Generation of DNA Methylation Signatures and Classification of Variants in Rare Neurodevelopmental Disorders Using EpigenCentral
Bibliographic record
Abstract
There are more than 700 genes that encode proteins that function in epigenetic regulation and chromatin modification. Germline variants in these genes (typically heterozygous) are associated with rare neurodevelopmental disorders (NDDs) characterized by growth abnormalities and intellectual and developmental delay. Advancements in next-generation sequencing have dramatically increased the detection of pathogenic sequence variants in genes encoding epigenetic machinery associated with NDDs and, concurrently, the number of clinically uninterpretable variants classified as variants of uncertain significance (VUS). Recently, DNA methylation (DNAm) signatures, disorder-specific patterns of DNAm change, have emerged as a functional tool that provides insights into disorder pathophysiology and can classify pathogenicity of variants in NDDs. To date, our group and others have identified DNAm signatures for more than 60 Mendelian neurodevelopmental disorders caused by variants in genes encoding epigenetic machinery. There is broad interest in both the research and clinical communities to develop and catalog DNAm signatures in rare NDDs, but there are challenges in optimizing study design considerations and availability of platforms that integrate bioinformatics tools with the appropriate statistical framework required to analyze genome-wide DNAm data. We previously published EpigenCentral, a platform for analysis of DNAm data in rare NDDs. In this article, we utilize the published Weaver syndrome dataset to provide step-by-step protocols for using EpigenCentral for exploratory analysis to identify DNAm signatures and for classification of NDD variants. We also provide important considerations for experimental design and interpretation of DNAm results. © 2022 Wiley Periodicals LLC. Basic Protocol 1: Exploratory analysis to identify disorder-specific DNAm signatures Basic Protocol 2: Classification of variants associated with neurodevelopmental disorders.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".