DeeplyTough: Learning Structural Comparison of Protein Binding Sites
Preprint
Abstract
Motivation: Protein binding site comparison (pocket matching) is of importance in drug discovery. Identification of similar binding sites can help guide efforts for hit finding, understanding polypharmacology and characterization of protein function. The design of pocket matching methods has traditionally involved much intuition, and has employed a broad variety of algorithms and representations of the input protein structures. We regard the high heterogeneity of past work and the recent availability of large-scale benchmarks as an indicator that a data-driven approach may provide a new perspective. Results: We propose DeeplyTough, a convolutional neural network that encodes a three-dimensional representation of protein binding sites into descriptor vectors that may be compared efficiently in an alignment-free manner by computing pairwise Euclidean distances. The network is trained with supervision: (i) to provide similar pockets with similar descriptors, (ii) to separate the descriptors of dissimilar pockets by a minimum margin, and (iii) to achieve robustness to nuisance variations. We evaluate our method using three large-scale benchmark datasets, on which it demonstrates excellent performance for held-out data coming from the training distribution and competitive performance when the trained network is required to generalize to datasets constructed independently. Availability: https://github.com/BenevolentAI/DeeplyTough Contact: martin.simonovsky@enpc.fr , joshua.meyers@benevolent.aiKeywords
All Related Versions
- Published version: Journal of Chemical Information and Modeling, 60 (4), 2356.
This publication has 53 references indexed in Scilit:
- An Augmented Pocketome: Detection and Analysis of Small-Molecule Binding Pockets in Proteins of Known 3D StructureStructure, 2018
- End-to-End Differentiable Learning of Protein StructureSSRN Electronic Journal, 2018
- Prediction of Protein Pairs Sharing Common Active Ligands Using Protein Sequence, Structure, and Ligand SimilarityJournal of Chemical Information and Modeling, 2016
- HTMD: High-Throughput Molecular Dynamics for Molecular DiscoveryJournal of Chemical Theory and Computation, 2016
- The Recognition of Identical Ligands by Unrelated ProteinsACS Chemical Biology, 2015
- Graph-Based Clustering of Predicted Ligand-Binding Pockets on Protein SurfacesJournal of Chemical Information and Modeling, 2015
- SiteHopper - a unique tool for binding site comparisonJournal of Cheminformatics, 2014
- What is the relationship between the global structures of apo and holo proteins?Proteins: Structure, Function, and Bioinformatics, 2007
- Fundamentals of Data Mining in Genomics and Proteomics2007
- The Protein Data BankNucleic Acids Research, 2000