ProAffiMuSeq: sequence-based method to predict the binding free energy change of protein-protein complexes upon mutation using functional classification

Decoding the effects of mutation on protein interactions using machine learning

Accurately predicting mutation-caused binding free energy changes (ΔΔGs) on protein interactions is crucial for understanding how genetic variations affect interactions between proteins and other biomolecules, such as proteins, DNA/RNA, and ligands, which are vital for regulating numerous biological processes. Developing computational approaches with high accuracy and efficiency is critical for elucidating the mechanisms underlying various diseases, identifying potential biomarkers for early diagnosis, and developing targeted therapies. This review provides a comprehensive overview of recent advancements in predicting the impact of mutations on protein interactions across different interaction types, which are central to understanding biological processes and disease mechanisms, including cancer. We summarize recent progress in predictive approaches, including physicochemical-based, machine learning, and deep learning methods, evaluating the strengths and limitations of each. Additionally, we discuss the challenges related to the limitations of mutational data, including biases, data quality, and dataset size, and explore the difficulties in developing accurate prediction tools for mutation-induced effects on protein interactions. Finally, we discuss future directions for advancing these computational tools, highlighting the capabilities of advancing technologies, such as artificial intelligence to drive significant improvements in mutational effects prediction.

SAAMBE-MEM: a sequence-based method for predicting binding free energy change upon mutation in membrane protein-protein complexes

MOTIVATION

Mutations in protein-protein interactions can affect the corresponding complexes, impacting function and potentially leading to disease. Given the abundance of membrane proteins, it is crucial to assess the impact of mutations on the binding affinity of these proteins. Although several methods exist to predict the binding free energy change due to mutations in protein-protein complexes, most require structural information of the protein complex and are primarily trained on the SKEMPI database, which is composed mainly of soluble proteins.

RESULTS

A novel sequence-based method (SAAMBE-MEM) for predicting binding free energy changes (ΔΔG) in membrane protein-protein complexes due to mutations has been developed. This method utilized the MPAD database, which contains binding affinities for wild-type and mutant membrane protein complexes. A machine learning model was developed to predict ΔΔG by leveraging features such as amino acid indices and position-specific scoring matrices (PSSM). Through extensive dataset curation and feature extraction, SAAMBE-MEM was trained and validated using the XGBoost regression algorithm. The optimal feature set, including PSSM-related features, achieved a Pearson correlation coefficient of 0.64, outperforming existing methods trained on the SKEMPI database. Furthermore, it was demonstrated that SAAMBE-MEM performs much better when utilizing evolution-based features in contrast to physicochemical features.

AVAILABILITY AND IMPLEMENTATION

The method is accessible via a web server and standalone code at http://compbio.clemson.edu/SAAMBE-MEM/. The cleaned MPAD database is available at the website.

DeepPPAPredMut: deep ensemble method for predicting the binding affinity change in protein-protein complexes upon mutation

MOTIVATION

Protein-protein interactions underpin many cellular processes and their disruption due to mutations can lead to diseases. With the evolution of protein structure prediction methods like AlphaFold2 and the availability of extensive experimental affinity data, there is a pressing need for updated computational tools that can efficiently predict changes in binding affinity caused by mutations in protein-protein complexes.

RESULTS

We developed a deep ensemble model that leverages protein sequences, predicted structure-based features, and protein functional classes to accurately predict the change in binding affinity due to mutations. The model achieved a correlation of 0.97 and a mean absolute error (MAE) of 0.35 kcal/mol on the training dataset, and maintained robust performance on the test set with a correlation of 0.72 and a MAE of 0.83 kcal/mol. Further validation using Leave-One-Out Complex (LOOC) cross-validation exhibited a correlation of 0.83 and a MAE of 0.51 kcal/mol, indicating consistent performance.

AVAILABILITY AND IMPLEMENTATION

https://web.iitm.ac.in/bioinfo2/DeepPPAPredMut/index.html.

MPA-Pred: A machine learning approach for predicting the binding affinity of membrane protein-protein complexes

Membrane protein-protein interactions are essential for several functions including cell signaling, ion transport, and enzymatic activity. These interactions are mainly dictated by their binding affinities. Although several methods are available for predicting the binding affinity of protein-protein complexes, there exists no specific method for membrane protein-protein complexes. In this work, we collected the experimental binding affinity data for a set of 114 membrane protein-protein complexes and derived several structure and sequence-based features. Our analysis on the relationship between binding affinity and the features revealed that the important factors mainly depend on the type of membrane protein and the functional class of the protein. Specifically, aromatic and charged residues at the interface, and aromatic-aromatic and electrostatic interactions are found to be important to understand the binding affinity. Further, we developed a method, MPA-Pred, for predicting the binding affinity of membrane protein-protein complexes using a machine learning approach. It showed an average correlation and mean absolute error of 0.83 and 0.91 kcal/mol, respectively, using the jack-knife test on a set of 114 complexes. We have also developed a web server and it is available at https://web.iitm.ac.in/bioinfo2/MPA-Pred/. This method can be used for predicting the affinity of membrane protein-protein complexes at a large scale and aid to improve drug design strategies.

