Protein-protein Binding Affinity Research Articles

MuToN Quantifies Binding Affinity Changes upon Protein Mutations by Geometric Deep Learning.

Assessing changes in protein-protein binding affinity due to mutations helps understanding a wide range of crucial biological processes within cells. Despite significant efforts to create accurate computational models, predicting how mutations affect affinity remains challenging due to the complexity of the biological mechanisms involved. In the present work, a geometric deep learning framework called MuToN is introduced for quantifying protein binding affinity change upon residue mutations. The method, designed with geometric attention networks, is mechanism-aware. It captures changes in the protein binding interfaces of mutated complexes and assesses the allosteric effects of amino acids. Experimental results highlight MuToN's superiority compared to existing methods. Additionally, MuToN's flexibility and effectiveness are illustrated by its precise predictions of binding affinity changes between SARS-CoV-2 variants and the ACE2 complex.

Classifying Protein-Protein Binding Affinity with Free-Energy Calculations and Machine Learning Approaches.

Understanding the intricate phenomenon of neuronal wiring in the brain is of great interest in neuroscience. In the fruit fly, Drosophila melanogaster, the Dpr-DIP interactome has been identified to play an important role in this process. However, experimental data suggest that a merely limited subset of complexes, essentially 57 out of a total of 231, exhibit strong binding affinity. In this work, we sought to identify the residue-level molecular basis underlying the difference in binding affinity using a state-of-the-art methodology consisting of standard binding free-energy calculations with a geometrical route and machine learning (ML) techniques. We determined the binding affinity for two complexes using statistical mechanics simulations, achieving an excellent reproduction of the experimental data. Moreover, we predicted the binding free energy for two additional low-affinity complexes, devoid of experimental estimation, while simultaneously identifying key residues for the binding. Furthermore, through the use of ML algorithms, linear discriminant analysis, and random forest, we achieved remarkable accuracy, as high as 0.99, in discerning between strong (cognate) and weak (noncognate) binders. The presented ML approach encompasses easily transferable input features, enabling its broad application to any interactome while facilitating the identification of pivotal residues critical for binding interactions. The predictive power of the generated model was probed on similar protein families from 13 diverse species. Our ML model exhibited commendable performance on these additional data sets, showcasing its reliability and robustness across the species barrier.

Software for Predicting Binding Free Energy of Protein-Protein Complexes and Their Mutants.

Protein-protein binding affinity prediction is important for understanding complex biochemical pathways and to uncover protein interaction networks. Quantitative estimation of the binding affinity changes caused by mutations can provide critical information for protein function annotation and genetic disease diagnoses. The binding free energies of protein-protein complexes can be predicted using several computational tools. This chapter is a summary of software developed for the prediction of binding free energies for protein-protein complexes and their mutants.

Systematic investigation of machine learning on limited data: A study on predicting protein-protein binding strength

The application of machine learning techniques in biological research, especially when dealing with limited data availability, poses significant challenges. In this study, we leveraged advancements in method development for predicting protein-protein binding strength to conduct a systematic investigation into the application of machine learning on limited data. The binding strength, quantitatively measured as binding affinity, is vital for understanding the processes of recognition, association, and dysfunction that occur within protein complexes. By incorporating transfer learning, integrating domain knowledge, and employing both deep learning and traditional machine learning algorithms, we mitigated the impact of data limitations and made significant advancements in predicting protein-protein binding affinity. In particular, we developed over 20 models, ultimately selecting three representative best-performing ones that belong to distinct categories. The first model is structure-based, consisting of a random forest regression and thirteen handcrafted features. The second model is sequence-based, employing an architecture that combines transferred embedding features with a multilayer perceptron. Finally, we created an ensemble model by averaging the predictions of the two aforementioned models. The comparison with other predictors on three independent datasets confirms the significant improvements achieved by our models in predicting protein-protein binding affinity. The programs for running these three models are available at https://github.com/minghuilab/BindPPI.

A Rigorous Framework for Calculating Protein-Protein Binding Affinities in Membranes.

