BERMP: a cross-species classifier for predicting m6A sites by integrating a deep learning algorithm and a random forest approach

N-6-methyladenosine (m(6)A) is a prevalent RNA methylation modification involved in several biological processes. Hundreds or thousands of m(6)A sites identified from different species using high-throughput experiments provides a rich resource to construct in-silico approaches for identifying m(6)A sites. The existing m(6)A predictors are developed using conventional machine-learning (ML) algorithms and most are species-centric. In this paper, we develop a novel cross-species deep-learning classifier based on bidirectional Gated Recurrent Unit (BGRU) for the prediction of m(6)A sites. In comparison with conventional ML approaches, BGRU achieves outstanding performance for the Mammalia dataset that contains over fifty thousand m(6)A sites but inferior for the Saccharomyces cerevisiae dataset that covers around a thousand positives. The accuracy of BGRU is sensitive to the data size and the sensitivity is compensated by the integration of a random forest classifier with a novel encoding of enhanced nucleic acid content. The integrated approach dubbed as BGRU-based Ensemble RNA Methylation site Predictor (BERMP) has competitive performance in both cross-validation test and independent test. BERMP also outperforms existing m(6)A predictors for different species. Therefore, BERMP is a novel multi-species tool for identifying m(6)A sites with high confidence.