Protein-ligand Binding Affinity Research Articles

Distance plus attention for binding affinity prediction

Protein-ligand binding affinity plays a pivotal role in drug development, particularly in identifying potential ligands for target disease-related proteins. Accurate affinity predictions can significantly reduce both the time and cost involved in drug development. However, highly precise affinity prediction remains a research challenge. A key to improve affinity prediction is to capture interactions between proteins and ligands effectively. Existing deep-learning-based computational approaches use 3D grids, 4D tensors, molecular graphs, or proximity-based adjacency matrices, which are either resource-intensive or do not directly represent potential interactions. In this paper, we propose atomic-level distance features and attention mechanisms to capture better specific protein-ligand interactions based on donor-acceptor relations, hydrophobicity, and π\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pi $$\\end{document}-stacking atoms. We argue that distances encompass both short-range direct and long-range indirect interaction effects while attention mechanisms capture levels of interaction effects. On the very well-known CASF-2016 dataset, our proposed method, named Distance plus Attention for Affinity Prediction (DAAP), significantly outperforms existing methods by achieving Correlation Coefficient (R) 0.909, Root Mean Squared Error (RMSE) 0.987, Mean Absolute Error (MAE) 0.745, Standard Deviation (SD) 0.988, and Concordance Index (CI) 0.876. The proposed method also shows substantial improvement, around 2% to 37%, on five other benchmark datasets. The program and data are publicly available on the website https://gitlab.com/mahnewton/daap.Scientific Contribution StatementThis study innovatively introducesdistance-based features to predict protein-ligand binding affinity, capitalizing onunique molecular interactions. Furthermore, the incorporation of protein sequencefeatures of specific residues enhances the model’s proficiency in capturing intricatebinding patterns. The predictive capabilities are further strengthened through theuse of a deep learning architecture with attention mechanisms, and an ensembleapproach, averaging the outputs of five models, is implemented to ensure robustand reliable predictions.

Multimodal protein representation learning and target-aware variational auto-encoders for protein-binding ligand generation

Without knowledge of specific pockets, generating ligands based on the global structure of a protein target plays a crucial role in drug discovery as it helps reduce the search space for potential drug-like candidates in the pipeline. However, contemporary methods require optimizing tailored networks for each protein, which is arduous and costly. To address this issue, we introduce TargetVAE, a target-aware variational auto-encoder that generates ligands with desirable properties including high binding affinity and high synthesizability to arbitrary target proteins, guided by a multimodal deep neural network built based on geometric and sequence models, named Protein Multimodal Network (PMN), as the prior for the generative model. PMN unifies different representations of proteins (e.g. primary structure—sequence of amino acids, 3D tertiary structure, and residue-level graph) into a single representation. Our multimodal architecture learns from the entire protein structure and is able to capture their sequential, topological, and geometrical information by utilizing language modeling, graph neural networks, and geometric deep learning. We showcase the superiority of our approach by conducting extensive experiments and evaluations, including predicting protein-ligand binding affinity in the PBDBind v2020 dataset as well as the assessment of generative model quality, ligand generation for unseen targets, and docking score computation. Empirical results demonstrate the promising and competitive performance of our proposed approach. Our software package is publicly available at https://github.com/HySonLab/Ligand_Generation.

Discovery of a novel SHP2 allosteric inhibitor using virtual screening, FMO calculation, and molecular dynamic simulation.

