Nature Methods

Headlines · 1

1. Oct 15
   MIT's IRIS model decodes cell-signaling fingerprints across cell types

   Researchers led by MIT assistant professor Pulin Li and graduate student Nicholas Hutchins report that each cell-signaling pathway leaves a distinctive gene-activity fingerprint that is consistent across cell types. Their neural-network model, IRIS, uses those fingerprints to estimate which signaling pathways were active at specific times in a cell’s development; it was trained on data from thousands of human embryonic stem cells exposed to combinations of six major pathways. Tested on mouse embryo cells during gastrulation, IRIS predicted pathway activation in cells destined for heart, gut, muscle and spinal cord tissue, and a predicted lung-development signal was confirmed in mouse experiments, according to the open-access study published in Nature Methods on Sept. 8.

   MIT News · AI · 🔥 0

Experience and discussion from the community

Share my Nature Methods experienceAsk about Nature Methods