Towards in silico CLIP-seq: predicting protein-RNA interaction via sequence-to-signal learning

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Dokumenter

  • Fulltext

    Forlagets udgivne version, 3,86 MB, PDF-dokument

We present RBPNet, a novel deep learning method, which predicts CLIP-seq crosslink count distribution from RNA sequence at single-nucleotide resolution. By training on up to a million regions, RBPNet achieves high generalization on eCLIP, iCLIP and miCLIP assays, outperforming state-of-the-art classifiers. RBPNet performs bias correction by modeling the raw signal as a mixture of the protein-specific and background signal. Through model interrogation via Integrated Gradients, RBPNet identifies predictive sub-sequences that correspond to known and novel binding motifs and enables variant-impact scoring via in silico mutagenesis. Together, RBPNet improves imputation of protein-RNA interactions, as well as mechanistic interpretation of predictions.
OriginalsprogEngelsk
Artikelnummer180
TidsskriftGenome Biology
Vol/bind24
Udgave nummer1
Antal sider37
ISSN1474-7596
DOI
StatusUdgivet - 2023

Bibliografisk note

Funding Information:
Open Access funding enabled and organized by Projekt DEAL. This work was supported by the Helmholtz Association under the joint research school “Munich School for Data Science (MUDS)” to M.H., N.W., J.G. and A.M., the Deutsche Forschungsgemeinschaft (SFB/TR501 84 TP C01) to A.M. and L.M. and (SFB/Transregio TRR267) to J.G.; O.W.’s work was funded in part by the Novo Nordisk Foundation through the Center for Basic Machine Learning Research in Life Science (NNF20OC0062606). O.W. further acknowledges support from the Pioneer Centre for AI, DNRF grant number P1; K.K.’s and J.U.’s work was funded by the European Union’s Horizon 2020 research and innovation program (835300-RNPdynamics). K.K. and J.U. further acknowledge support from The Francis Crick Institute, which receives its core funding from Cancer Research UK (FC001110), the UK Medical Research Council (FC001110), and the Wellcome Trust (FC001110).

Publisher Copyright:
© 2023, BioMed Central Ltd., part of Springer Nature.

ID: 362744991