biostudies-literatureUnknown5(1)Tahir M<h4>Motivation</h4>N6-methyladenosine ( m6A ) is the most abundant internal modification in eukaryotic mRNA and plays essential roles in post-transcriptional gene regulation. While several deep learning approaches have been proposed to predict m6A sites, most suffer from limited chromosome-level generalizability due to evaluation on randomly split datasets.<h4>Results</h4>In this study, we propose two novel hybrid deep learning models-Hybrid Model and Hybrid Deep Model-that integrate local sequence features (<i>k</i>-mers) and contextual embeddings via convolutional neural networks to improve predictive performance and generalization. We evaluate these models using both a Random-Split strategy and a more biologically realistic Leave-One-Chromosome-Out setting to ensure robustness across geBioinformatics advancesvbaf170https://www.ebi.ac.uk/biostudies/studies/S-EPMC12288952biostudies-literatureHybrid representation learning for human m&lt;sup&gt;6&lt;/sup&gt;A modifications with chromosome-level generalizability.PMC12288952Liu QTahir MRamanna SfalseHybrid representation learning for human m&lt;sup&gt;6&lt;/sup&gt;A modifications with chromosome-level generalizability.<h4>Motivation</h4>N6-methyladenosine ( m6A ) is the most abundant internal modification in eukaryotic mRNA and plays essential roles in post-transcriptional gene regulation. While several deep learning approaches have been proposed to predict m6A sites, most suffer from limited chromosome-level generalizability due to evaluation on randomly split datasets.<h4>Results</h4>In this study, we propose two novel hybrid deep learning models-Hybrid Model and Hybrid Deep Model-that integrate local sequence features (<i>k</i>-mers) and contextual embeddings via convolutional neural networks to improve predictive performance and generalization. We evaluate these models using both a Random-Split strategy and a more biologically realistic Leave-One-Chromosome-Out setting to ensure robustness across ge2025-01-01T00:00:00Z20252026-03-17T15:35:37.102Z2025-08-17T03:06:09.621ZS-EPMC122889524070886810.1093/bioadv/vbaf170