Large-Scale Comparison of Four Binding Site Detection Algorithms.

A large-scale evaluation and comparison of four cavity detection algorithms was carried out. The algorithms SiteFinder, fpocket, PocketFinder, and Site Map were evaluated on a protein test set containing 5416 protein-ligand complexes and 9900 apo forms, corresponding to a subset of the set used earlier for benchmarking the Pocket Finder algorithm. For the holo structures, all four algorithms correctly identified a similar amount of pockets (around 95%). Site Finder, using optimized parameters, Site Map, and fpocket showed similar pocket ranking performance, which was defined by ranking the correct binding site on rank 1 of the predictions or within the first 5 ranks of the predictions. On the apo structures, Pocket Finder especially and also Site Finder (optimized parameters) performed best, identifying 96% and 84% of all binding sites, respectively. The fpocket program predicts binding sites most accurately among the algorithms evaluated here. Site Finder needed an average calculation time of 1.6 s compared with 2 min for Site Map and around 2 s for fpocket.