Calculating the binding free energy of integral transmembrane (TM) proteins is crucial for understanding the mechanisms by which they recognize one another and reversibly associate. The glycophorin A (GpA) homodimer, composed of two α-helical segments, has long served as a model system for studying TM protein reversible association. The present work establishes a methodological framework for calculating the binding affinity of the GpA homodimer in the heterogeneous environment of a membrane. Our investigation carefully considered a variety of protocols, including the appropriate choice of the force field, rigorous standardization reflecting the experimental conditions, sampling algorithm, anisotropic environment, and collective variables, to accurately describe GpA dimerization via molecular dynamics-based approaches. Specifically, two strategies were explored: (i) an unrestrained potential mean force (PMF) calculation, which merely enhances sampling along the separation of the two binding partners without any restraint, and (ii) a so-called "geometrical route", whereby the α-helices are progressively separated with imposed restraints on their orientational, positional, and conformational degrees of freedom to accelerate convergence. Our simulations reveal that the simplified, unrestrained PMF approach is inadequate for the description of GpA dimerization. Instead, the geometrical route, tailored specifically to GpA in a membrane environment, yields excellent agreement with experimental data within a reasonable computational time. A dimerization free energy of -10.7 kcal/mol is obtained, in fairly good agreement with available experimental data. The geometrical route further helps elucidate how environmental forces drive association before helical interactions stabilize it. Our simulations also brought to light a distinct, long-lived spatial arrangement that potentially serves as an intermediate state during dimer formation. The methodological advances in the generalized geometrical route provide a powerful tool for accurate and efficient binding-affinity calculations of intricate TM protein complexes in inhomogeneous environments.

Quantification of biases in predictions of protein-protein binding affinity changes upon mutations.

Understanding the impact of mutations on protein-protein binding affinity is a key objective for a wide range of biotechnological applications and for shedding light on disease-causing mutations, which are often located at protein-protein interfaces. Over the past decade, many computational methods using physics-based and/or machine learning approaches have been developed to predict how protein binding affinity changes upon mutations. They all claim to achieve astonishing accuracy on both training and test sets, with performances on standard benchmarks such as SKEMPI 2.0 that seem overly optimistic. Here we benchmarked eight well-known and well-used predictors and identified their biases and dataset dependencies, using not only SKEMPI 2.0 as a test set but also deep mutagenesis data on the severe acute respiratory syndrome coronavirus 2 spike protein in complex with the human angiotensin-converting enzyme 2. We showed that, even though most of the tested methods reach a significant degree of robustness and accuracy, they suffer from limited generalizability properties and struggle to predict unseen mutations. Interestingly, the generalizability problems are more severe for pure machine learning approaches, while physics-based methods are less affected by this issue. Moreover, undesirable prediction biases toward specific mutation properties, the most marked being toward destabilizing mutations, are also observed and should be carefully considered by method developers. We conclude from our analyses that there is room for improvement in the prediction models and suggest ways to check, assess and improve their generalizability and robustness.

Solvated interaction energy: from small-molecule to antibody drug design.

Scoring functions are ubiquitous in structure-based drug design as an aid to predicting binding modes and estimating binding affinities. Ideally, a scoring function should be broadly applicable, obviating the need to recalibrate and refit its parameters for every new target and class of ligands. Traditionally, drugs have been small molecules, but in recent years biologics, particularly antibodies, have become an increasingly important if not dominant class of therapeutics. This makes the goal of having a transferable scoring function, i.e., one that spans the range of small-molecule to protein ligands, even more challenging. One such broadly applicable scoring function is the Solvated Interaction Energy (SIE), which has been developed and applied in our lab for the last 15years, leading to several important applications. This physics-based method arose from efforts to understand the physics governing binding events, with particular care given to the role played by solvation. SIE has been used by us and many independent labs worldwide for virtual screening and discovery of novel small-molecule binders or optimization of known drugs. Moreover, without any retraining, it is found to be transferrable to predictions of antibody-antigen relative binding affinities and as accurate as functions trained on protein-protein binding affinities. SIE has been incorporated in conjunction with other scoring functions into ADAPT (Assisted Design of Antibody and Protein Therapeutics), our platform for affinity modulation of antibodies. Application of ADAPT resulted in the optimization of several antibodies with 10-to-100-fold improvements in binding affinity. Further applications included broadening the specificity of a single-domain antibody to be cross-reactive with virus variants of both SARS-CoV-1 and SARS-CoV-2, and the design of safer antibodies by engineering of a pH switch to make them more selective towards acidic tumors while sparing normal tissues at physiological pH.

