Machine learning approach could bring greater certainty to prenatal genetic testing
Advances in genome sequencing are giving more families access to prenatal genetic testing and new information about an unborn baby's health, including whether genetic changes may be linked to a neurodevelopmental condition.
Prenatal genetic testing is becoming more accessible, offering families detailed information about an unborn baby's health. However, this testing can sometimes reveal "variants of uncertain significance," or VUS, which are genetic changes that cannot be easily classified as harmful or harmless. This uncertainty can lead to anxiety for expecting parents.
Dr. Rosanna Weksberg, a clinical geneticist at The Hospital for Sick Children, explains that while doctors may detect new genetic changes, they often cannot determine if these variants are truly abnormal or simply part of normal development. To address this issue, Weksberg and her team have developed a machine learning model that can transform blood-derived DNA methylation episignatures into tissue-agnostic patterns.
This innovation could bring greater certainty to prenatal testing by enabling the identification of disease-specific episignatures across different tissue types, including amniotic fluid and placental samples. In a study published in The American Journal of Human Genetics, the researchers demonstrated that their model accurately recognized the Down syndrome pattern in various tissue types, using blood-derived episignatures from 266 individuals with Down syndrome and DNA methylation data from 850 individuals with and without the condition.
This breakthrough could ultimately support more accurate and earlier diagnoses, offering families clearer information to make informed decisions about their child's health.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
