TY - JOUR
T1 - Towards in silico CLIP-seq
T2 - predicting protein-RNA interaction via sequence-to-signal learning
AU - Horlacher, Marc
AU - Wagner, Nils
AU - Moyon, Lambert
AU - Kuret, Klara
AU - Goedert, Nicolas
AU - Salvatore, Marco
AU - Ule, Jernej
AU - Gagneur, Julien
AU - Winther, Ole
AU - Marsico, Annalisa
N1 - Publisher Copyright:
© 2023, BioMed Central Ltd., part of Springer Nature.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - CLIP-seq
KW - Computational biology
KW - Deep learning
KW - Protein-RNA interaction
U2 - 10.1186/s13059-023-03015-7
DO - 10.1186/s13059-023-03015-7
M3 - Journal article
C2 - 37542318
AN - SCOPUS:85166598318
VL - 24
JO - Genome Biology (Online Edition)
JF - Genome Biology (Online Edition)
SN - 1474-7596
IS - 1
M1 - 180
ER -