What question did this study set out to answer?

The study aims to develop a computational model, MethylFM, for analyzing DNA methylation dynamics and its implications for gene regulation.

April 5, 2026

Abstract 5482: MethylFM: A DNA methylation foundation model for modeling epigenomic regulatory dynamics.

Key Points

The study aims to develop a computational model, MethylFM, for analyzing DNA methylation dynamics and its implications for gene regulation.
Utilized the BLUEprint Epigenome dataset for training, including WGBS profiles and histone modification data.
Employed a BERT-style transformer with rotary positional embeddings for processing methylation patterns.
Focused on CpG sites around transcription start sites for regulatory region analysis.
Achieved R2 > 0.6 for CpG-level imputation accuracy from 450k array data.
MethylFM outperformed METHimpute slightly with R2 = 0.518 compared to 0.513.
In TSS-level H3K27ac prediction, reached R2 = 0.614, close to the state-of-the-art M2A.
Demonstrated strong clustering accuracy in hematopoietic lineages compared to experimental data, with a Silhouette score of 0.47.

Abstract

Abstract DNA methylation regulates gene expression, differentiation, and disease, making it a key target for computational modeling in precision medicine. To integrate high-resolution whole-genome bisulfite sequencing (WGBS) data into a unified analytical framework, we developed MethylFM, a transformer-based foundation model that captures context-aware methylation patterns and supports multiple downstream tasks.We trained on the BLUEprint Epigenome dataset, comprising single-base WGBS profiles across diverse blood cell types with matched histone modification and transcriptome data. By focusing on ±100 CpG sites around transcription start sites (TSS), MethylFM targets regulatory regions central to gene expression and chromatin dynamics. Built on a BERT-style transformer with rotary positional embeddings and a masked-value prediction objective, it learns robust representations capturing both local and long-range dependencies in methylation.MethylFM demonstrated versatility across three downstream applications. For CpG-level imputation, it reconstructed high-resolution WGBS profiles from 450k array data with strong accuracy (R2 0.6, MAE 0.15). When benchmarked against METHimpute, evaluation was restricted to two samples due to METHimpute’s intensive runtime; nonetheless, MethylFM achieved slightly higher accuracy (R2 = 0.518 vs. 0.513), underscoring both precision and computational efficiency. In TSS-level H3K27ac prediction, the model reached R2 = 0.614, matching the state-of-the-art M2A (R2 = 0.617) and highlighting its capacity to infer promoter activity directly from DNA methylation. Finally, sample-level clustering based on predicted H3K27ac profiles accurately recapitulated hematopoietic lineages, surpassing experimental H3K27ac data (Silhouette = 0.47 vs. 0.30) and approaching RNA-seq-derived clustering performance (Silhouette = 0.51), demonstrating that MethylFM captures biologically meaningful epigenetic structure. Together, these results establish MethylFM as a generalizable and efficient framework for epigenomic modeling, enabling cost-effective methylation imputation, promoter activity prediction, and cellular identity characterization to advance biomarker discovery and precision medicine. Citation Format: Limeng Pu, Xiang Chen, . MethylFM: A DNA methylation foundation model for modeling epigenomic regulatory dynamics abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 5482.

KI fragen

Bookmark