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/.

TMKit: a Python interface for computational analysis of transmembrane proteins.

Transmembrane proteins are receptors, enzymes, transporters and ion channels that are instrumental in regulating a variety of cellular activities, such as signal transduction and cell communication. Despite tremendous progress in computational capacities to support protein research, there is still a significant gap in the availability of specialized computational analysis toolkits for transmembrane protein research. Here, we introduce TMKit, an open-source Python programming interface that is modular, scalable and specifically designed for processing transmembrane protein data. TMKit is a one-stop computational analysis tool for transmembrane proteins, enabling users to perform database wrangling, engineer features at the mutational, domain and topological levels, and visualize protein-protein interaction interfaces. In addition, TMKit includes seqNetRR, a high-performance computing library that allows customized construction of a large number of residue connections. This library is particularly well suited for assigning correlation matrix-based features at a fast speed. TMKit should serve as a useful tool for researchers in assisting the study of transmembrane protein sequences and structures. TMKit is publicly available through https://github.com/2003100127/tmkit and https://tmkit-guide.herokuapp.com/doc/overview.

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.

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.

Identification of potential driver mutations in glioblastoma using machine learning.

Glioblastoma is a fast and aggressively growing tumor in the brain and spinal cord. Mutation of amino acid residues in targets proteins, which are involved in glioblastoma, alters the structure and function and may lead to disease. In this study, we collected a set of 9386 disease-causing (drivers) mutations based on the recurrence in patient samples and experimentally annotated as pathogenic and 8728 as neutral (passenger) mutations. We observed that Arg is highly preferred at the mutant sites of drivers, whereas Met and Ile showed preferences in passengers. Inspecting neighboring residues at the mutant sites revealed that the motifs YP, CP and GRH, are preferred in drivers, whereas SI, IQ and TVI are dominant in neutral. In addition, we have computed other sequence-based features such as conservation scores, Position Specific Scoring Matrices (PSSM) and physicochemical properties, and developed a machine learning-based method, GBMDriver (GlioBlastoma Multiforme Drivers), for distinguishing between driver and passenger mutations. Our method showed an accuracy and AUC of 73.59% and 0.82, respectively, on 10-fold cross-validation and 81.99% and 0.87 in a blind set of 1809 mutants. The tool is available at https://web.iitm.ac.in/bioinfo2/GBMDriver/index.html. We envisage that the present method is helpful to prioritize driver mutations in glioblastoma and assist in identifying therapeutic targets.

ProNAB: database for binding affinities of protein-nucleic acid complexes and their mutants.

Protein-nucleic acid interactions are involved in various biological processes such as gene expression, replication, transcription, translation and packaging. The binding affinities of protein-DNA and protein-RNA complexes are important for elucidating the mechanism of protein-nucleic acid recognition. Although experimental data on binding affinity are reported abundantly in the literature, no well-curated database is currently available for protein-nucleic acid binding affinity. We have developed a database, ProNAB, which contains more than 20 000 experimental data for the binding affinities of protein-DNA and protein-RNA complexes. Each entry provides comprehensive information on sequence and structural features of a protein, nucleic acid and its complex, experimental conditions, thermodynamic parameters such as dissociation constant (Kd), binding free energy (ΔG) and change in binding free energy upon mutation (ΔΔG), and literature information. ProNAB is cross-linked with GenBank, UniProt, PDB, ProThermDB, PROSITE, DisProt and Pubmed. It provides a user-friendly web interface with options for search, display, sorting, visualization, download and upload the data. ProNAB is freely available at https://web.iitm.ac.in/bioinfo2/pronab/ and it has potential applications such as understanding the factors influencing the affinity, development of prediction tools, binding affinity change upon mutation and design complexes with the desired affinity.

MPTherm: database for membrane protein thermodynamics for understanding folding and stability.

