Summary A deep learning framework called STARS recovers single-cell-level gene expression from spatial transcriptomics data across multiple platforms, revealing immune cell subpopulations and tissue architecture invisible at conventional spot-level resolution. Transcript INTRO Imagine you're looking at a piece of tissue under a microscope—say, from a tumor or a lung with disease. You want to know exactly which genes are being expressed in each individual cell, right? The problem is, most spatial transcriptomics technologies can't give you that level of detail. They measure gene expression at the spot or bin level, which means you're essentially looking at neighborhoods of cells rather than individual cells themselves. It's like trying to understand what […]