New Computational Tool Reveals Genetic Driver of Idiopathic Neuropathy

S. and nearly 30% of adults over age 65. Because many cases remain unexplained and standard genetic testing often misses disease-causing repeat expansions in the RFC1 gene, researchers have developed a machine learning–enabled computational approach to identify these expansions and clarify their role in idiopathic neuropathy.

Researchers at Washington University (St. Louis, MO, USA) and collaborating institutions developed a novel computational tool that couples a genome-sequencing pipeline with machine learning to reliably identify and classify RFC1 repeat expansions. The method focuses on expansions of the DNA motif AAGGG that extend far beyond normal length and are difficult to detect with standard genetic testing methods. By analyzing genome sequencing data, the approach distinguishes pathogenic repeat expansions with improved reliability for use across clinical and research workflows.

Using this approach, the investigators found that RFC1 repeat expansions may account for more than 2% of idiopathic peripheral neuropathy. The finding addresses a persistent diagnostic gap in unexplained neuropathy, where repeat expansions can be missed by conventional assays. The study further indicates that broader genetic testing is warranted for people with unexplained peripheral neuropathy, including those presenting with muscle weakness as well as sensory symptoms.

The work is published in Annals of Neurology. According to the researchers, the tool offers a more affordable and reliable way to interrogate this complex genetic variation in both clinical and research settings. The team has released the tool publicly on GitHub, which could expand access to testing, support more accurate diagnoses, and provide families with clearer information on the genetic causes of their condition.

Related Links
WashU Medicine