Simultaneous profiling of ac⁴C and m⁵C modifications from nanopore direct RNA sequencing

N4-acetylcytidine (ac⁴C) and 5-methylcytidine (m⁵C) play important roles in mRNA stability, translation efficiency, and cellular stress responses. Current methods for detecting RNA modifications from nanopore sequencing data do not support simultaneous de novo identification of both modifications. In this study, we generate in vitro transcripts from a cDNA library with modifications, and develop modCnet, a deep learning frame utilizing nanopore direct RNA sequencing to identify ac⁴C and m⁵C from a single sample. We demonstrate the high performance of modCnet and apply it to detect ac⁴C and m⁵C sties on in vivo mRNAs from human cell lines, supported by RIP-seq, BisSeq and RedaC:T-seq. We further validate candidate ac⁴C sites by NaBH₄-induced reverse transcription (RT) stop events. The versatility for simultaneous identification of different types of modified cytidines at the single-molecule level open a window for studying the biological function of the co-occurrence of ac⁴C and m⁵C modifications.