Predicting the immune escape of SARS-CoV-2 neutralizing antibodies upon mutation

COVID-19 has resulted in millions of deaths and severe impact on economies worldwide. Moreover, the emergence of SARS-CoV-2 variants presented significant challenges in controlling the pandemic, particularly their potential to avoid the immune system and evade vaccine immunity. This has led to a growing need for research to predict how mutations in SARS-CoV-2 reduces the ability of antibodies to neutralize the virus. In this study, we assembled a set of 1813 mutations from the interface of SARS-CoV-2 spike protein's receptor binding domain (RBD) and neutralizing antibody complexes and developed a machine learning model to classify high or low escape mutations using interaction energy, inter-residue contacts and predicted binding free energy change. Our approach achieved an Area under the Receiver Operating Characteristics (ROC) Curve (AUC) of 0.91 using the Random Forest classifier on the test dataset with 217 mutations. The model was further utilized to predict the escape mutations on a dataset of 29,165 mutations located at the interface of 83 RBD-neutralizing antibody complexes. A small subset of this dataset was also validated based on available experimental data. We found that top 10 % high escape mutations were dominated by charged to nonpolar mutations whereas low escape mutations were dominated by polar to nonpolar mutations. We believe that the present method will allow prioritization of high/low escape mutations in the context of neutralizing antibodies targeting SARS-CoV-2 RBD region and assist antibody design for current and emerging variants.

Reliable method for predicting the binding affinity of RNA-small molecule interactions using machine learning

Ribonucleic acids (RNAs) play important roles in cellular regulation. Consequently, dysregulation of both coding and non-coding RNAs has been implicated in several disease conditions in the human body. In this regard, a growing interest has been observed to probe into the potential of RNAs to act as drug targets in disease conditions. To accelerate this search for disease-associated novel RNA targets and their small molecular inhibitors, machine learning models for binding affinity prediction were developed specific to six RNA subtypes namely, aptamers, miRNAs, repeats, ribosomal RNAs, riboswitches and viral RNAs. We found that differences in RNA sequence composition, flexibility and polar nature of RNA-binding ligands are important for predicting the binding affinity. Our method showed an average Pearson correlation (r) of 0.83 and a mean absolute error of 0.66 upon evaluation using the jack-knife test, indicating their reliability despite the low amount of data available for several RNA subtypes. Further, the models were validated with external blind test datasets, which outperform other existing quantitative structure-activity relationship (QSAR) models. We have developed a web server to host the models, RNA-Small molecule binding Affinity Predictor, which is freely available at: https://web.iitm.ac.in/bioinfo2/RSAPred/.

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.

Geometric Graph Learning to Predict Changes in Binding Free Energy and Protein Thermodynamic Stability upon Mutation

Accurate prediction of binding free energy changes upon mutations is vital for optimizing drugs, designing proteins, understanding genetic diseases, and cost-effective virtual screening. While machine learning methods show promise in this domain, achieving accuracy and generalization across diverse data sets remains a challenge. This study introduces Geometric Graph Learning for Protein-Protein Interactions (GGL-PPI), a novel approach integrating geometric graph representation and machine learning to forecast mutation-induced binding free energy changes. GGL-PPI leverages atom-level graph coloring and multiscale weighted colored geometric subgraphs to capture structural features of biomolecules, demonstrating superior performance on three standard data sets, namely, AB-Bind, SKEMPI 1.0, and SKEMPI 2.0 data sets. The model's efficacy extends to predicting protein thermodynamic stability in a blind test set, providing unbiased predictions for both direct and reverse mutations and showcasing notable generalization. GGL-PPI's precision in predicting changes in binding free energy and stability due to mutations enhances our comprehension of protein complexes, offering valuable insights for drug design endeavors.

