m6ATM: a deep learning framework for demystifying the m6A epitranscriptome with Nanopore long-read RNA-seq data

N6-methyladenosine (m6A) is one of the most abundant and well-known modifications in messenger RNAs since its discovery in the 1970s. Recent studies have demonstrated that m6A is involved in various biological processes, such as alternative splicing and RNA degradation, playing an important role in a variety of diseases. To better understand the role of m6A, transcriptome-wide m6A profiling data are indispensable. In recent years, the Oxford Nanopore Technology Direct RNA Sequencing (DRS) platform has shown promise for RNA modification detection based on current disruptions measured in transcripts. However, decoding current intensity data into modification profiles remains a challenging task. Here, we introduce the m6A Transcriptome-wide Mapper (m6ATM), a novel Python-based computational pipeline that applies deep neural networks to predict m6A sites at a single-base resolution using DRS data. The m6ATM model architecture incorporates a WaveNet encoder and a dual-stream multiple-instance learning model to extract features from specific target sites and characterize the m6A epitranscriptome. For validation, m6ATM achieved an accuracy of 80% to 98% across in vitro transcription datasets containing varying m6A modification ratios and outperformed other tools in benchmarking with human cell line data. Moreover, we demonstrated the versatility of m6ATM in providing reliable stoichiometric information and used it to pinpoint PEG10 as a potential m6A target transcript in liver cancer cells. In conclusion, m6ATM is a high-performance m6A detection tool, and our results pave the way for future advancements in epitranscriptomic research.