The functions of membrane proteins (MPs) are attributed to their structure and stability. Factors influencing the stability of MPs differ from globular proteins due to the presence of membrane spanning regions. Thermodynamic data of MPs aid to understand the relationship among their structure, stability and function. Although a wealth of experimental data on thermodynamics of MPs are reported in the literature, there is no database available explicitly for MPs. In this work, we have developed a database for MP thermodynamics, MPTherm, which contains more than 7000 thermodynamic data from about 320 MPs. Each entry contains protein sequence and structural information, membrane topology, experimental conditions, thermodynamic parameters such as melting temperature, free energy, enthalpy etc. and literature information. MPTherm assists users to retrieve the data by using different search and display options. We have also provided the sequence and structure visualization as well as cross-links to UniProt and PDB databases. MPTherm database is freely available at http://www.iitm.ac.in/bioinfo/mptherm/. It is implemented in HTML, PHP, MySQL and JavaScript, and supports the latest versions of major browsers, such as Firefox, Chrome and Opera. MPTherm would serve as an effective resource for understanding the stability of MPs, development of prediction tools and identifying drug targets for diseases associated with MPs.

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.

Evaluation of in silico tools for the prediction of protein and peptide aggregation on diverse datasets.

Several prediction algorithms and tools have been developed in the last two decades to predict protein and peptide aggregation. These in silico tools aid to predict the aggregation propensity and amyloidogenicity as well as the identification of aggregation-prone regions. Despite the immense interest in the field, it is of prime importance to systematically compare these algorithms for their performance. In this review, we have provided a rigorous performance analysis of nine prediction tools using a variety of assessments. The assessments were carried out on several non-redundant datasets ranging from hexapeptides to protein sequences as well as amyloidogenic antibody light chains to soluble protein sequences. Our analysis reveals the robustness of the current prediction tools and the scope for improvement in their predictive performances. Insights gained from this work provide critical guidance to the scientific community on advantages and limitations of different aggregation prediction methods and make informed decisions about their research needs.

Mutations in transmembrane proteins: diseases, evolutionary insights, prediction and comparison with globular proteins.

Membrane proteins are unique in that they interact with lipid bilayers, making them indispensable for transporting molecules and relaying signals between and across cells. Due to the significance of the protein's functions, mutations often have profound effects on the fitness of the host. This is apparent both from experimental studies, which implicated numerous missense variants in diseases, as well as from evolutionary signals that allow elucidating the physicochemical constraints that intermembrane and aqueous environments bring. In this review, we report on the current state of knowledge acquired on missense variants (referred to as to single amino acid variants) affecting membrane proteins as well as the insights that can be extrapolated from data already available. This includes an overview of the annotations for membrane protein variants that have been collated within databases dedicated to the topic, bioinformatics approaches that leverage evolutionary information in order to shed light on previously uncharacterized membrane protein structures or interaction interfaces, tools for predicting the effects of mutations tailored specifically towards the characteristics of membrane proteins as well as two clinically relevant case studies explaining the implications of mutated membrane proteins in cancer and cardiomyopathy.

Ab-CoV: a curated database for binding affinity and neutralization profiles of coronavirus-related antibodies.

SUMMARY: We have developed a database, Ab-CoV, which contains manually curated experimental interaction profiles of 1780 coronavirus-related neutralizing antibodies. It contains more than 3200 datapoints on half maximal inhibitory concentration (IC50), half maximal effective concentration (EC50) and binding affinity (KD). Each data with experimentally known three-dimensional structures are complemented with predicted change in stability and affinity of all possible point mutations of interface residues. Ab-CoV also includes information on epitopes and paratopes, structural features of viral proteins, sequentially similar therapeutic antibodies and Collier de Perles plots. It has the feasibility for structure visualization and options to search, display and download the data. AVAILABILITY AND IMPLEMENTATION: Ab-CoV database is freely available at https://web.iitm.ac.in/bioinfo2/ab-cov/home. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