SHP2 is a non-receptor protein tyrosine phosphatase to remove tyrosine phosphorylation. Functionally, SHP2 is an essential bridge to connect numerous oncogenic cell-signaling cascades including RAS-ERK, PI3K-AKT, JAK-STAT, and PD-1/PD-L1 pathways. This study aims to discover novel and potent SHP2 inhibitors using a hierarchical structure-based virtual screening strategy that combines molecular docking and the fragment molecular orbital method (FMO) for calculating binding affinity (referred to as the Dock-FMO protocol). For the SHP2 target, the FMO method prediction has a high correlation between the binding affinity of the protein-ligand interaction and experimental values (R2 = 0.55), demonstrating a significant advantage over the MM/PBSA (R2 = 0.02) and MM/GBSA (R2 = 0.15) methods. Therefore, we employed Dock-FMO virtual screening of ChemDiv database of ∼2,990,000 compounds to identify a novel SHP2 allosteric inhibitor bearing hydroxyimino acetamide scaffold. Experimental validation demonstrated that the new compound (E)-2-(hydroxyimino)-2-phenyl-N-(piperidin-4-ylmethyl)acetamide (7188-0011) effectively inhibited SHP2 in a dose-dependent manner. Molecular dynamics (MD) simulation analysis revealed the binding stability of compound 7188-0011 and the SHP2 protein, along with the key interacting residues in the allosteric binding site. Overall, our work has identified a novel and promising allosteric inhibitor that targets SHP2, providing a new starting point for further optimization to develop more potent inhibitors. All the molecular docking studies were employed to identify potential leads with Maestro v10.1. The protein-ligand binding affinities of potential leads were further predicted by FMO calculations at MP2/6-31G* level using GAMESS v2020 system. MD simulations were carried out with AmberTools18 by applying the FF14SB force field. MD trajectories were analyzed using VMD v1.9.3. MM/GB(PB)SA binding free energy analysis was carried out with the mmpbsa.py tool of AmberTools18. The docking and MD simulation results were visualized through PyMOL v2.5.0.

Purification, structural characterization, and neuroprotective effect of 3,6-diisobutyl-2,5-piperazinedione from Halomonas pacifica CARE-V15 against okadaic acid-inducedneurotoxicity in zebrafish model.

Halomonas pacifica CARE-V15 was isolated from the southeastern coast of India to determine its genome sequence. Secondary metabolite gene clusters were identified using an anti-SMASH server. The concentrated crude ethyl acetate extract was evaluated by GC-MS. The bioactive compound from the crude ethyl acetate extract was fractionated by gel column chromatography. HPLC was used to purify the 3,6-diisobutyl-2,5-piperazinedione (DIP),and the structure was determined using FTIR and NMR spectroscopy. Purified DIP was used in an in silico molecular docking analysis. Purified DIP exhibits a stronger affinity for antioxidant genes like glutathione peroxidase(GPx), glutathione-S-transferase(GST), and glutathione reductase(GSR). Using in silco molecular docking analysis, the protein-ligand binding affinities of GSR (-4.70 kcal/mol), GST (-5.27 kcal/mol), and GPx (-5.37 kcal/mol) were measured. The expression of antioxidant genes were investigated by qRT-PCR. The in vivo reactive oxygen species production, lipid peroxidation, and cell death levels were significantly (p ≤ 0.05) increased in OA-induced group, but all these levels were significantly (p ≤ 0.05) decreased in the purified DIP pretreated group. Purified DIP from halophilic bacteria could thus be a useful treatment for neurological disorders associated with oxidative stress.

Constant-pH Simulations with the Polarizable Atomic Multipole AMOEBA Force Field.

Accurately predicting protein behavior across diverse pH environments remains a significant challenge in biomolecular simulations. Existing constant-pH molecular dynamics (CpHMD) algorithms are limited to fixed-charge force fields, hindering their application to biomolecular systems described by permanent atomic multipoles or induced dipoles. This work overcomes these limitations by introducing the first polarizable CpHMD algorithm in the context of the Atomic Multipole Optimized Energetics for Biomolecular Applications (AMOEBA) force field. Additionally, our implementation in the open-source Force Field X (FFX) software has the unique ability to handle titration state changes for crystalline systems including flexible support for all 230 space groups. The evaluation of constant-pH molecular dynamics (CpHMD) with the AMOEBA force field was performed on 11 crystalline peptide systems that span the titrating amino acids (Asp, Glu, His, Lys, and Cys). Titration states were correctly predicted for 15 out of the 16 amino acids present in the 11 systems, including for the coordination of Zn2+ by cysteines. The lone exception was for a HIS-ALA peptide where CpHMD predicted both neutral histidine tautomers to be equally populated, whereas the experimental model did not consider multiple conformers and diffraction data are unavailable for rerefinement. This work demonstrates the promise polarizable CpHMD simulations for pKa predictions, the study of biochemical mechanisms such as the catalytic triad of proteases, and for improved protein-ligand binding affinity accuracy in the context of pharmaceutical lead optimization.

