PDBspheres - a method for finding 3D similarities in local regions in proteins

We present a structure-based method for finding and evaluating structural similarities in protein regions relevant to ligand binding. PDBspheres comprises an exhaustive library of protein structure regions (spheres) adjacent to complexed ligands derived from the Protein Data Bank (PDB), along with methods to find and evaluate structural matches between a protein of interest and spheres in the library. Currently, PDBspheres library contains more than 2 million spheres, organized to facilitate searches by sequence and/or structure similarity of protein-ligand binding sites or interfaces between interacting molecules. PDBspheres uses the LGA structure alignment algorithm as the main engine for detecting structure similarities between the protein of interest and library spheres. An all-atom structure similarity metric ensures that sidechain placement is taken into account in the PDBspheres primary assessment of confidence in structural matches. In this paper, we (1) describe the PDBspheres method, (2) demonstrate how PDBspheres can be used to detect and characterize binding sites in protein structures, (3) compare PDBspheres use for binding site prediction with seven other binding site prediction methods using a curated dataset of 2,528 ligand-bound and ligand-free crystal structures, and (4) use PDBspheres to cluster pockets and assess structural similarities among protein binding sites of the 4,876 structures in the refined set of PDBbind 2019 dataset. The PDBspheres library is made publicly available for download at https://proteinmodel.org/AS2TS/PDBspheres

Enzyme modification using mutation site prediction method for enhancing the regioselectivity of substrate reaction sites

Enzymes with low regioselectivity of substrate reaction sites may produce multiple products from a single substrate. When a target product is produced industrially using these enzymes, the production of non-target products (byproducts) causes adverse effects such as increased processing costs for purification and the amount of raw material. Thus it is required the development of modified enzymes to reduce the amount of byproducts’ production. In this paper, we report a method called mutation site prediction for enhancing the regioselectivity of substrate reaction sites (MSPER). MSPER takes conformational data for docking poses of an enzyme and a substrate as input and automatically generates a ranked list of mutation sites to destabilize docking poses for byproducts while maintaining those for target products in silico. We applied MSPER to the enzyme cytochrome P450 CYP102A1 (BM3) and the two substrates to enhance the regioselectivity for four target products with different reaction sites. The 13 of the total 14 top-ranked mutation sites predicted by MSPER for the four target products succeeded in selectively enhancing the regioselectivity up to 6.4-fold. The results indicate that MSPER can distinguish differences of substrate structures and the reaction sites, and can accurately predict mutation sites to enhance regioselectivity without selection by directed evolution screening.

ScanNet: An interpretable geometric deep learning model for structure-based protein binding site prediction

Predicting the functional sites of a protein from its structure, such as the binding sites of small molecules, other proteins or antibodies sheds light on its function in vivo. Currently, two classes of methods prevail: Machine Learning (ML) models built on top of handcrafted features and comparative modeling. They are respectively limited by the expressivity of the handcrafted features and the availability of similar proteins. Here, we introduce ScanNet, an end-to-end, interpretable geometric deep learning model that learns features directly from 3D structures. ScanNet builds representations of atoms and amino acids based on the spatio-chemical arrangement of their neighbors. We train ScanNet for detecting protein-protein and protein-antibody binding sites, demonstrate its accuracy - including for unseen protein folds - and interpret the filters learned. Finally, we predict epitopes of the SARS-CoV-2 spike protein, validating known antigenic regions and predicting previously uncharacterized ones. Overall, ScanNet is a versatile, powerful, and interpretable model suitable for functional site prediction tasks. A webserver for ScanNet is available from http://bioinfo3d.cs.tau.ac.il/ScanNet/