m6AGE: A Predictor for N6-Methyladenosine Sites Identification Utilizing Sequence Characteristics and Graph Embedding-Based Geometrical Information

N-6-methyladenosine (m(6)A) is one of the most prevalent RNA post-transcriptional modifications and is involved in various vital biological processes such as mRNA splicing, exporting, stability, and so on. Identifying m(6)A sites contributes to understanding the functional mechanism and biological significance of m(6)A. The existing biological experimental methods for identifying m(6)A sites are time-consuming and costly. Thus, developing a high confidence computational method is significant to explore m(6)A intrinsic characters. In this study, we propose a predictor called m(6)AGE which utilizes sequence-derived and graph embedding features. To the best of our knowledge, our predictor is the first to combine sequence-derived features and graph embeddings for m(6)A site prediction. Comparison results show that our proposed predictor achieved the best performance compared with other predictors on four public datasets across three species. On the A101 dataset, our predictor outperformed 1.34% (accuracy), 0.0227 (Matthew's correlation coefficient), 5.63% (specificity), and 0.0081 (AUC) than comparing predictors, which indicates that m6AGE is a useful tool for m(6)A site prediction. The source code of m(6)AGE is available at https://github.com/bokunoBike/ m(6)AGE.

Automated summary

N-6-methyladenosine (m(6)A) is a prevalent RNA post-transcriptional modification with significant biological implications. The proposed predictor m(6)AGE combines sequence-derived and graph embedding features for m(6)A site prediction, outperforming other predictors across multiple datasets.