Enhancing Generalizability in Protein-Ligand Binding Affinity Prediction with Multimodal Contrastive Learning.

Improving the generalization ability of scoring functions remains a major challenge in protein-ligand binding affinity prediction. Many machine learning methods are limited by their reliance on single-modal representations, hindering a comprehensive understanding of protein-ligand interactions. We introduce a graph-neural-network-based scoring function that utilizes a triplet contrastive learning loss to improve protein-ligand representations. In this model, three-dimensional complex representations and the fusion of two-dimensional ligand and coarse-grained pocket representations converge while distancing from decoy representations in latent space. After rigorous validation on multiple external data sets, our model exhibits commendable generalization capabilities compared to those of other deep learning-based scoring functions, marking it as a promising tool in the realm of drug discovery. In the future, our training framework can be extended to other biophysical- and biochemical-related problems such as protein-protein interaction and protein mutation prediction.

Enhancing Protein-Ligand Binding Affinity Predictions Using Neural Network Potentials.

This letter gives results on improving protein-ligand binding affinity predictions based on molecular dynamics simulations using machine learning potentials with a hybrid neural network potential and molecular mechanics methodology (NNP/MM). We compute relative binding free energies with the Alchemical Transfer Method and validate its performance against established benchmarks and find significant enhancements compared with conventional MM force fields like GAFF2.

GraphLambda: Fusion Graph Neural Networks for Binding Affinity Prediction.

Predicting the binding affinity of protein-ligand complexes is crucial for computer-aided drug discovery (CADD) and the identification of potential drug candidates. The deep learning-based scoring functions have emerged as promising predictors of binding constants. Building on recent advancements in graph neural networks, we present graphLambda for protein-ligand binding affinity prediction, which utilizes graph convolutional, attention, and isomorphism blocks to enhance the predictive capabilities. The graphLambda model exhibits superior performance across CASF16 and CSAR HiQ NRC benchmarks and demonstrates robustness with respect to different types of train-validation set partitions. The development of graphLambda underscores the potential of graph neural networks in advancing binding affinity prediction models, contributing to more effective CADD methodologies.

An ensemble-based approach to estimate confidence of predicted protein-ligand binding affinity values.

When designing a machine learning-based scoring function, we access a limited number of protein-ligand complexes with experimentally determined binding affinity values, representing only a fraction of all possible protein-ligand complexes. Consequently, it is crucial to report a measure of confidence and quantify the uncertainty in the model's predictions during test time. Here, we adopt the conformal prediction technique to evaluate the confidence of a prediction for each member of the core set of the CASF 2016 benchmark. The conformal prediction technique requires a diverse ensemble of predictors for uncertainty estimation. To this end, we introduce ENS-Score as an ensemble predictor, which includes 30 models with different protein-ligand representation approaches and achieves Pearson's correlation of 0.842 on the core set of the CASF 2016 benchmark. Also, we comprehensively investigate the residual error of each data point to assess the normality behavior of the distribution of the residual errors and their correlation to the structural features of the ligands, such as hydrophobic interactions and halogen bonding. In the end, we provide a local host web application to facilitate the usage of ENS-Score. All codes to repeat results are provided at https://github.com/miladrayka/ENS_Score.

Machine Learning Methods as a Cost-Effective Alternative to Physics-Based Binding Free Energy Calculations.

The rank ordering of ligands remains one of the most attractive challenges in drug discovery. While physics-based in silico binding affinity methods dominate the field, they still have problems, which largely revolve around forcefield accuracy and sampling. Recent advances in machine learning have gained traction for protein-ligand binding affinity predictions in early drug discovery programs. In this article, we perform retrospective binding free energy evaluations for 172 compounds from our internal collection spread over four different protein targets and five congeneric ligand series. We compared multiple state-of-the-art free energy methods ranging from physics-based methods with different levels of complexity and conformational sampling to state-of-the-art machine-learning-based methods that were available to us. Overall, we found that physics-based methods behaved particularly well when the ligand perturbations were made in the solvation region, and they did not perform as well when accounting for large conformational changes in protein active sites. On the other end, machine-learning-based methods offer a good cost-effective alternative for binding free energy calculations, but the accuracy of their predictions is highly dependent on the experimental data available for training the model.

