Ab initio detection of multiple epitranscriptomic modifications from ONT direct RNA sequencing data

Charting the eukaryotic epitranscriptome by direct RNA sequencing is promising but still challenging as current bioinformatics tools are based on modification-unaware software and require multiple modification-specific learning steps. Here, we introduce NanoSpeech, a modification-aware basecaller for ab initio simultaneous detection of up to nine modified bases through a transformer model, and NanoListener, implementing a simulated randomers strategy for robust training datasets and a new generation of ONT basecallers.