Researchers have made a groundbreaking breakthrough by combining the power of artificial intelligence with the connectome, a map of neurons and their connections, to predict brain cell activity without making a single measurement in a living brain. This achievement has the potential to transform how neuroscientists generate and test hypotheses about how the brain works. A team of researchers from HHMI's Janelia Research Campus and the University of Tübingen used the fruit fly optic lobe connectome to build a detailed deep mechanistic network simulation of the fly visual system. Led by Srini Turaga, Janne Lappalainen, and Jakob Macke, the team created an AI simulation that can predict the activity of every neuron in the circuit, accurately reproducing more than two dozen experimental studies performed over the past two decades. This new method has the potential to accelerate scientific discovery, and HHMI's $500 million investment in AI@HHMI will support similar projects in the life sciences.
↧