CryptoBank: A resource for the identification and prediction of cryptic sites in proteins

Cryptic binding sites offer opportunities to modulate targets previously considered "undruggable." However, the scarcity of validated examples limits the development of predictive tools. Here, we introduce CryptoBank, a large-scale database of cryptic sites identified by applying a machine learning model to detect ligand-induced conformational changes in more than 6 million structural alignments of unbound (apo) and bound (holo) protein pairs from the Protein Data Bank (PDB). Our analysis reveals that cryptic pockets are widespread, occurring in ~18% of protein clusters. Leveraging this resource, we fine-tuned a protein language model (PLM) to predict cryptic sites directly from protein sequences. Crucially, we show the broad applicability of our strategy by predicting cryptic sites in four proteins with low sequence identity to any CryptoBank entry and then validating these predictions using molecular dynamics simulations. CryptoBank and the predictive PLM are publicly accessible via a web server, providing valuable resources for cryptic site discovery.