Using artificial intelligence techniques, researchers have revealed that mutations in so-called ‘junk’ DNA may cause autism. The study is the first to functionally link such mutations to the neurodevelopmental condition.
The research, which has been published in Nature Genetics, utilized machine learning to analyze the whole genomes of 1790 individuals with autism and their unaffected parents and siblings. These individuals had no family history of autism, which indicates that the cause of their conditions was most likely spontaneous rather than inherited mutations.
The analysis predicted the ramifications of genetic mutations in parts of the genome that do not encode proteins, regions often mischaracterized as ‘junk’ DNA. The number of autism cases linked to the noncoding mutations was comparable to the number of cases linked to protein-coding mutations that disable gene function.
According to Olga Troyanskaya (Princeton University, NJ, USA), who led the study, the implications of the work extend beyond autism. “This is the first clear demonstration of non-inherited, noncoding mutations causing any complex human disease or disorder.”
At most, approximately 30% of autism cases can be accounted for by mutations in protein-coding regions in individuals without a family history of autism. Evidence has suggested that autism-causing mutations must happen elsewhere in the genome as well.
However, identifying which noncoding mutations may cause autism is challenging. A single individual might have dozens of noncoding mutations, most of which will be unique to that individual. Thus, the traditional approach of identifying common mutations among affected populations is nonviable.
You might also like:
Troyanskaya and colleagues consequently took a new approach, where they trained a machine-learning model to predict how a given sequence would affect gene expression.
The researchers studied the genetic basis of autism by applying the machine-learning model to a treasure trove of genetic data called the Simons Simplex Collection. The Collection contains the whole genomes of nearly 2000 ‘quartets’ made up of a child with autism, an unaffected sibling and their unaffected parents.
The researchers used their model to predict the impact of non-inherited, noncoding mutations in each child with autism. They then compared those predictions with the effects of the same, unmutated strand in the child’s unaffected sibling.
Noncoding mutations in many of the children with autism altered gene regulation, the analysis suggested. Moreover, the results suggested that the mutations affected gene expression in the brain and genes already linked to autism, such as those responsible for neuron migration and development.
“This is consistent with how autism most likely manifests in the brain. It’s not just the number of mutations occurring, but what kind of mutations are occurring,” explained study co-author Christopher Park (Princeton University).
The researchers then tested the effects of some of the noncoding mutations in laboratory experiments. They inserted predicted high-impact mutations found in children with autism into cells and observed the resulting changes in gene expression. These changes affirmed the model’s predictions.
Troyanskaya stated that she and her colleagues will continue improving and expanding their method. Ultimately, they hope that their work will improve how genetic data are used for diagnosing and treating diseases and disorders. “Right now, 98% of the genome is usually being thrown away. Our work allows you to think about what we can do with the 98%.”
Sources: Zhou J, Park CY, Theesfeld CL et al. Whole-genome deep-learning analysis identifies contribution of noncoding mutations to autism risk. Nat. Gen. doi:10.1038/s41588-019-0420-0 (2019) (Epub ahead of print); www.simonsfoundation.org/2019/05/27/autism-noncoding-mutations/