insane This new paper is basically saying Cells can now be "prompted" like LLMs. STACK is a foundation model for biology trained on 149 million human single cells. Instead of treating each cell in isolation, it understands cells in context, like how tokens make sense inside a sentence. At inference time, cells teach the model how to think about new cells. Why this is a big deal Most single cell models = "Here’s one cell, guess what it is." STACK = "Here’s a whole neighborhood of cells, now predict what happens if I perturb them." It can: Learn new biological conditions on the fly Predict effects of chemical perturbations Generalize across donors, tissues, and diseases Work zero shot, straight out of the box This is in context learning, but for human biology.👀 The insane part - They used it to create Perturb Sapiens: First whole human atlas of perturbed cells 28 tissues 40 cell classes 201 perturbations That’s a simulation layer for the human body. This is how biological world models begin. This is huge bio/acc