Skip to main content

Projects RNA

A computational map of the Human-SARS-CoV-2 Protein-RNA Interactome predicted at single-nucleotide resolution

We adapted our deep learning Pysster classifier to predict binding sites of hundreds of human RBPs on the viral RNA of SARS-CoV-2, 7 related coronaviruses and different variants of concerns. “In silico approaches are very powerful and deeply needed to quickly screen the thousands of viral mutations that potentially drive the fitness of the virus, in order to be prepared for the next pandemics” points out Marc Horlacher, the PhD student leading the project.


Unraveling sequence determinants which drive protein-RNA interaction is crucial for studying binding mechanisms and the impact of genomic variants. RBPNet, a novel deep learning method, predicts CLIP crosslink count distribution from RNA sequence at single-nucleotide resolution. RBPNet achieves high generalization on eCLIP, iCLIP and miCLIP assays, outperforming state-of-the-art classifiers. Via model-intrinsic bias correction, RBPNet identifies predictive RNA sub-sequences corresponding to known binding motifs and enables variant-impact scoring via in silico mutagenesis. Together, RBPNet improves inference of protein-RNA interaction, as well as mechanistic interpretation of predictions.

Author: Marc Horlacher.


In silico modeling of RNA modifications from both bulk and single cell NGS data

RNA modifications control the entire life cycle of mRNAs and are associated with numerous diseases. In collaboration with Robert Schneider’s group, at the Institute of Functional Epigenetics (IFE) Helmholtz Munich, we leverage the latest next generation sequencing techniques to reconstruct maps of RNA modifications at single nucleotide resolution across the entire transcriptome. We then use advanced statistical modeling to extract patterns that could explain how epitranscriptomic modifications are deposited and what functional processes they control in the cell.

Author: Patrick Schinke.