Understanding and predicting druggability. A high-throughput method for detection of drug binding sites

Abstract

Druggability predictions are important to avoid intractable targets and to focus drug discovery efforts on sites offering better prospects. However, few druggability prediction tools have been released and none has been extensively tested. Here, a set of druggable and nondruggable cavities has been compiled in a collaborative platform ( http://fpocket.sourceforge.net/dcd ) that can be used, contributed, and curated by the community. Druggable binding sites are often oversimplified as closed, hydrophobic cavities, but data set analysis reveals that polar groups in druggable binding sites have properties that enable them to play a decisive role in ligand recognition. Finally, the data set has been used in conjunction with the open source fpocket suite to train and validate a logistic model. State of the art performance was achieved for predicting druggability on known binding sites and on virtual screening experiments where druggable pockets are retrieved from a pool of decoys. The algorithm is free, extremely fast, and can effectively be used to automatically sieve through massive collections of structures ( http://fpocket.sourceforge.net ).