Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics. Homo Sapiens, Mus Musculus

We introduce RNAkinet, a deep convolutional and recurrent neural network, to detect nascent RNA molecules following metabolic labeling with the nucleoside analog 5-ethynyl uridine. RNAkinet is tailored to directly process electrical signals from nanopore sequencing and effectively distinguishes between nascent and pre-existing RNA molecules from various cell types and organisms. By modeling RNA decay rates, RNAkinet allows reproducible identification of the kinetic parameters, such as decay rates, of individual RNA isoforms and is expected to facilitate studies of RNA isoform metabolism and the regulatory elements that influence it.