Inferring the Effects of Protein Variants on Protein-Protein Interactions with Interpretable Transformer Representations

Identifying pathogenetic variants and inferring their impact on protein-protein interactions sheds light on their functional consequences on diseases. Limited by the availability of experimental data on the consequences of protein interaction, most existing methods focus on building models to predict changes in protein binding affinity. Here, we introduced MIPPI, an end-to-end, interpretable transformer-based deep learning model that learns features directly from sequences by leveraging the interaction data from IMEx. MIPPI was specifically trained to determine the types of variant impact (increasing, decreasing, disrupting, and no effect) on protein-protein interactions. We demonstrate the accuracy of MIPPI and provide interpretation through the analysis of learned attention weights, which exhibit correlations with the amino acids interacting with the variant. Moreover, we showed the practicality of MIPPI in prioritizing de novo mutations associated with complex neurodevelopmental disorders and the potential to determine the pathogenic and driving mutations. Finally, we experimentally validated the functional impact of several variants identified in patients with such disorders. Overall, MIPPI emerges as a versatile, robust, and interpretable model, capable of effectively predicting mutation impacts on protein-protein interactions and facilitating the discovery of clinically actionable variants.

Predicting the Effect of Single Mutations on Protein Stability and Binding with Respect to Types of Mutations

The development of methods and algorithms to predict the effect of mutations on protein stability, protein-protein interaction, and protein-DNA/RNA binding is necessitated by the needs of protein engineering and for understanding the molecular mechanism of disease-causing variants. The vast majority of the leading methods require a database of experimentally measured folding and binding free energy changes for training. These databases are collections of experimental data taken from scientific investigations typically aimed at probing the role of particular residues on the above-mentioned thermodynamic characteristics, i.e., the mutations are not introduced at random and do not necessarily represent mutations originating from single nucleotide variants (SNV). Thus, the reported performance of the leading algorithms assessed on these databases or other limited cases may not be applicable for predicting the effect of SNVs seen in the human population. Indeed, we demonstrate that the SNVs and non-SNVs are not equally presented in the corresponding databases, and the distribution of the free energy changes is not the same. It is shown that the Pearson correlation coefficients (PCCs) of folding and binding free energy changes obtained in cases involving SNVs are smaller than for non-SNVs, indicating that caution should be used in applying them to reveal the effect of human SNVs. Furthermore, it is demonstrated that some methods are sensitive to the chemical nature of the mutations, resulting in PCCs that differ by a factor of four across chemically different mutations. All methods are found to underestimate the energy changes by roughly a factor of 2.

Accelerating therapeutic protein design with computational approaches toward the clinical stage

Therapeutic protein, represented by antibodies, is of increasing interest in human medicine. However, clinical translation of therapeutic protein is still largely hindered by different aspects of developability, including affinity and selectivity, stability and aggregation prevention, solubility and viscosity reduction, and deimmunization. Conventional optimization of the developability with widely used methods, like display technologies and library screening approaches, is a time and cost-intensive endeavor, and the efficiency in finding suitable solutions is still not enough to meet clinical needs. In recent years, the accelerated advancement of computational methodologies has ushered in a transformative era in the field of therapeutic protein design. Owing to their remarkable capabilities in feature extraction and modeling, the integration of cutting-edge computational strategies with conventional techniques presents a promising avenue to accelerate the progression of therapeutic protein design and optimization toward clinical implementation. Here, we compared the differences between therapeutic protein and small molecules in developability and provided an overview of the computational approaches applicable to the design or optimization of therapeutic protein in several developability issues.

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.

Elucidating important structural features for the binding affinity of spike - SARS-CoV-2 neutralizing antibody complexes

The coronavirus disease 2019 (COVID-19) has affected the lives of millions of people around the world. In an effort to develop therapeutic interventions and control the pandemic, scientists have isolated several neutralizing antibodies against SARS-CoV-2 from the vaccinated and convalescent individuals. These antibodies can be explored further to understand SARS-CoV-2 specific antigen-antibody interactions and biophysical parameters related to binding affinity, which can be utilized to engineer more potent antibodies for current and emerging SARS-CoV-2 variants. In the present study, we have analyzed the interface between spike protein of SARS-CoV-2 and neutralizing antibodies in terms of amino acid residue propensity, pair preference, and atomic interaction energy. We observed that Tyr residues containing contacts are highly preferred and energetically favorable at the interface of spike protein-antibody complexes. We have also developed a regression model to relate the experimental binding affinity for antibodies using structural features, which showed a correlation of 0.93. Moreover, several mutations at the spike protein-antibody interface were identified, which may lead to immune escape (epitope residues) and improved affinity (paratope residues) in current/emerging variants. Overall, the work provides insights into spike protein-antibody interactions, structural parameters related to binding affinity and mutational effects on binding affinity change, which can be helpful to develop better therapeutics against COVID-19.

