Dyno Therapeutics, whose co-founders include George Church, PhD, designs diverse AAV capsid variants using deep learning
Investigators from Dyno Therapeutics, Google Research, and partners have reported successfully using artificial intelligence to generate an unprecedented diversity of adeno-associated virus (AAV) capsids, in order to identify functional variants capable of evading the immune system, a key hurdle to wider use of gene therapy. [Rost-9D/Getty Images]
Focusing on a 28-amino-acid segment, investigators generated more than 200,000 variants of the AAV2 wildtype sequence, which yielded some 110,000 viable engineered capsids, half of which surpassed the average diversity of natural AAV serotype sequences with 12-29 mutations across the region . . .
