<scp>RNA</scp> Base Pairing Probability Prediction Based on <scp>IoMT</scp> ‐Driven Conv‐Transformer

ABSTRACT RNA base pairing probability is a critical determinant of RNA structure, influencing its stability and functionality. This property is pivotal for mRNA vaccine design, disease diagnosis, and drug discovery. We introduce an innovative Internet of Medical Things (IoMT)‐driven Conv‐Transformer model to predict RNA base pairing probabilities. Leveraging IoMT's edge intelligence, our model efficiently collects and processes real‐time RNA sequence data from diverse medical devices, thereby enhancing our model's feature extraction and prediction accuracy. Given the data‐driven advantages from IoMT, the proposed Conv‐Transformer model utilizes word embedding and position coding to encode primary and secondary RNA structures. It then employs a multi‐headed self‐attention mechanism to capture global base interactions and one‐dimensional convolution to extract local features. Our experiments demonstrate superior performance compared to five classical machine learning models, reducing RMSE and MAE by at least 16% and 20%, respectively. This work highlights the potential of IoMT and advanced deep learning techniques in enhancing RNA structure prediction.