AREA-AFFINITY: A Web Server for Machine Learning-Based Prediction of Protein-Protein and Antibody-Protein Antigen Binding Affinities.

Protein-Protein binding affinity reflects the binding strength between the binding partners. The prediction of protein-protein binding affinity is important for elucidating protein functions and also for designing protein-based therapeutics. The geometric characteristics such as area (both interface and surface areas) in the structure of a protein-protein complex play an important role in determining protein-protein interactions and their binding affinity. Here, we present a free web server for academic use, AREA-AFFINITY, for prediction of protein-protein or antibody-protein antigen binding affinity based on interface and surface areas in the structure of a protein-protein complex. AREA-AFFINITY implements 60 effective area-based protein-protein affinity predictive models and 37 effective area-based models specific for antibody-protein antigen binding affinity prediction developed in our recent studies. These models take into consideration the roles of interface and surface areas in binding affinity by using areas classified according to different amino acid types with different biophysical nature. The models with the best performances integrate machine learning methods such as neural network or random forest. These newly developed models have superior or comparable performance compared to the commonly used existing methods. AREA-AFFINITY is available for free at: https://affinity.cuhk.edu.cn/.

DGCddG: Deep Graph Convolution for Predicting Protein-Protein Binding Affinity Changes Upon Mutations.

Effectively and accurately predicting the effects of interactions between proteins after amino acid mutations is a key issue for understanding the mechanism of protein function and drug design. In this study, we present a deep graph convolution (DGC) network-based framework, DGCddG, to predict the changes of protein-protein binding affinity after mutation. DGCddG incorporates multi-layer graph convolution to extract a deep, contextualized representation for each residue of the protein complex structure. The mined channels of the mutation sites by DGC is then fitted to the binding affinity with a multi-layer perceptron. Experiments with results on multiple datasets show that our model can achieve relatively good performance for both single and multi-point mutations. For blind tests on datasets related to angiotensin-converting enzyme 2 binding with the SARS-CoV-2 virus, our method shows better results in predicting ACE2 changes, may help in finding favorable antibodies. Code and data availability: https://github.com/lennylv/DGCddG.

Atomic-level thermodynamics analysis of the binding free energy of SARS-CoV-2 neutralizing antibodies.

Understanding how protein-protein binding affinity is determined from molecular interactions at the interface is essential in developing protein therapeutics such as antibodies, but this has not yet been fully achieved. Among the major difficulties are the facts that it is generally difficult to decompose thermodynamic quantities into contributions from individual molecular interactions and that the solvent effect-dehydration penalty-must also be taken into consideration for every contact formation at the binding interface. Here, we present an atomic-level thermodynamics analysis that overcomes these difficulties and illustrate its utility through application to SARS-CoV-2 neutralizing antibodies. Our analysis is based on the direct interaction energy computed from simulated antibody-protein complex structures and on the decomposition of solvation free energy change upon complex formation. We find that the formation of a single contact such as a hydrogen bond at the interface barely contributes to binding free energy due to the dehydration penalty. On the other hand, the simultaneous formation of multiple contacts between two interface residues favorably contributes to binding affinity. This is because the dehydration penalty is significantly alleviated: the total penalty for multiple contacts is smaller than a sum of what would be expected for individual dehydrations of those contacts. Our results thus provide a new perspective for designing protein therapeutics of improved binding affinity.

Entropic Overcompensation of the N501Y Mutation on SARS-CoV-2 S Binding to ACE2.