In silico evaluation of the impact of Omicron variant of concern sublineage BA.4 and BA.5 on the sensitivity of RT-qPCR assays for SARS-CoV-2 detection using whole genome sequencing.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variant of concern (VoC) Omicron (B.1.1.529) has rapidly spread around the world, presenting a new threat to global public human health. Due to the large number of mutations accumulated by SARS-CoV-2 Omicron, concerns have emerged over potentially reduced diagnostic accuracy of reverse-transcription polymerase chain reaction (RT-qPCR), the gold standard diagnostic test for diagnosing coronavirus disease 2019 (COVID-19). Thus, we aimed to assess the impact of the currently endemic Omicron sublineages BA.4 and BA.5 on the integrity and sensitivity of RT-qPCR assays used for coronavirus disease 2019 (COVID-19) diagnosis via in silico analysis. We employed whole genome sequencing data and evaluated the potential for false negatives or test failure due to mismatches between primers/probes and the Omicron VoC viral genome. METHODS: In silico sensitivity of 12 RT-qPCR tests (containing 30 primers and probe sets) developed for detection of SARS-CoV-2 reported by the World Health Organization (WHO) or available in the literature, was assessed for specifically detecting SARS-CoV-2 Omicron BA.4 and BA.5 sublineages, obtained after removing redundancy from publicly available genomes from National Center for Biotechnology Information (NCBI) and Global Initiative on Sharing Avian Influenza Data (GISAID) databases. Mismatches between amplicon regions of SARS-CoV-2 Omicron VoC and primers and probe sets were evaluated, and clustering analysis of corresponding amplicon sequences was carried out. RESULTS: From the 1164 representative SARS-CoV-2 Omicron VoC BA.4 sublineage genomes analyzed, a substitution in the first five nucleotides (C to T) of the amplicon's 3'-end was observed in all samples resulting in 0% sensitivity for assays HKUnivRdRp/Hel (mismatch in reverse primer) and CoremCharite N (mismatch in both forward and reverse primers). Due to a mismatch in the forward primer's 5'-end (3-nucleotide substitution, GGG to AAC), the sensitivity of the ChinaCDC N assay was at 0.69%. The 10 nucleotide mismatches in the reverse primer resulted in 0.09% sensitivity for Omicron sublineage BA.4 for Thai N assay. Of the 1926 BA.5 sublineage genomes, HKUnivRdRp/Hel assay also had 0% sensitivity. A sensitivity of 3.06% was observed for the ChinaCDC N assay because of a mismatch in the forward primer's 5'-end (3-nucleotide substitution, GGG to AAC). Similarly, due to the 10 nucleotide mismatches in the reverse primer, the Thai N assay's sensitivity was low at 0.21% for sublineage BA.5. Further, eight assays for BA.4 sublineage retained high sensitivity (more than 97%) and 9 assays for BA.5 sublineage retained more than 99% sensitivity. CONCLUSION: We observed four assays (HKUnivRdRp/Hel, ChinaCDC N, Thai N, CoremCharite N) that could potentially result in false negative results for SARS-CoV-2 Omicron VoCs BA.4 and BA.5 sublineages. Interestingly, CoremCharite N had 0% sensitivity for Omicron Voc BA.4 but 99.53% sensitivity for BA.5. In addition, 66.67% of the assays for BA.4 sublineage and 75% of the assays for BA.5 sublineage retained high sensitivity. Further, amplicon clustering and additional substitution analysis along with sensitivity analysis could be used for the modification and development of RT-qPCR assays for detecting SARS-CoV-2 Omicron VoC sublineages.

DeepBSRPred: deep learning-based binding site residue prediction for proteins.

