Scientists have created an algorithm to find the cause of neuropathy

One of the reasons for the diagnostic difficulties is the so-called repeat expansions, which are abnormal increases in the number of repetitions of a specific DNA sequence (in this case, “AAGGG”). Standard genome sequencing protocols often miss these variations due to their complexity.

A team of scientists led by Associate Professor of Genetics Shen Zhi Jin has developed a specialized computational pipeline that analyzes sequencing data and classifies these expansions with high accuracy. The application of this method to a sample of patients with “idiopathic” peripheral neuropathy showed that mutations in the RFC1 gene are the cause of the disease in more than 2% of cases.

This development offers a more accessible and reliable way to search for complex genetic variations for both clinical and research purposes. The tool is available for open use on the GitHub platform, which will improve the accuracy of diagnosis for patients with unknown etiology of neuropathy and justify the need for extended genetic testing for individuals with a combination of sensory impairments and muscle weakness. It will also provide patients’ families with complete information about the hereditary nature of their condition.

The researchers emphasize that the use of machine learning algorithms for interpreting genomic data is becoming a key tool in modern medicine, allowing patients to be transferred from the group of “unexplained” diagnoses to the group of individuals with established etiology, which is a prerequisite for the development of personalized treatment strategies.