The epitranscriptomics field has undergone an enormous expansion in the last few years; however, a major limitation is the lack of generic methods to map RNA modifications transcriptome-wide. Here, we show that using direct RNA sequencing, N-methyladenosine (mA) RNA modifications can be detected with high accuracy, in the form of systematic errors and decreased base-calling qualities. Specifically, we find that our algorithm, trained with mA-modified and unmodified synthetic sequences, can predict mA RNA modifications with ~90% accuracy. We then extend our findings to yeast data sets, finding that our method can identify mA RNA modifications in vivo with an accuracy of 87%. Moreover, we further validate our method by showing that these 'errors' are typically not observed in yeast ime4-knockout strains, which lack mA modifications. Our results open avenues to investigate the biological roles of RNA modifications in their native RNA context.