DNA methylation-based classification of malformations of cortical development in the human brain

Abstract

Malformations of cortical development (MCD) comprise a broad spectrum of structural brain lesions frequently associated with epilepsy. Disease definition and diagnosis remain challenging and are often prone to arbitrary judgment. Molecular classification of histopathological entities may help rationalize the diagnostic process. We present a retrospective, multi-center analysis of genome-wide DNA methylation from human brain specimens obtained from epilepsy surgery using EPIC 850 K BeadChip arrays. A total of 308 samples were included in the study. In the reference cohort, 239 formalin-fixed and paraffin-embedded (FFPE) tissue samples were histopathologically classified as MCD, including 12 major subtype pathologies. They were compared to 15 FFPE samples from surgical non-MCD cortices and 11 FFPE samples from post-mortem non-epilepsy controls. We applied three different statistical approaches to decipher the DNA methylation pattern of histopathological MCD entities, i.e., pairwise comparison, machine learning, and deep learning algorithms. Our deep learning model, which represented a shallow neuronal network, achieved the highest level of accuracy. A test cohort of 43 independent surgical samples from different epilepsy centers was used to test the precision of our DNA methylation-based MCD classifier. All samples from the test cohort were accurately assigned to their disease classes by the algorithm. These data demonstrate DNA methylation-based MCD classification suitability across major histopathological entities amenable to epilepsy surgery and age groups and will help establish an integrated diagnostic classification scheme for epilepsy-associated MCD.

RNA-sequencing improves diagnosis for neurodevelopmental disorders by identifying pathogenic non-coding variants and reinterpretation of coding variants

“…For example, proteome analysis can increase the diagnostic yield where both DNA and RNA analysis fail to identify a pathogenic change (70). Introduction of specific epigenetic methylation signatures for NDD, as a complementary diagnostic aid, could also be valuable (71). It is clear that there currently is no single technology capable of serving all diagnostic queries and solving all genetically undiagnosed NDD cases.…”

Methylation classifiers: Brain tumors, sarcomas, and what's next

“…These include the “infant type hemispheric glioma” previously diagnosed as glioblastoma in most instances or the “diffuse glioneuronal tumor with oligodendroglioma‐like features and nuclear clusters (DGONC),” 69 Novel tumors not yet included are the “PLAGL1‐fused neuroepithelial tumor” 70 reminiscent of ependymoma or the “Primary mismatch repair deficient IDH‐mutant astrocytoma (PMMRDIA).” 71 Characterization of several other novel tumor types can be expected within short time. Recently, methylation analysis has been employed to characterize hamartous malformations and cortical dysplasias, both constituting challenging differential diagnoses to low glioneuronal tumors 72,73 …”

“…"71 Characterization of several other novel tumor types can be expected within short time. Recently, methylation analysis has been employed to characterize hamartous malformations and cortical dysplasias, both constituting challenging differential diagnoses to low glioneuronal tumors 72,73.…”

Disease classification for whole blood DNA methylation: meta-analysis, missing values imputation, and XAI

“…Classification of cases and controls for certain diseases is also performed using DNA methylation data. Examples of machine learning applications using epigenetic data include classification of coronary heart disease, neurodevelopmental syndromes, schizophrenia, Alzheimer's disease, psychiatric disorders and others [33][34][35][36][37][38][39].…”