SAAMBE-SEQ: a sequence-based method for predicting mutation effect on protein-protein binding affinity

MOTIVATION

Vast majority of human genetic disorders are associated with mutations that affect protein-protein interactions by altering wild-type binding affinity. Therefore, it is extremely important to assess the effect of mutations on protein-protein binding free energy to assist the development of therapeutic solutions. Currently, the most popular approaches use structural information to deliver the predictions, which precludes them to be applicable on genome-scale investigations. Indeed, with the progress of genomic sequencing, researchers are frequently dealing with assessing effect of mutations for which there is no structure available.

RESULTS

Here, we report a Gradient Boosting Decision Tree machine learning algorithm, the SAAMBE-SEQ, which is completely sequence-based and does not require structural information at all. SAAMBE-SEQ utilizes 80 features representing evolutionary information, sequence-based features and change of physical properties upon mutation at the mutation site. The approach is shown to achieve Pearson correlation coefficient (PCC) of 0.83 in 5-fold cross validation in a benchmarking test against experimentally determined binding free energy change (ΔΔG). Further, a blind test (no-STRUC) is compiled collecting experimental ΔΔG upon mutation for protein complexes for which structure is not available and used to benchmark SAAMBE-SEQ resulting in PCC in the range of 0.37-0.46. The accuracy of SAAMBE-SEQ method is found to be either better or comparable to most advanced structure-based methods. SAAMBE-SEQ is very fast, available as webserver and stand-alone code, and indeed utilizes only sequence information, and thus it is applicable for genome-scale investigations to study the effect of mutations on protein-protein interactions.

AVAILABILITY AND IMPLEMENTATION

SAAMBE-SEQ is available at http://compbio.clemson.edu/saambe_webserver/indexSEQ.php#started.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Assessment of software methods for estimating protein-protein relative binding affinities

A growing number of computational tools have been developed to accurately and rapidly predict the impact of amino acid mutations on protein-protein relative binding affinities. Such tools have many applications, for example, designing new drugs and studying evolutionary mechanisms. In the search for accuracy, many of these methods employ expensive yet rigorous molecular dynamics simulations. By contrast, non-rigorous methods use less exhaustive statistical mechanics, allowing for more efficient calculations. However, it is unclear if such methods retain enough accuracy to replace rigorous methods in binding affinity calculations. This trade-off between accuracy and computational expense makes it difficult to determine the best method for a particular system or study. Here, eight non-rigorous computational methods were assessed using eight antibody-antigen and eight non-antibody-antigen complexes for their ability to accurately predict relative binding affinities (ΔΔG) for 654 single mutations. In addition to assessing accuracy, we analyzed the CPU cost and performance for each method using a variety of physico-chemical structural features. This allowed us to posit scenarios in which each method may be best utilized. Most methods performed worse when applied to antibody-antigen complexes compared to non-antibody-antigen complexes. Rosetta-based JayZ and EasyE methods classified mutations as destabilizing (ΔΔG < -0.5 kcal/mol) with high (83-98%) accuracy and a relatively low computational cost for non-antibody-antigen complexes. Some of the most accurate results for antibody-antigen systems came from combining molecular dynamics with FoldX with a correlation coefficient (r) of 0.46, but this was also the most computationally expensive method. Overall, our results suggest these methods can be used to quickly and accurately predict stabilizing versus destabilizing mutations but are less accurate at predicting actual binding affinities. This study highlights the need for continued development of reliable, accessible, and reproducible methods for predicting binding affinities in antibody-antigen proteins and provides a recipe for using current methods.

MutaBind2: Predicting the Impacts of Single and Multiple Mutations on Protein-Protein Interactions

Missense mutations may affect proteostasis by destabilizing or over-stabilizing protein complexes and changing the pathway flux. Predicting the effects of stabilizing mutations on protein-protein interactions is notoriously difficult because existing experimental sets are skewed toward mutations reducing protein-protein binding affinity and many computational methods fail to correctly evaluate their effects. To address this issue, we developed a method MutaBind2, which estimates the impacts of single as well as multiple mutations on protein-protein interactions. MutaBind2 employs only seven features, and the most important of them describe interactions of proteins with the solvent, evolutionary conservation of the site, and thermodynamic stability of the complex and each monomer. This approach shows a distinct improvement especially in evaluating the effects of mutations increasing binding affinity. MutaBind2 can be used for finding disease driver mutations, designing stable protein complexes, and discovering new protein-protein interaction inhibitors.