Paper

SiteFerret: beyond simple pocket identification in proteins

We present a novel method for the automatic detection of pockets on protein molecular surfaces. The algorithm is based on an ad hoc hierarchical clustering of virtual SES probe spheres obtained from the geometrical primitives generated by the NanoShaper software. The final ranking of putative pockets is based on the Isolation Forest method, an unsupervised learning approach originally developed for anomaly detection. A detailed importance analysis of pocket features provides insight on which geometrical (clustering) and chemical (residues) properties characterize a good binding site. The method also provides a segmentation of pockets into smaller subpockets. We prove that subpockets are a reliable representation that pinpoint the binding site with greater precision. Site Ferret is outstanding in its versatility, accurately predicting a wide range of binding sites, from small molecules to peptides and difficult shallow sites.

Results in Papers With Code
(↓ scroll down to see all results)