PepSite: prediction of peptide-binding sites from protein surfaces

Abstract

Complex biological functions emerge through intricate protein-protein interaction networks. An important class of protein-protein interaction corresponds to peptide-mediated interactions, in which a short peptide stretch from one partner interacts with a large protein surface from the other partner. Protein-peptide interactions are typically of low affinity and involved in regulatory mechanisms, dynamically reshaping protein interaction networks. Due to the relatively small interaction surface, modulation of protein-peptide interactions is feasible and highly attractive for therapeutic purposes. Unfortunately, the number of available 3D structures of protein-peptide interfaces is very limited. For typical cases where a protein-peptide structure of interest is not available, the PepSite web server can be used to predict peptide-binding spots from protein surfaces alone. The PepSite method relies on preferred peptide-binding environments calculated from a set of known protein-peptide 3D structures, combined with distance constraints derived from known peptides. We present an updated version of the web server that is orders of magnitude faster than the original implementation, returning results in seconds instead of minutes or hours. The PepSite web server is available at http://pepsite2.russelllab.org.

Figure 1.

Top prediction of an MLL peptide (residues 4–15, RWRFPARP according to UniProt accession Q9Y6P1) bound to a menin structure from N. vectensis (PDB 3RE2, chain A) (38). The menin structure is displayed either as a cartoon (A) or as a surface (B). Image generated with VMD (37).