Highly accurate carbohydrate-binding site prediction with DeepGlycanSite

As the most abundant organic substances in nature, carbohydrates are essential for life. Understanding how carbohydrates regulate proteins in the physiological and pathological processes presents opportunities to address crucial biological problems and develop new therapeutics. However, the diversity and complexity of carbohydrates pose a challenge in experimentally identifying the sites where carbohydrates bind to and act on proteins. Here, we introduce a deep learning model, DeepGlycanSite, capable of accurately predicting carbohydrate-binding sites on a given protein structure. Incorporating geometric and evolutionary features of proteins into a deep equivariant graph neural network with the transformer architecture, DeepGlycanSite remarkably outperforms previous state-of-the-art methods and effectively predicts binding sites for diverse carbohydrates. Integrating with a mutagenesis study, DeepGlycanSite reveals the guanosine-5'-diphosphate-sugar-recognition site of an important G-protein coupled receptor. These findings demonstrate DeepGlycanSite is invaluable for carbohydrate-binding site prediction and could provide insights into molecular mechanisms underlying carbohydrate-regulation of therapeutically important proteins.

A comprehensive review and comparison of existing computational methods for protein function prediction

Protein function prediction is critical for understanding the cellular physiological and biochemical processes, and it opens up new possibilities for advancements in fields such as disease research and drug discovery. During the past decades, with the exponential growth of protein sequence data, many computational methods for predicting protein function have been proposed. Therefore, a systematic review and comparison of these methods are necessary. In this study, we divide these methods into four different categories, including sequence-based methods, 3D structure-based methods, PPI network-based methods and hybrid information-based methods. Furthermore, their advantages and disadvantages are discussed, and then their performance is comprehensively evaluated and compared. Finally, we discuss the challenges and opportunities present in this field.

CarbDisMut: database on neutral and disease-causing mutations in human carbohydrate-binding proteins

Protein-carbohydrate interactions are involved in several cellular and biological functions. Integrating structure and function of carbohydrate-binding proteins with disease-causing mutations help to understand the molecular basis of diseases. Although databases are available for protein-carbohydrate complexes based on structure, binding affinity and function, no specific database for mutations in human carbohydrate-binding proteins is reported in the literature. We have developed a novel database, CarbDisMut, a comprehensive integrated resource for disease-causing mutations with sequence and structural features. It has 1.17 million disease-associated mutations and 38,636 neutral mutations from 7,187 human carbohydrate-binding proteins. The database is freely available at https://web.iitm.ac.in/bioinfo2/carbdismut. The web-site is implemented using HTML, PHP and JavaScript and supports recent versions of all major browsers, such as Firefox, Chrome and Opera.

Structure-based neural network protein-carbohydrate interaction predictions at the residue level

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 (DL) models named CArbohydrate-Protein interaction Site IdentiFier (CAPSIF) that predicts non-covalent 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.

Structure-Based Neural Network Protein-Carbohydrate Interaction Predictions at the Residue Level

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.

Building, Visualizing, and Analyzing Glycosaminoglycan-Protein Interaction Networks

This chapter describes how to generate, visualize, and analyze interaction networks of glycosaminoglycans (GAGs), which are linear polyanionic polysaccharides mostly located at the cell surface and in the extracellular matrix. The protocol is divided into three major steps: (1) the collection of GAG-mediated interaction data, (2) the visualization of GAG interaction networks, and (3) the computational enrichment analyses of these networks to identify their overrepresented features (e.g., protein domains, location, molecular functions, and biological pathways) compared to a reference proteome. These analyses are critical to interpret GAG interactomic datasets, decipher their specificities and functions, and ultimately identify GAG-protein interactions to target for therapeutic purpose.

Investigations on the binding specificity of β-galactoside analogues with human galectin-1 using molecular dynamics simulations

Galectin-1 (Gal-1) is the first member of galectin family, which has a carbohydrate recognition domain, specifically binds towards β-galactoside containing oligosaccharides. Owing its association with carbohydrates, Gal-1 is involved in many biological processes such as cell signaling, adhesion and pathological pathways such as metastasis, apoptosis and increased tumour cell survival. The development of β-galactoside based inhibitors would help to control the Gal-1 expression. In the current study, we carried out molecular dynamics (MD) simulations to examine the structural and dynamic behaviour Gal-1-thiodigalactoside (TDG), Gal-1-lactobionic acid (LBA) and Gal-1-beta-(1→6)-galactobiose (G16G) complexes. The analysis of glycosidic torsional angles revealed that β-galactoside analogues TDG and LBA have a single binding mode (BM1) whereas G16G has two binding modes (BM1 and BM2) for interacting with Gal-1 protein. We have computed the binding free energies for the complexes Gal-1-TDG, Gal-1-LBA and Gal-1-G16G using MM/PBSA and are -6.45, -6.22 and -3.08 kcal/mol, respectively. This trend agrees well with experiments that the binding of Gal-1 with TDG is stronger than LBA. Further analysis revealed that the interactions due to direct and water-mediated hydrogen bonds play a significant role to the structural stability of the complexes. The result obtained from this study is useful to formulate a set of rules and derive pharmacophore-based features for designing inhibitors against galectin-1.Communicated by Ramaswamy H. Sarma.

