MIT's IRIS predicts cell fate signals, verified in mouse embryo experiments
alex_verem · x · 2026-10-17
MIT and the Whitehead Institute built an AI model called IRIS that decodes how cells communicate. Every organ starts as blank stem cells that decide to become heart, lung, or brain via chemical signals — signals that were hard to read because they seemed to work differently in every cell type.
IRIS reads the fingerprint each signal leaves in a cell's genes. Trained on thousands of human stem cells, it generalized to cell types it had never seen. In mouse embryos, it correctly predicted when signals would switch on in cells fated to become heart, gut, muscle, and spinal cord. It also predicted that turning on one specific signal would push cells toward lung tissue — and the team's follow-up experiment in mouse embryos confirmed it.
Implications include better lab-grown mini-organs, improved ways to study asthma, lung cancer, and pulmonary fibrosis, and eventually repairing damaged tissue.
Related event: MIT's IRIS Model Decodes the Chemical Language of Cell Communication(3 posts)→
More from Research
- Paper argues mechanistic interpretability needs a rigorous "logic of inference" — burny_tech · 2026-10-18
- NeurIPS 2026 Journal Track accepts 88 papers from TMLR, JMLR, AoS — NeurIPSConf · 2026-10-18
- RCT: AI-generated layperson summaries of medical findings improve visit quality and shorten consultations — EricTopol · 2026-10-18
- Progress on mapping jev's j-space — sloppenheimer · 2026-10-18
- Hand-probing tiny model neurons: gate is swappable, down steers it into an owl — maxsloef · 2026-10-18
- MIT paper builds attention-based foundation model for quantum states, 18 training points suffice — jwt0625 · 2026-10-18