Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22850v1</id>\n    <title>MEDNA-DFM: A Dual-View FiLM-MoE Model for Explainable DNA Methylation Prediction</title>\n    <updated>2026-02-26T10:38:41Z</updated>\n    <link href='https://arxiv.org/abs/2602.22850v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22850v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-26T10:38:41Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Yi He</name>\n      <arxiv:affiliation>Cuiying Honors College, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n      <arxiv:affiliation>School of Mathematics and Statistics, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Yina Cao</name>\n      <arxiv:affiliation>School of Management, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Jixiu Zhai</name>\n      <arxiv:affiliation>Shanghai Innovation Institute, Shanghai, China</arxiv:affiliation>\n      <arxiv:affiliation>School of Mathematics and Statistics, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Di Wang</name>\n      <arxiv:affiliation>Cuiying Honors College, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n      <arxiv:affiliation>School of Mathematics and Statistics, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Junxiao Kong</name>\n      <arxiv:affiliation>School of Mathematics and Statistics, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Tianchi Lu</name>\n      <arxiv:affiliation>School of Mathematics and Statistics, Lanzhou University, Lanzhou, Gansu, China</arxiv:affiliation>\n      <arxiv:affiliation>Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China</arxiv:affiliation>\n    </author>\n  </entry>"
}