Structure-Based Neural Network Protein-Carbohydrate Interaction Predictions at the Residue Level
Preprint
Abstract
Carbohydrates dynamically and transiently interact with proteins for cell-cell recognition, cellular differentiation, immune response, and many other cellular processes. Despite the molecular importance of these interactions, there are currently few reliable computational tools to predict potential carbohydrate binding sites on any given protein. Here, we present two deep learning models named CArbohydrate-Protein interaction Site IdentiFier (CAPSIF) that predict carbohydrate binding sites on proteins: (1) a 3D-UNet voxel-based neural network model (CAPSIF:V) and (2) an equivariant graph neural network model (CAPSIF:G). While both models outperform previous surrogate methods used for carbohydrate binding site prediction, CAPSIF:V performs better than CAPSIF:G, achieving test Dice scores of 0.597 and 0.543 and test set Matthews correlation coefficients (MCCs) of 0.599 and 0.538, respectively. We further tested CAPSIF:V on AlphaFold2-predicted protein structures. CAPSIF:V performed equivalently on both experimentally determined structures and AlphaFold2 predicted structures. Finally, we demonstrate how CAPSIF models can be used in conjunction with local glycan-docking protocols, such as GlycanDock, to predict bound protein-carbohydrate structures.Keywords
This publication has 55 references indexed in Scilit:
- Protein-Carbohydrate Interactions Studied by NMR: From Molecular Recognition to Drug DesignCurrent Protein & Peptide Science, 2012
- Prediction of Carbohydrate Binding Sites on Protein Surfaces with 3-Dimensional Probability Density Distributions of Interacting AtomsPLOS ONE, 2012
- Alternate States of Proteins Revealed by Detailed Energy Landscape MappingJournal of Molecular Biology, 2011
- PyRosetta: a script-based interface for implementing molecular modeling algorithms using RosettaBioinformatics, 2010
- From carbohydrate leads to glycomimetic drugsNature Reviews Drug Discovery, 2009
- Fpocket: An open source platform for ligand pocket detectionBMC Bioinformatics, 2009
- Polysialic Acid-Directed Migration and Differentiation of Neural Precursors Are Essential for Mouse Brain DevelopmentMolecular and Cellular Biology, 2007
- Therapeutic value of glycosaminoglycans in cancerMolecular Cancer Therapeutics, 2006
- The Protein Data BankNucleic Acids Research, 2000
- A simple method for displaying the hydropathic character of a proteinJournal of Molecular Biology, 1982