American researchers succeed in “breaking the autism code”

The team says the new AI analysis can identify genetic markers of autism from biological activity in the brain, with an accuracy of 89 to 95 percent.

The developed method involves mapping the brain using standard magnetic resonance imaging (MRI), before reanalyzing those scans with artificial intelligence to detect movements of proteins, nutrients and other brain processes that may indicate autism.

Dr. Shinji Kondo, assistant professor of radiology at Washington University in St. Louis, developed the new mathematical modeling technique for the brain while she was a graduate student and researcher.

The method, called “transport-based morphometry” after the transport of biological material in the brain, focuses on identifying patterns associated with key parts of the genetic code.

Genetic code sequences, called copy number variations (CNVs), reveal sections of DNA that have been deleted or duplicated, changes that have been linked to autism in previous studies.

“Some copy number variations are known to be associated with autism, but their association with brain morphology, or in other words, how different types of brain tissue such as gray or white matter are arranged in our brain, is not well known,” said biomedical engineering professor Gustavo Rode, who taught Kondo during her doctoral studies.

“Discovering how CNVs are associated with brain tissue morphology is an important first step in understanding the biological basis of autism,” he added.

The new method could help distinguish between more meaningful biological differences within brain structures, beyond deletions or duplications associated with copy number variations and autism.

Participants in the nonprofit Simons Variation in Individuals Project — a group of people with known genetic variations linked to autism — contributed key data used in the new study.

The researchers also recruited patients from other medical or clinical settings, based on their similarities to the Simons group (such as age, gender, and nonverbal IQ), to reduce variables that could influence their results.

The study was published in the journal Science Advances.

Source: Daily Mail