Researchers have developed a new artificial intelligence (AI) approach that is accelerating the identification of genes connected to neurodevelopmental disorders (NDDs) such as autism spectrum disorder, epilepsy, and developmental delay. This breakthrough could lead to improved diagnosis and the development of targeted therapies.
Credit: Dr_Microbe / iStock / Getty Images Plus
Published in the American Journal of Human Genetics, the study details how these AI models can help fully characterize the genetic landscape of NDDs. “Although researchers have made major strides identifying different genes associated with neurodevelopmental disorders, many patients with these conditions still do not receive a genetic diagnosis, indicating that there are many more genes waiting to be discovered,” said Dr. Ryan S. Dhindsa, the study’s first author and an assistant professor at Baylor College of Medicine.
Despite extensive research, thousands of NDD-associated genes remain undiscovered. Instead of sequencing the genomes of large patient populations, the researchers developed a machine-learning (ML) approach, training their model on single-cell RNA sequencing data. “We demonstrate that models trained solely on single-cell RNA sequencing data can robustly predict genes implicated in autism spectrum disorder (ASD), developmental and epileptic encephalopathy (DEE), and developmental delay (DD),” the researchers wrote.
Building on early findings, the team enhanced their ML-based models further by integrating over 300 additional biological features. These included gene intolerance to mutations, interactions with other disease-associated genes, and functional roles in biological pathways. “These models have exceptionally high predictive value,” Dhindsa said. “Top-ranked genes were up to two-fold or six-fold, depending on the mode of inheritance, more enriched for high-confidence neurodevelopmental disorder risk genes compared to genic intolerance metrics alone.”
The study also revealed significant differences in gene expression patterns between genes with monoallelic (one copy) and bi-allelic (both copies) inheritance patterns in the developing human cortex. Refining these models improved the prediction of genes associated with NDDs based on inheritance type.
The research has significant implications for diagnosing and treating NDDs. “We see these models as analytical tools that can validate genes that are beginning to emerge from sequencing studies but don’t yet have enough statistical proof of being involved in neurodevelopmental conditions,” Dhindsa said. This could speed up the discovery process and increase diagnostic accuracy, especially for those currently undiagnosed despite extensive genetic testing. The models predict high-confidence NDD risk genes, complementing large-scale gene discovery efforts.
Dhindsa added, “We hope that our models will accelerate gene discovery and patient diagnoses, and future studies will assess this possibility.”
