Unbiased single-cell morphology with self-supervised vision transformers
Michael Doron, Théo Moutakanni, Zitong Chen, Nikita Moshkov, Mathilde Caron, Hugo Touvron, Piotr Bojanowski, Wolfgang M. Pernice, Juan C. Caicedo
Self-supervised DINO features, learned without labels, describe cell morphology from subcellular detail to experimental groups and expose a hierarchy of biological and technical variation in three public datasets.
bioRxiv · Jun 16, 2023 · PreprintBioinformatics