Hybrid representation learning for human m⁶A modifications with chromosome-level generalizability

$N^6-\text{methyladenosine}$ ( $m^{6}A$ ) 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 $m^{6}A$ sites, most suffer from limited chromosome-level generalizability due to evaluation on randomly split datasets.

In this study, we propose two novel hybrid deep learning models-Hybrid Model and Hybrid Deep Model-that integrate local sequence features (k-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 genomic regions. Our proposed models outperform the state-of-the-art m6A-TCPred model across all key evaluation metrics. Hybrid Deep Model achieves the highest accuracy under Random-Split, while Hybrid Model demonstrates superior generalization under Leave-One-Chromosome-Out, indicating that deep global representations may overfit in chromosome-independent settings. These findings underscore the importance of rigorous validation strategies and offer insights into designing robust $m^{6}A$ predictors.

Source code and datasets are available at: https://github.com/malikmtahir/LOCO-m6A.