MEDNA-DFM: A Dual-View FiLM-MoE Model for Explainable DNA Methylation Prediction

TL;DR

This paper introduces MEDNA-DFM, an explainable deep learning model for DNA methylation prediction that captures conserved motifs and generates biological hypotheses, outperforming prior methods in reliability and interpretability.

Contribution

The study presents MEDNA-DFM, a novel dual-view FiLM-MoE model with mechanism-inspired algorithms, enhancing interpretability and motif extraction in DNA methylation prediction.

Findings

MEDNA-DFM accurately distinguishes methylation patterns across species.

The model's generalization relies on conserved motifs like GC content.

Motif extraction significantly outperforms previous methods.

Abstract

Accurate computational identification of DNA methylation is essential for understanding epigenetic regulation. Although deep learning excels in this binary classification task, its "black-box" nature impedes biological insight. We address this by introducing a high-performance model MEDNA-DFM, alongside mechanism-inspired signal purification algorithms. Our investigation demonstrates that MEDNA-DFM effectively captures conserved methylation patterns, achieving robust distinction across diverse species. Validation on external independent datasets confirms that the model's generalization is driven by conserved intrinsic motifs (e.g., GC content) rather than phylogenetic proximity. Furthermore, applying our developed algorithms extracted motifs with significantly higher reliability than prior studies. Finally, empirical evidence from a Drosophila 6mA case study prompted us to propose a "sequence-structure synergy" hypothesis, suggesting that the GAGG core motif and an upstream A-tract element function cooperatively. We further validated this hypothesis via in silico mutagenesis, confirming that the ablation of either or both elements significantly degrades the model's recognition capabilities. This work provides a powerful tool for methylation prediction and demonstrates how explainable deep learning can drive both methodological innovation and the generation of biological hypotheses.