AI Detects a New Class of Mutations Behind Autism

Princeton University researchers used AI in analyzing DNA mutations to decode their harmful impact in people with autism.

Researchers analyzed the genomes of 1,790 families and sorted 120,000 mutations to find those that affect gene behavior in people with autism. Many mutations in DNA that contribute to disease are not in actual genes but instead lie in the 99% of the genome once considered “junk.”

Olga Troyanskaya, the author of the study, says that this method uses deep learning to identify sections of DNA to predict protein interactions known to affect gene regulation.

With this new method, the team is analyzing the genetic causes of various forms of cancer, heart disease and other disorders.⠀