEMS platform, which combines physics and deep learning, with oncology programmes in the clinic pipeline."},{"id":"iambic-therapeutics","kind":"company","name":"Iambic Therapeutics","route":"/companies/iambic-therapeutics/","tldr":"AI-discovered oncology molecules in the clinic, including a HER2 inhibitor and a CDK2/4 inhibitor."},{"id":"chan-zuckerberg-initiative","kind":"company","name":"Chan Zuckerberg Initiative (Biohub)","route":"/companies/chan-zuckerberg-initiative/","tldr":"Funds and builds the Human Cell Atlas infrastructure and the CZI virtual cell models (TranscriptFormer), plus one of the largest nonprofit GPU clusters for biology."},{"id":"chemistry42","kind":"technology","name":"Chemistry42 and Pharma.AI (Insilico)","route":"/technologies/chemistry42/","status":"emerging","tldr":"Generative chemistry platform behind the first AI-discovered drug to reach phase 2, plus oncology candidates."}]}