MOTIVATION: Structure-based methods for detecting protein-ligand binding sites play a crucial role in various domains, from fundamental research to biomedical applications. However, current prediction methodologies often rely on holo (ligand-bound) protein conformations for training and evaluation, overlooking the significance of the apo (ligand-free) states. This oversight is particularly problematic in the case of cryptic binding sites (CBSs) where holo-based assessment yields unrealistic performance expectations. RESULTS: To advance the development in this domain, we introduce CryptoBench, a benchmark dataset tailored for training and evaluating novel CBS prediction methodologies. CryptoBench is constructed upon a large collection of apo-holo protein pairs, grouped by UniProtID, clustered by sequence identity, and filtered to contain only structures with substantial structural change in the binding site. CryptoBench comprises 1107 structures with predefined cross-validation splits, making it the most extensive CBS dataset to date. To establish a performance baseline, we measured the predictive power of sequence- and structure-based CBS residue prediction methods using the benchmark. We selected PocketMiner as the state-of-the-art representative of the structure-based methods for CBS detection, and P2Rank, a widely-used structure-based method for general binding site prediction that is not specifically tailored for cryptic sites. For sequence-based approaches, we trained a neural network to classify binding residues using protein language model embeddings. Our sequence-based approach outperformed PocketMiner and P2Rank across key metrics, including area under the curve, area under the precision-recall curve, Matthew's correlation coefficient, and F1 scores. These results provide baseline benchmark results for future CBS and potentially also non-CBS prediction endeavors, leveraging CryptoBench as the foundational platform for further advancements in the field. AVAILABILITY AND IMPLEMENTATION: The CryptoBench dataset, including the benchmark model, is available on Open Science Framework-https://osf.io/pz4a9/. The code and tutorial are available at the GitHub repository-https://github.com/skrhakv/CryptoBench/.

SUMMARY: Understanding the mechanism of action of a protein or designing better ligands for it, often requires access to a bound (holo) and an unbound (apo) state of the protein. Resources for the quick and easy retrieval of such conformations are severely limited. Apo-Holo Juxtaposition (AHoJ), is a web application for retrieving apo-holo structure pairs for user-defined ligands. Given a query structure and one or more user-specified ligands, it retrieves all other structures of the same protein that feature the same binding site(s), aligns them, and examines the superimposed binding sites to determine whether each structure is apo or holo, in reference to the query. The resulting superimposed datasets of apo-holo pairs can be visualized and downloaded for further analysis. AHoJ accepts multiple input queries, allowing the creation of customized apo-holo datasets. AVAILABILITY AND IMPLEMENTATION: Freely available for non-commercial use at http://apoholo.cz. Source code available at https://github.com/cusbg/AHoJ-project. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Ligand binding site prediction from protein structure plays an important role in various complex rational drug design efforts. Its applications include drug side effects prediction, docking prioritization in inverse virtual screening and elucidation of protein function in genome wide structural studies. Currently available tools have limitations that disqualify them from many possible use cases. In general they are either fast and relatively inaccurate (e.g. purely geometric methods) or accurate but too slow for large scale applications (e.g. methods that rely on a large template libraries of known protein-ligand complexes). P2Rank is a recently introduced machine learning based method that have already exhibited speeds comparable to fastest geometric methods while providing much higher identification success rates. Here we present an improved version that brings speed-up as well as higher quality predictions. A leap in predictive performance was achieved thanks to the technique of Bayesian optimization, which allowed simultaneous optimization of numerous arbitrary parameters of the algorithm. We have evaluated our method with respect to various performance and prediction quality criteria and compared it to other state of the art methods, as well as to it's previous version, with encouraging results.