Diagnostic Utility of Genome-Wide DNA Methylation Analysis in Mendelian Neurodevelopmental Disorders

Abstract

Mendelian neurodevelopmental disorders customarily present with complex and overlapping symptoms, complicating the clinical diagnosis. Individuals with a growing number of the so-called rare disorders exhibit unique, disorder-specific DNA methylation patterns, consequent to the underlying gene defects. Besides providing insights to the pathophysiology and molecular biology of these disorders, we can use these epigenetic patterns as functional biomarkers for the screening and diagnosis of these conditions. This review summarizes our current understanding of DNA methylation episignatures in rare disorders and describes the underlying technology and analytical approaches. We discuss the computational parameters, including statistical and machine learning methods, used for the screening and classification of genetic variants of uncertain clinical significance. Describing the rationale and principles applied to the specific computational models that are used to develop and adapt the DNA methylation episignatures for the diagnosis of rare disorders, we highlight the opportunities and challenges in this emerging branch of diagnostic medicine.

Keywords: DNA methylation; constitutional disorders; epigenetics; episignature; machine learning; neurodevelopmental disorders; overgrowth with intellectual disability syndromes; random forest; support vector machines.

Figure 1

Summary of a DNA methylation analysis and constructing the classification model.

Figure 2

Classification of unresolved cases. (A) Six individuals suspected of having mental retardation, X-linked syndromic, Claes-Jensen-type (MRXSCJ) were supplied to the multi-class support vector machine (SVM) classifier. The methylation variant pathogenicity (MVP) scores generated by the model illustrate that 4 individuals are classified as cases of MRXSCJ, one as not having any of the 15 syndromes, and one (the red one) is classified as a Sotos syndrome 1 (Sotos1) case. (B) The multiple dimensional scaling (MDS) plot with MRXSCJ samples (purple circles), healthy control samples (green circles), and Sotos1 samples (red circles). This plot illustrates the clustering of four of the individuals described in panel A with the MRXSCJ case samples (blue circles) and two individuals separate from the MRXSCJ case samples. The grey circle represents the patient classified as not having any of the 15 syndromes, and the pink circle depicts the individual classified as a Sotos1 case.