RESUMO
RNA modifications modulate essential cellular functions. However, it is challenging to quantitatively identify the differences in RNA modifications. To further improve the single-molecule sensing ability of nanopores, we propose a machine-learning algorithm called SmartImage for identifying and classifying nanopore electrochemical signals based on a combination of improved graph conversion methods and deep neural networks. SmartImage is effective for nearly all ranges of signal duration, which breaks the limitation of the current nanopore algorithm. The overall accuracy (OA) of our proposed recognition strategy exceeded 90% for identifying three types of RNAs. Prediction experiments show that the SmartImage owns the ability to recognize one modified RNA molecule from 1000 normal RNAs with OA >90%. Thus our proposed model and algorithm hold the potential application in clinical applications.