Recent experimental work has shown that the N501Y mutation in the SARS-CoV-2 S glycoprotein's receptor binding domain (RBD) increases binding affinity to the angiotensin-converting enzyme 2 (ACE2), primarily by overcompensating for a less favorable enthalpy of binding by greatly reducing the entropic penalty for complex formation, but the basis for this entropic overcompensation is not clear [Prévost et al. J. Biol. Chem.2021, 297, 101151]. We use all-atom molecular dynamics simulations and free-energy calculations to qualitatively assess the impact of the N501Y mutation on the enthalpy and entropy of binding of RBD to ACE2. Our calculations correctly predict that N501Y causes a less favorable enthalpy of binding to ACE2 relative to the original strain. Furthermore, we show that this is overcompensated for by a more entropically favorable increase in large-scale quaternary flexibility and intraprotein root mean square fluctuations of residue positions upon binding in both RBD and ACE2. The enhanced quaternary flexibility stems from N501Y's ability to remodel the inter-residue interactions between the two proteins away from interactions central to the epitope and toward more peripheral interactions. These findings suggest that an important factor in determining protein-protein binding affinity is the degree to which fluctuations are distributed throughout the complex and that residue mutations that may seem to result in weaker interactions than their wild-type counterparts may yet result in increased binding affinity thanks to their ability to suppress unfavorable entropy changes upon binding.

Machine learning methods for protein-protein binding affinity prediction in protein design.

Protein-protein interactions govern a wide range of biological activity. A proper estimation of the protein-protein binding affinity is vital to design proteins with high specificity and binding affinity toward a target protein, which has a variety of applications including antibody design in immunotherapy, enzyme engineering for reaction optimization, and construction of biosensors. However, experimental and theoretical modelling methods are time-consuming, hinder the exploration of the entire protein space, and deter the identification of optimal proteins that meet the requirements of practical applications. In recent years, the rapid development in machine learning methods for protein-protein binding affinity prediction has revealed the potential of a paradigm shift in protein design. Here, we review the prediction methods and associated datasets and discuss the requirements and construction methods of binding affinity prediction models for protein design.

Multiscale Modeling of Hepatitis B Virus Capsid Assembly and Its Dimorphism.

Hepatitis B virus (HBV) is an endemic, chronic virus that leads to 800000 deaths per year. Central to the HBV lifecycle, the viral core has a protein capsid assembled from many copies of a single protein. The capsid protein adopts different (quasi-equivalent) conformations to form icosahedral capsids containing 180 or 240 proteins: T = 3 or T = 4, respectively, in Caspar-Klug nomenclature. HBV capsid assembly has become an important target for recently developed antivirals; nonetheless, the assembly pathways and mechanisms that control HBV dimorphism remain unclear. We describe computer simulations of the HBV assembly, using a coarse-grained model that has parameters learned from all-atom molecular dynamics simulations of a complete HBV capsid and yet is computationally tractable. Dynamical simulations with the resulting model reproduce experimental observations of HBV assembly pathways and products. By constructing Markov state models and employing transition path theory, we identify pathways leading to T = 3, T = 4, and other experimentally observed capsid morphologies. The analysis shows that capsid polymorphism is promoted by the low HBV capsid bending modulus, where the key factors controlling polymorphism are the conformational energy landscape and protein-protein binding affinities.

Hom-Complex-Based Machine Learning (HCML) for the Prediction of Protein-Protein Binding Affinity Changes upon Mutation.

Protein-protein interactions (PPIs) are involved in almost all biological processes in the cell. Understanding protein-protein interactions holds the key for the understanding of biological functions, diseases and the development of therapeutics. Recently, artificial intelligence (AI) models have demonstrated great power in PPIs. However, a key issue for all AI-based PPI models is efficient molecular representations and featurization. Here, we propose Hom-complex-based PPI representation, and Hom-complex-based machine learning models for the prediction of PPI binding affinity changes upon mutation, for the first time. In our model, various Hom complexes Hom(G1, G) can be generated for the graph representation G of protein-protein complex by using different graphs G1, which reveal G1-related inner connections within the graph representation G of protein-protein complex. Further, for a specific graph G1, a series of nested Hom complexes are generated to give a multiscale characterization of the PPIs. Its persistent homology and persistent Euler characteristic are used as molecular descriptors and further combined with the machine learning model, in particular, gradient boosting tree (GBT). We systematically test our model on the two most-commonly used data sets, that is, SKEMPI and AB-Bind. It has been found that our model outperforms all the existing models as far as we know, which demonstrates the great potential of our model for the analysis of PPIs. Our model can be used for the analysis and design of efficient antibodies for SARS-CoV-2.

