Researchers diagnose cerebral palsy using AI and next-generation sequencing

Download PDF Copy

June 22, 2018

Researchers from the University of Delaware have shown that patients with spastic cerebral palsy (CP) can be identified using DNA methylation patterns in circulating blood cells.

Image Credit: Tobias Arhelger / Shutterstock

The study, which was recently published in BMC Bioinformatics, was conducted by researchers at Nemours/Alfred I. duPont Hospital for Children and Genome Profiling LLC (GenPro), a biotech start-up from a University of Delaware molecular biologist named Adam Marsh's company.

Symptoms of spastic CP include jerky movements, muscle stiffness and muscle tightness that can affect posture, make movement difficult, and cause affected children to be less active.

The Centers for Disease Control and Prevention (CDC) estimate that 1 in every 323 children has CP, making it the most common physical disability in children.

Blood samples from children aged 9 to 19 years old were analyzed as part of a blinded study, using next-generation sequencing. The aim was to establish whether DNA methylation patterns vary between patients with spastic CP waiting for surgery and regular orthopedic patients.

Strong variations in DNA methylation patterns were identified by the scientists, suggesting that there are differences in the genome of children with spastic CP that could be used to diagnose the condition.

The team then proved the use of these methylation markers by blindly separating groups of children with and without CP.

Samples from a different group ranging from 2 to 5 years of age in a second study were also used to validate the results. The researchers were able to predict that blood samples belonged to children with the condition with 73% accuracy.

The evidence suggests that there is some epigenetic or genetic connection. If we can do a better job of screening for these at time of birth versus waiting for the disorder to be diagnosed say, at two years of age, then potentially we'll be able to deliver earlier therapeutics and have better outcomes and lower medical costs."
Erin Crowgey, Associate Director of Bioinformatics at Nemours

This new study utilizes a novel software platform and statistical method developed by Prof. Marsh at UD, and licensed by GenPro, to take measurements of methylation patterns in DNA (a cell's genetic code) using next generation sequencing (NGS) data.

The approach uses sophisticated machine learning techniques and algorithms to sort through hundreds of gigabytes of NGS data looking for these distinct DNA methylation patterns.

Having a clearer insight into methylation signals could help researchers uncover more details surrounding the cellular processes that accelerate CP, which could result in improved treatments for the condition. The team believes the test may be used to help treat other disorders, such as infant leukemia.

This blood test could be a game changer. The earlier the diagnosis, the earlier we can direct therapies at the child. Specifically, high intensity physical therapy and possibly early surgery to prevent more significant problems in the future, and hopefully improve overall function and quality of life."
Dr. M. W. Shrader, Director of the Cerebral Palsy Centre at Nemours

Source:

https://www.eurekalert.org/pub_releases/2018-06/uod-ddd062118.php