SQM2.20: Semiempirical quantum-mechanical scoring function yields DFT-quality protein–ligand binding affinity predictions in minutes

Accurate estimation of protein–ligand binding affinity is the cornerstone of computer-aided drug design. We present a universal physics-based scoring function, named SQM2.20, addressing key terms of binding free energy using semiempirical quantum-mechanical computational methods. SQM2.20 incorporates the latest methodological advances while remaining computationally efficient even for systems with thousands of atoms. To validate it rigorously, we have compiled and made available the PL-REX benchmark dataset consisting of high-resolution crystal structures and reliable experimental affinities for ten diverse protein targets. Comparative assessments demonstrate that SQM2.20 outperforms other scoring methods and reaches a level of accuracy similar to much more expensive DFT calculations. In the PL-REX dataset, it achieves excellent correlation with experimental data (average R2 = 0.69) and exhibits consistent performance across all targets. In contrast to DFT, SQM2.20 provides affinity predictions in minutes, making it suitable for practical applications in hit identification or lead optimization.

Geometry-complete perceptron networks for 3D molecular graphs.

The field of geometric deep learning has recently had a profound impact on several scientific domains such as protein structure prediction and design, leading to methodological advancements within and outside of the realm of traditional machine learning. Within this spirit, in this work, we introduce GCPNet, a new chirality-aware SE(3)-equivariant graph neural network designed for representation learning of 3D biomolecular graphs. We show that GCPNet, unlike previous representation learning methods for 3D biomolecules, is widely applicable to a variety of invariant or equivariant node-level, edge-level, and graph-level tasks on biomolecular structures while being able to (1) learn important chiral properties of 3D molecules and (2) detect external force fields. Across four distinct molecular-geometric tasks, we demonstrate that GCPNet's predictions (1) for protein-ligand binding affinity achieve a statistically significant correlation of 0.608, more than 5%, greater than current state-of-the-art methods; (2) for protein structure ranking achieve statistically significant target-local and dataset-global correlations of 0.616 and 0.871, respectively; (3) for Newtownian many-body systems modeling achieve a task-averaged mean squared error less than 0.01, more than 15% better than current methods; and (4) for molecular chirality recognition achieve a state-of-the-art prediction accuracy of 98.7%, better than any other machine learning method to date. The source code, data, and instructions to train new models or reproduce our results are freely available at https://github.com/BioinfoMachineLearning/GCPNet.

Improving structure-based protein-ligand affinity prediction by graph representation learning and ensemble learning.

Predicting protein-ligand binding affinity presents a viable solution for accelerating the discovery of new lead compounds. The recent widespread application of machine learning approaches, especially graph neural networks, has brought new advancements in this field. However, some existing structure-based methods treat protein macromolecules and ligand small molecules in the same way and ignore the data heterogeneity, potentially leading to incomplete exploration of the biochemical information of ligands. In this work, we propose LGN, a graph neural network-based fusion model with extra ligand feature extraction to effectively capture local features and global features within the protein-ligand complex, and make use of interaction fingerprints. By combining the ligand-based features and interaction fingerprints, LGN achieves Pearson correlation coefficients of up to 0.842 on the PDBbind 2016 core set, compared to 0.807 when using the features of complex graphs alone. Finally, we verify the rationalization and generalization of our model through comprehensive experiments. We also compare our model with state-of-the-art baseline methods, which validates the superiority of our model. To reduce the impact of data similarity, we increase the robustness of the model by incorporating ensemble learning.

Binding Free Energy Calculation Based on the Fragment Molecular Orbital Method and Its Application in Designing Novel SHP-2 Allosteric Inhibitors.

