Related Experiment Video
Updated: Jun 22, 2025
Comprehensive DNA Methylation Analysis Using a Methyl-CpG-binding Domain Capture-based Method in Chronic Lymphocytic Leukemia Patients
Published on: June 16, 2017
Novel Machine Learning of DNA Methylation Patterns to Diagnose Complex Disease: Identification of Cerebral Palsy with
Jonathan Hicks1,2, Karyn Robinson2, Stephanie Lee2
1Bioinformatics and Computational Biology, University of Delaware.
Insights
This study shows that DNA methylation patterns in blood can help diagnose spastic cerebral palsy (CP), even when epilepsy is present. Machine learning effectively identifies these methylation markers for accurate CP diagnosis.
Area of Science:
- Neuroscience
- Genetics
- Computational Biology
Background:
- Spastic cerebral palsy (CP) is a prevalent pediatric neurological disorder, often diagnosed late due to complexity and co-occurring conditions like epilepsy.
- Early diagnosis of CP is challenging, with many cases identified after 19 months and confirmed by age five.
- Altered DNA methylation in peripheral blood cells shows potential for CP diagnosis.
Purpose of the Study:
- To evaluate the diagnostic value of DNA methylation patterns for spastic cerebral palsy (CP).
- To assess machine learning's ability to detect CP in complex cases, including those with co-occurring epilepsy.
- To identify specific methylation loci associated with CP and epilepsy.
Main Methods:
- Analysis of DNA methylation patterns using Illumina MethylationEpic arrays on blood samples from 30 participants (CP, epilepsy, both, or neither).
- Development of a novel machine learning algorithm (Support Vector Machine/Linear Discriminant Analysis) for classification.
- Binary and 4-way classification analyses to identify informative methylation loci and measure classification performance.
Main Results:
- The machine learning algorithm achieved high classification performance, with median F1 scores of 0.67 in a 4-class comparison and 1.0 in binary classification for SVM.
- Support Vector Machine (SVM) outperformed Linear Discriminant Analysis (LDA), demonstrating its efficacy in classifying CP and epilepsy.
- The algorithm successfully classified individuals with spastic CP and/or epilepsy from controls with significant accuracy.
Conclusions:
- DNA methylation patterns in peripheral blood hold diagnostic potential for spastic cerebral palsy (CP).
- Machine learning algorithms, particularly SVM, can effectively utilize these methylation patterns for CP diagnosis, including in complex cases with epilepsy.
- This approach offers a promising avenue for earlier and more accurate diagnosis of CP.
Abstract:
Spastic cerebral palsy (CP) is a common pediatric-onset disability with an estimated prevalence of 0.2%. It is a complex condition characterized by muscle stiffness, contractures, and abnormal movement. Spastic CP is difficult to diagnose. Although nearly all affected children are born with it or acquire it immediately after birth, many are not identified until after 19 months of age with the diagnosis often not confirmed until 5 years of age. In addition, CP frequently co-occurs with other complex conditions that can complicate diagnosis and treatment. For example, an estimated 42% of spastic CP cases have co-occurring epilepsy. Recent studies indicate that altered DNA methylation patterns in peripheral blood cells are associated with CP and may have diagnostic value.Accordingly, the purpose of this study is to assess the diagnostic value of methylation in CP with more complex disease states. We evaluated machine learning classification for detecting CP based on DNA methylation pattern analysis in the context of co-occurrent epilepsy. Blood samples from 30 study participants diagnosed with epilepsy (n=4), spastic CP (n=10), both (n=8), or neither (n=8) were analyzed by Illumina MethylationEpic arrays. A novel machine learning algorithm using a Support Vector Machine (SVM) or Linear Discriminant Analysis (LDA) was developed to identify methylation loci that classified CP from controls and to measure the classification ability of identified methylation loci. The isolation of informative methylation loci was performed in a binary comparison between CP and controls, as well as in a 4-way comparison that included epilepsy. Median F1 scores for SVM-based analysis were 0.67 in 4-class comparison, and 1.0 in the binary classification. SVM outperformed LDA (median F1 0.57 and 0.86, respectively). Overall, the novel machine learning based algorithm was able to classify study participants with spastic CP and/or epilepsy from controls with significant performance.
More Related Videos
08:22A Novel Strategy Combining Array-CGH, Whole-exome Sequencing and In Utero Electroporation in Rodents to Identify Causative Genes for Brain Malformations
Published on: December 1, 2017
13:11Optimized Analysis of DNA Methylation and Gene Expression from Small, Anatomically-defined Areas of the Brain
Published on: July 12, 2012