Un marco de aprendizaje profundo para la predicción integral de proteínas humanas que se unen a ARN G-cuádruplex

G-quadruplex-binding proteins (G4BPs) play key roles in RNA metabolism and stress response, yet their identification remains experimentally challenging. Here, we present a deep learning framework for the prediction of RNA G4BPs (RG4BPs), integrating diverse encoding strategies and neural architectures. Our best-performing model, which includes ESM-2 protein language model embeddings and consists of an LSTM architecture, achieved 86% accuracy in distinguishing RG4BPs from non-binders proteins. The application of this model to the human proteome uncovered 2,160 high-confidence RG4BP candidates, many of which display intrinsically disordered regions (IDRs) and enrichment in stress granule organelles. These findings reveal a potential link between G-quadruplex recognition and cellular stress responses. To enable easy and broad access to the framework, we developed G4REP, a web server for RG4BP prediction and analysis. Overall, an effective approach to explore the RG4BPs landscape and uncover novel players in RNA regulation is provided.

Source code for the G4REP Model training and evaluation is available at: https://github.com/G4REP/G4REPmodel and at https://doi.org/10.5281/zenodo.17963046 G4REP Server is hosted at: https://schubert.bio.uniroma1.it/g4/.

Supplementary data are available at Bioinformatics online.