The accurate prediction of binding free energy is a major challenge in structure-based drug design. Quantum mechanics (QM)-based approaches show promising potential in predicting ligand-protein binding affinity by accurately describing the behavior and structure of electrons. However, traditional QM calculations face computational limitations, hindering their practical application in drug design. Nevertheless, the fragment molecular orbital (FMO) method has gained widespread application in drug design due to its ability to reduce computational costs and achieve efficient ab initio QM calculations. Although the FMO method has demonstrated its reliability in calculating the gas phase potential energy, the binding of proteins and ligands also involves other contributing energy terms, such as solvent effects, the 'deformation energy' of a ligand's bioactive conformations, and entropy. Particularly in cases involving ionized fragments, the calculation of solvation free energy becomes particularly crucial. We conducted an evaluation of some previously reported implicit solvent methods on the same data set to assess their potential for improving the performance of the FMO method. Herein, we develop a new QM-based binding free energy calculation method called FMOScore, which enhances the performance of the FMO method. The FMOScore method incorporates linear fitting of various terms, including gas-phase potential energy, deformation energy, and solvation free energy. Compared to other widely used traditional prediction methods such as FEP+, MM/PBSA, MM/GBSA, and Autodock vina, FMOScore showed good performance in prediction accuracies. By constructing a retrospective case study, it was observed that incorporating calculations for solvation free energy and deformation energy can further enhance the precision of FMO predictions for binding affinity. Furthermore, using FMOScore-guided lead optimization against Src homology-2-containing protein tyrosine phosphatase 2 (SHP-2), we discovered a novel and potent allosteric SHP-2 inhibitor (compound 8).

Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures.

Inductive bias in machine learning (ML) is the set of assumptions describing how a model makes predictions. Different ML-based methods for protein-ligand binding affinity (PLA) prediction have different inductive biases, leading to different levels of generalization capability and interpretability. Intuitively, the inductive bias of an ML-based model for PLA prediction should fit in with biological mechanisms relevant for binding to achieve good predictions with meaningful reasons. To this end, we propose an interaction-based inductive bias to restrict neural networks to functions relevant for binding with two assumptions: (1) A protein-ligand complex can be naturally expressed as a heterogeneous graph with covalent and non-covalent interactions; (2) The predicted PLA is the sum of pairwise atom-atom affinities determined by non-covalent interactions. The interaction-based inductive bias is embodied by an explainable heterogeneous interaction graph neural network (EHIGN) for explicitly modeling pairwise atom-atom interactions to predict PLA from 3D structures. Extensive experiments demonstrate that EHIGN achieves better generalization capability than other state-of-the-art ML-based baselines in PLA prediction and structure-based virtual screening. More importantly, comprehensive analyses of distance-affinity, pose-affinity, and substructure-affinity relations suggest that the interaction-based inductive bias can guide the model to learn atomic interactions that are consistent with physical reality. As a case study to demonstrate practical usefulness, our method is tested for predicting the efficacy of Nirmatrelvir against SARS-CoV-2 variants. EHIGN successfully recognizes the changes in the efficacy of Nirmatrelvir for different SARS-CoV-2 variants with meaningful reasons.

Exploring protein-ligand binding affinity prediction with electron density-based geometric deep learning.

Rational structure-based drug design relies on accurate predictions of protein-ligand binding affinity from structural molecular information. Although deep learning-based methods for predicting binding affinity have shown promise in computational drug design, certain approaches have faced criticism for their potential to inadequately capture the fundamental physical interactions between ligands and their macromolecular targets or for being susceptible to dataset biases. Herein, we propose to include bond-critical points based on the electron density of a protein-ligand complex as a fundamental physical representation of protein-ligand interactions. Employing a geometric deep learning model, we explore the usefulness of these bond-critical points to predict absolute binding affinities of protein-ligand complexes, benchmark model performance against existing methods, and provide a critical analysis of this new approach. The models achieved root-mean-squared errors of 1.4-1.8 log units on the PDBbind dataset, and 1.0-1.7 log units on the PDE10A dataset, not indicating significant advantages over benchmark methods, and thus rendering the utility of electron density for deep learning models context-dependent. The relationship between intermolecular electron density and corresponding binding affinity was analyzed, and Pearson correlation coefficients r > 0.7 were obtained for several macromolecular targets.

Equivariant Line Graph Neural Network for Protein-Ligand Binding Affinity Prediction.