Ppdx: Automated modeling of protein–protein interaction descriptors for use with machine learning

This paper describes ppdx, a python workflow tool that combines protein sequence alignment, homology modeling, and structural refinement, to compute a broad array of descriptors for characterizing protein-protein interactions. The descriptors can be used to predict various properties of interest, such as protein-protein binding affinities, or inhibitory concentrations (IC50 ), using approaches that range from simple regression to more complex machine learning models. The software is highly modular. It supports different protocols for generating structures, and 95 descriptors can be currently computed. More protocols and descriptors can be easily added. The implementation is highly parallel and can fully exploit the available cores in a single workstation, or multiple nodes on a supercomputer, allowing many systems to be analyzed simultaneously. As an illustrative application, ppdx is used to parametrize a model that predicts the IC50 of a set of antigens and a class of antibodies directed to the influenza hemagglutinin stalk.

On the Rapid Calculation of Binding Affinities for Antigen and Antibody Design and Affinity Maturation Simulations.

The accurate and efficient calculation of protein-protein binding affinities is an essential component in antibody and antigen design and optimization, and in computer modeling of antibody affinity maturation. Such calculations remain challenging despite advances in computer hardware and algorithms, primarily because proteins are flexible molecules, and thus, require explicit or implicit incorporation of multiple conformational states into the computational procedure. The astronomical size of the amino acid sequence space further compounds the challenge by requiring predictions to be computed within a short time so that many sequence variants can be tested. In this study, we compare three classes of methods for antibody/antigen (Ab/Ag) binding affinity calculations: (i) a method that relies on the physical separation of the Ab/Ag complex in equilibrium molecular dynamics (MD) simulations, (ii) a collection of 18 scoring functions that act on an ensemble of structures created using homology modeling software, and (iii) methods based on the molecular mechanics-generalized Born surface area (MM-GBSA) energy decomposition, in which the individual contributions of the energy terms are scaled to optimize agreement with the experiment. When applied to a set of 49 antibody mutations in two Ab/HIV gp120 complexes, all of the methods are found to have modest accuracy, with the highest Pearson correlations reaching about 0.6. In particular, the most computationally intensive method, i.e., MD simulation, did not outperform several scoring functions. The optimized energy decomposition methods provided marginally higher accuracy, but at the expense of requiring experimental data for parametrization. Within each method class, we examined the effect of the number of independent computational replicates, i.e., modeled structures or reinitialized MD simulations, on the prediction accuracy. We suggest using about ten modeled structures for scoring methods, and about five simulation replicates for MD simulations as a rule of thumb for obtaining reasonable convergence. We anticipate that our study will be a useful resource for practitioners working to incorporate binding affinity calculations within their protein design and optimization process.

PPI-Affinity: A Web Tool for the Prediction and Optimization of Protein-Peptide and Protein-Protein Binding Affinity.

Virtual screening of protein–protein and protein–peptide interactions is a challenging task that directly impacts the processes of hit identification and hit-to-lead optimization in drug design projects involving peptide-based pharmaceuticals. Although several screening tools designed to predict the binding affinity of protein–protein complexes have been proposed, methods specifically developed to predict protein–peptide binding affinity are comparatively scarce. Frequently, predictors trained to score the affinity of small molecules are used for peptides indistinctively, despite the larger complexity and heterogeneity of interactions rendered by peptide binders. To address this issue, we introduce PPI-Affinity, a tool that leverages support vector machine (SVM) predictors of binding affinity to screen datasets of protein–protein and protein–peptide complexes, as well as to generate and rank mutants of a given structure. The performance of the SVM models was assessed on four benchmark datasets, which include protein–protein and protein–peptide binding affinity data. In addition, we evaluated our model on a set of mutants of EPI-X4, an endogenous peptide inhibitor of the chemokine receptor CXCR4, and on complexes of the serine proteases HTRA1 and HTRA3 with peptides. PPI-Affinity is freely accessible at https://protdcal.zmb.uni-due.de/PPIAffinity.