Multifaceted Computational Modeling in Glycoscience

Glycoscience assembles all the scientific disciplines involved in studying various molecules and macromolecules containing carbohydrates and complex glycans. Such an ensemble involves one of the most extensive sets of molecules in quantity and occurrence since they occur in all microorganisms and higher organisms. Once the compositions and sequences of these molecules are established, the determination of their three-dimensional structural and dynamical features is a step toward understanding the molecular basis underlying their properties and functions. The range of the relevant computational methods capable of addressing such issues is anchored by the specificity of stereoelectronic effects from quantum chemistry to mesoscale modeling throughout molecular dynamics and mechanics and coarse-grained and docking calculations. The Review leads the reader through the detailed presentations of the applications of computational modeling. The illustrations cover carbohydrate-carbohydrate interactions, glycolipids, and N- and O-linked glycans, emphasizing their role in SARS-CoV-2. The presentation continues with the structure of polysaccharides in solution and solid-state and lipopolysaccharides in membranes. The full range of protein-carbohydrate interactions is presented, as exemplified by carbohydrate-active enzymes, transporters, lectins, antibodies, and glycosaminoglycan binding proteins. A final section features a list of 150 tools and databases to help address the many issues of structural glycobioinformatics.

CSM-carbohydrate: protein-carbohydrate binding affinity prediction and docking scoring function

Protein-carbohydrate interactions are crucial for many cellular processes but can be challenging to biologically characterise. To improve our understanding and ability to model these molecular interactions, we used a carefully curated set of 370 protein-carbohydrate complexes with experimental structural and biophysical data in order to train and validate a new tool, cutoff scanning matrix (CSM)-carbohydrate, using machine learning algorithms to accurately predict their binding affinity and rank docking poses as a scoring function. Information on both protein and carbohydrate complementarity, in terms of shape and chemistry, was captured using graph-based structural signatures. Across both training and independent test sets, we achieved comparable Pearson's correlations of 0.72 under cross-validation [root mean square error (RMSE) of 1.58 Kcal/mol] and 0.67 on the independent test (RMSE of 1.72 Kcal/mol), providing confidence in the generalisability and robustness of the final model. Similar performance was obtained across mono-, di- and oligosaccharides, further highlighting the applicability of this approach to the study of larger complexes. We show CSM-carbohydrate significantly outperformed previous approaches and have implemented our method and make all data freely available through both a user-friendly web interface and application programming interface, to facilitate programmatic access at http://biosig.unimelb.edu.au/csm_carbohydrate/. We believe CSM-carbohydrate will be an invaluable tool for helping assess docking poses and the effects of mutations on protein-carbohydrate affinity, unravelling important aspects that drive binding recognition.

Prediction of protein-carbohydrate complex binding affinity using structural features

Protein-carbohydrate interactions play a major role in several cellular and biological processes. Elucidating the factors influencing the binding affinity of protein-carbohydrate complexes and predicting their free energy of binding provide deep insights for understanding the recognition mechanism. In this work, we have collected the experimental binding affinity data for a set of 389 protein-carbohydrate complexes and derived several structure-based features such as contact potentials, interaction energy, number of binding residues and contacts between different types of atoms. Our analysis on the relationship between binding affinity and structural features revealed that the important factors depend on the type of the complex based on number of carbohydrate and protein chains. Specifically, binding site residues, accessible surface area, interactions between various atoms and energy contributions are important to understand the binding affinity. Further, we have developed multiple regression equations for predicting the binding affinity of protein-carbohydrate complexes belonging to six categories of protein-carbohydrate complexes. Our method showed an average correlation and mean absolute error of 0.731 and 1.149 kcal/mol, respectively, between experimental and predicted binding affinities on a jackknife test. We have developed a web server PCA-Pred, Protein-Carbohydrate Affinity Predictor, for predicting the binding affinity of protein-carbohydrate complexes. The web server is freely accessible at https://web.iitm.ac.in/bioinfo2/pcapred/. The web server is implemented using HTML and Python and supports recent versions of major browsers such as Chrome, Firefox, IE10 and Opera.

Three-Dimensional Structures of Carbohydrates and Where to Find Them

Analysis and systematization of accumulated data on carbohydrate structural diversity is a subject of great interest for structural glycobiology. Despite being a challenging task, development of computational methods for efficient treatment and management of spatial (3D) structural features of carbohydrates breaks new ground in modern glycoscience. This review is dedicated to approaches of chemo- and glyco-informatics towards 3D structural data generation, deposition and processing in regard to carbohydrates and their derivatives. Databases, molecular modeling and experimental data validation services, and structure visualization facilities developed for last five years are reviewed.