Binding affinity prediction of three-dimensional (3D) protein-ligand complexes is critical for drug repositioning and virtual drug screening. Existing approaches usually transform a 3D protein-ligand complex to a two-dimensional (2D) graph, and then use graph neural networks (GNNs) to predict its binding affinity. However, the node and edge features of the 2D graph are extracted based on invariant local coordinate systems of the 3D complex. As a result, these approaches can not fully learn the global information of the complex, such as the physical symmetry and the topological information of bonds. To address these issues, we propose a novel Equivariant Line Graph Network (ELGN) for binding affinity prediction of 3D protein-ligand complexes. The proposed ELGN firstly adds a super node to the 3D complex, and then builds a line graph based on the 3D complex. After that, ELGN uses a new E(3)-equivariant network layer to pass the messages between nodes and edges based on the global coordinate system of the 3D complex. Experimental results on two real datasets demonstrate the effectiveness of ELGN over several state-of-the-art baselines.

SadNet: a novel multimodal fusion network for protein-ligand binding affinity prediction.

Protein-ligand binding affinity prediction plays an important role in the field of drug discovery. Existing deep learning-based approaches have significantly improved the efficiency of protein-ligand binding affinity prediction through their excellent inductive bias capability. However, these methods only focus on fragmented three-dimensional data, which truncates the integrity of pocket data, leading to the neglect of potential long-range interactions. In this paper, we propose a dual-stream framework, with amino acid sequence assisting the atomic data fusion for graph neural network (termed SadNet), to fuse both 3D atomic data and sequence data for more accurate prediction results. In detail, SadNet consists of a pocket module and a sequence module. The sequence module expands the "receptive field" of the pocket module through a mid-term virtual node fusion. To better integrate sequence-level information from the sequence module and 3D structural information from the pocket module, we incorporate structural information for each amino acid within the sequence module. Besides, to better understand the intrinsic relationship between sequences and 3D atomic information, our SadNet utilizes information stacking from both the early stage and later stage. Experimental results on publicly available benchmark datasets demonstrate the superiority of the proposed dual-stream approach over the state-of-the-art alternatives. The code of this work is available online at https://github.com/wardhong/SadNet.

Structure-Aware Graph Attention Diffusion Network for Protein-Ligand Binding Affinity Prediction.

Accurate prediction of protein-ligand binding affinities can significantly advance the development of drug discovery. Several graph neural network (GNN)-based methods learn representations of protein-ligand complexes via modeling intermolecule interactions and spatial structures (e.g., distances and angles) of complexes. However, these methods fail to emphasize the importance of bonds and learn hierarchical structures of complexes, which are significant for binding affinity prediction. In this article, we propose the structure-aware graph attention diffusion network (SGADN) to incorporate both distance and angle information for efficient spatial structure learning. We model complexes as line graphs with distance and angle information, focusing on bonds as nodes. Then we perform line graph attention diffusion layers (LGADLs) on line graphs to explore long-range bond node interactions and enhance spatial structure learning. Furthermore, we propose an attentive pooling layer (APL) to refine the hierarchical structures in complexes. Extensive experimental studies on two benchmarks demonstrate the superiority of SGADN for binding affinity prediction.

Decision tree-based identification of important molecular fragments for protein-ligand binding.

Fragment-based drug design is an emerging technology in pharmaceutical research and development. One of the key aspects of this technology is the identification and quantitative characterization of molecular fragments. This study presents a strategy for identifying important molecular fragments based on molecular fingerprints and decision tree algorithms and verifies its feasibility in predicting protein-ligand binding affinity. Specifically, the three-dimensional (3D) structures of protein-ligand complexes are encoded using extended-connectivity fingerprints (ECFP), and three decision tree models, namely Random Forest, XGBoost, and LightGBM, are used to quantitatively characterize the feature importance, thereby extracting important molecular fragments with high reliability. Few-shot learning reveals that the extracted molecular fragments contribute significantly and consistently to the binding affinity even with a small sample size. Despite the absence of location and distance information for molecular fragments in ECFP, 3D visualization, in combination with the reverse ECFP process, shows that the majority of the extracted fragments are located at the binding interface of the protein and the ligand. This alignment with the distance constraints critical for binding affinity further supports the reliability of the strategy for identifying important molecular fragments.