Isothermal Titration Calorimetry in Biocatalysis

Isothermal titration calorimetry (ITC) is a popular chemical analysis technique that can be used to measure macromolecular interactions and chemical and physical processes. ITC involves the measurement of heat flow to and from a measurement cell after each injection during a titration experiment. ITC has been useful to measure the thermodynamics of macromolecular interactions such as protein-ligand or protein-protein binding affinity and also chemical processes such as enzyme catalyzed reactions. The use of ITC in biocatalysis has a number of advantages as ITC enables the measurement of enzyme kinetic parameters in a direct manner and, in principle, can be used for most enzymes and substrates. ITC approaches have been developed to measure reversible and irreversible enzyme inhibition, the effects of molecular crowding on enzyme activity, the activity of immobilized enzymes and the conversion of complex polymeric substrates. A disadvantage is that in order to obtain accurate kinetic parameters special care has to be taken in proper experimental design and data interpretation, which unfortunately is not always the case in reported studies. Furthermore, special caution is necessary when ITC experiments are performed that include solvents, reducing agents and may have side reactions. An important bottleneck in the use of calorimetry to measure enzyme activity is the relatively low throughput, which may be solved in the future by sensitive chip based microfluidic enzyme calorimetric devices.

Searching for a mechanistic description of pairwise epistasis in protein systems.

When two or more amino acid mutations occur in protein systems, they can interact in a nonadditive fashion termed epistasis. One way to quantify epistasis between mutation pairs in protein systems is by using free energy differences: ϵ=ΔΔG1,2 - (ΔΔG1 +ΔΔG2 ) where ΔΔG refers to the change in the Gibbs free energy, subscripts 1 and 2 refer to single mutations in arbitrary order and 1,2 refers to the double mutant. In this study, we explore possible biophysical mechanisms that drive pairwise epistasis in both protein-protein binding affinity and protein folding stability. Using the largest available datasets containing experimental protein structures and free energy data, we derived statistical models for both binding and folding epistasis (ϵ) with similar explanatory power (R2 ) of .299 and .258, respectively. These models contain terms and interactions that are consistent with intuition. For example, increasing the Cartesian separation between mutation sites leads to a decrease in observed epistasis for both folding and binding. Our results provide insight into factors that contribute to pairwise epistasis in protein systems and their importance in explaining epistasis. However, the low explanatory power indicates that more study is needed to fully understand this phenomenon.

Importance of interface and surface areas in protein-protein binding affinity prediction: A machine learning analysis based on linear regression and artificial neural network

Protein-protein interaction plays an important role in all biological systems. The binding affinity between two protein binding partners reflects the strength of their association, which is crucial to the elucidation of the biological functions of these proteins and also to the design of protein-based therapeutic agents. In recent years, many studies have been conducted in an effort to improve the ability to predict the binding affinity of a protein-protein complex. Different sequence and structural features have been adopted in the prediction, but the surface or interface areas of the protein-protein complex were often not given adequate consideration. In the present study, different types of interface and surface areas in the protein-protein complex were used to construct or train linear, nonlinear or mixed models using linear regression and artificial neural network to predict the binding affinity of protein-protein interactions. The relative importance of the different types of areas in the selected models for affinity prediction was analyzed using variable-controlling approach. In terms of performance, the best area-based binding affinity predictors appeared to be superior or at least comparable to the widely-used predictors PRODIGY (a contacts-based predictor) and LISA (Local Interaction Signal Analysis). This work highlights the importance of interface and surface areas in protein-protein binding interactions. It also sheds light on the more suitable computational approaches that may aid in solving some of the scientific and technical issues associated with protein-protein binding affinity prediction. SignificanceProtein-protein interactions are ubiquitous in living systems. Protein-protein binding affinity is a metric that estimates the binding strength between two protein binding partners. Reliable information on their binding affinity is of great value in understanding complex biological processes as well as in designing protein-based therapeutics. In this work, the interface and surface areas in protein-protein interaction are explored with respect to their relative importance in better predicting the protein-protein binding affinity. The results from this study showed that different types of areas contribute importantly to protein-protein interactions and thus should be jointly considered in an explicit manner to improve affinity predictions. In addition, the effective application of interface and surface areas may also facilitate the simulation of the protein folding and binding processes.