AI model decodes cell signaling fingerprints across diverse cell types
As an embryo develops from a small cluster of stem cells, those once "blank slate" cells begin to take on more specialized roles like brain, liver or muscle cells and organize themselves into three-dimensional structures such as tissues and organs.
Researchers have developed a machine learning model called IRIS that can decode the "fingerprints" left by cell signaling pathways across diverse cell types. These fingerprints represent unique patterns of gene activity that reveal the signaling history of a cell, even across different cell types. By using this model, scientists can now reconstruct the signaling processes that shape cell fate, which could accelerate stem cell engineering for regenerative medicine and improve the creation of 3D organoids for disease research.
IRIS, a neural network-based AI model, was trained on extensive experimental data measuring how human embryonic stem cells respond to major signaling pathways during development. The model accurately predicted signaling activation in mouse embryos, demonstrating its potential to guide stem cells into specific functional types and study diseases like asthma, lung cancer, and pulmonary fibrosis.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
