De novo basecalling of RNA modifications at single molecule and nucleotide resolution

RNA modifications influence RNA function and fate, but detecting them in individual molecules remains challenging for most modifications. Here we present a novel methodology to generate training sets and build modification-aware basecalling models. Using this approach, we develop the m6ABasecaller,...

Descripción completa

Detalles Bibliográficos
Autores: Cruciani, Sonia, Delgado-Tejedor, Anna, Pryszcz, Leszek Piotr, 1985-, Medina, Rebeca, Llovera Nadal, Laia, Novoa, Eva Maria
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/70384
Acceso en línea:http://hdl.handle.net/10230/70384
http://dx.doi.org/10.1186/s13059-025-03498-6
Access Level:acceso abierto
Palabra clave:Basecalling
Machine learning
N6-methyladenosine
Nanopore sequencing
Native RNA
RNA modifications
Single molecule resolution
Training data
Descripción
Sumario:RNA modifications influence RNA function and fate, but detecting them in individual molecules remains challenging for most modifications. Here we present a novel methodology to generate training sets and build modification-aware basecalling models. Using this approach, we develop the m6ABasecaller, a basecalling model that predicts m6A modifications from raw nanopore signals. We validate its accuracy in vitro and in vivo, revealing stable m6A modification stoichiometry across isoforms, m6A co-occurrence within RNA molecules, and m6A-dependent effects on poly(A) tails. Finally, we demonstrate that our method generalizes to other RNA and DNA modifications, paving the path towards future efforts detecting other modifications.