Phosformer-ST

Explainable kinase-substrate interaction predictions

Phosphorylation, a post-translational modification regulated by protein kinase enzymes, plays an essential role in almost all cellular processes. Understanding how each of the nearly 500 protein kinases encoded in the human genome selectively phosphorylates their substrates is a foundational challenge in bioinformatics and cell signaling. Although deep learning models have been a popular means to predict new kinase-substrate relationships, existing models often lack interpretability, making it challenging to evaluate model performance and generate informed hypotheses for experimental studies. Here, we provide a web interface for predicting kinase substrate associations for user-defined sequences and a resource for visualizing the learned kinase-substrate associations.