An MIT-led research team reported a machine learning model that estimates which signaling pathways a cell has encountered by reading its overall gene activity. In a study published in Nature Methods on Sept. 8, researchers led by MIT assistant professor of biology and Whitehead Institute member Pulin Li and graduate student Nicholas Hutchins said each signaling pathway leaves a distinctive gene-activity pattern, or fingerprint, that they found consistent across different cell types for the same pathway.

The model, IRIS, was trained on data measuring how thousands of human embryonic stem cells responded to dozens of combinations of six major signaling pathways at multiple developmental stages. The team then tested it on single cells from mouse embryos during gastrulation, reporting accurate predictions of when and where specific pathways would activate in cells destined for heart, gut, muscle and spinal cord tissue.

When IRIS predicted that activating a specific pathway would encourage lung-specific development, experiments in mouse embryos confirmed the prediction, the researchers reported. They suggested the approach could aid stem cell engineering and organoid creation, while noting it remains a research method.