DTC-m6Am: A Framework for Recognizing N6,2'-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms.

Background: m⁶Am is a specific RNA modification that plays an important role in regulating mRNA stability, translational efficiency, and cellular stress response. m⁶Am's precise identification is essential to gain insight into its functional mechanisms at transcriptional and post-transcriptional levels. Due to the limitations of experimental assays, the development of efficient computational tools to predict m⁶Am sites has become a major focus of research, offering potential breakthroughs in RNA epigenetics. In this study, we present a robust and reliable deep learning model, DTC-m6Am, for identifying m⁶Am sites across the transcriptome.

Methods: Our proposed DTC-m6Am model first represents RNA sequences by One-Hot coding to capture base-based features and provide structured inputs for subsequent deep learning models. The model then combines densely connected convolutional networks (DenseNet) and temporal convolutional network (TCN). The DenseNet module leverages its dense connectivity property to effectively extract local features and enhance information flow, whereas the TCN module focuses on capturing global time series dependencies to enhance the modeling capability for long sequence features. To further optimize feature extraction, the Convolutional Block Attention Module (CBAM) is used to focus on key regions through spatial and channel attention mechanisms. Finally, a fully connected layer is used for the classification task to achieve accurate prediction of the m⁶Am site. For the data imbalance problem, we use the focal loss function to balance the learning effect of positive and negative samples and improve the performance of the model on imbalanced data.

Results: The deep learning-based DTC-m6Am model performs well on all evaluation metrics, achieving 87.8%, 50.3%, 69.1%, 41.1%, and 76.5% for sensitivity (Sn), specificity (Sp), accuracy (ACC), Mathew's correlation coefficient (MCC), and area under the curve (AUC), respectively, on the independent test set.

Conclusions: We critically evaluated the performance of DTC-m6Am using 10-fold cross-validation and independent testing and compared it to existing methods. The MCC value of 41.1% was achieved when using the independent test, which is 19.7% higher than the current state-of-the-art prediction method, m6Aminer. The results indicate that the DTC-m6Am model has high accuracy and stability and is an effective tool for predicting m⁶Am sites.