MOTIVATION: Proteins-protein interactions (PPIs) are important to govern several cellular activities. Amino acid residues, which are located at the interface are known as the binding sites and the information about binding sites helps to understand the binding affinities and functions of protein-protein complexes. RESULTS: We have developed a deep neural network-based method, DeepBSRPred, for predicting the binding sites using protein sequence information and predicted structures from AlphaFold2. Specific sequence and structure-based features include position-specific scoring matrix (PSSM), solvent accessible surface area, conservation score and amino acid properties, and residue depth, respectively. Our method predicted the binding sites with an average F1 score of 0.73 in a dataset of 1236 proteins. Further, we compared the performance with other existing methods in the literature using four benchmark datasets and our method outperformed those methods. AVAILABILITY AND IMPLEMENTATION: The DeepBSRPred web server can be found at https://web.iitm.ac.in/bioinfo2/deepbsrpred/index.html , along with all datasets used in this study. The trained models, the DeepBSRPred standalone source code, and the feature computation pipeline are freely available at https://web.iitm.ac.in/bioinfo2/deepbsrpred/download.html .

ProThermDB: thermodynamic database for proteins and mutants revisited after 15 years.

ProThermDB is an updated version of the thermodynamic database for proteins and mutants (ProTherm), which has ∼31 500 data on protein stability, an increase of 84% from the previous version. It contains several thermodynamic parameters such as melting temperature, free energy obtained with thermal and denaturant denaturation, enthalpy change and heat capacity change along with experimental methods and conditions, sequence, structure and literature information. Besides, the current version of the database includes about 120 000 thermodynamic data obtained for different organisms and cell lines, which are determined by recent high throughput proteomics techniques using whole-cell approaches. In addition, we provided a graphical interface for visualization of mutations at sequence and structure levels. ProThermDB is cross-linked with other relevant databases, PDB, UniProt, PubMed etc. It is freely available at https://web.iitm.ac.in/bioinfo2/prothermdb/index.html without any login requirements. It is implemented in Python, HTML and JavaScript, and supports the latest versions of major browsers, such as Firefox, Chrome and Safari.

Effect of charged mutation on aggregation of a pentapeptide: Insights from molecular dynamics simulations.

Aggregation of therapeutic monoclonal antibodies (mAbs) can negatively affect their chemistry, manufacturing, and control attributes and lead to undesirable immune responses in patients. Therefore, optimization of lead mAb drug candidates during discovery stages to mitigate aggregation is increasingly becoming an integral part of their developability assessments. The disruption of short sequence motifs called aggregation prone regions (APRs) found in amino acid sequences of mAb candidates can potentially mitigate their aggregation. In this work, we have performed molecular dynamics simulations to study the aggregation of an APR (VLVIY) found in λ light chains of human antibodies and its single point mutant KLVIY. Eighteen different multicopy peptide simulation systems of "VLVIY" and "KLVIY" were constructed by varying their concentrations, temperatures, termini capping, and flanking gate-keeper regions. Within 20 ns of the simulation, peptide "VLVIY" formed an aggregate of 100 peptides at ~0.1 M concentration with a 60% reduction in solvent accessible surface area (SASA). Furthermore, analysis of the SASA change, peptide cluster distribution, and water residence time demonstrated how Val ➔ Lys mutation resists aggregation and improves solubility. Presence of Lys slows down aggregation kinetics via charge-charge repulsions and by raising the kinetic barrier to formation of large oligomers. However, the effect of the Val ➔ Lys mutation is dependent on sequence and structural contexts around the APR. This mutation also alters the solvation shell around the peptide by favoring solute-solvent interactions, thereby increasing its solubility. This work has provided a detailed mechanistic explanation of how APR disruption can mitigate aggregation in biotherapeutics and improve their developability.

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.

Tackling Covid-19 using disordered-to-order transition of residues in the spike protein upon angiotensin-converting enzyme 2 binding.

The 2019-novel coronavirus also known as severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) is a common threat to animals and humans, and is responsible for the human SARS pandemic in 2019 to 2021. The infection of SARS-CoV-2 in humans involves a viral surface glycoprotein named as spike proteins, which bind to the human angiotensin-converting enzyme 2 (ACE2) proteins. Particularly, the receptor binding domains (RBDs) mediate the interaction and contain several disordered regions, which help in the binding. Investigations on the influence of disordered residues/regions in stability and binding of spike protein with ACE2 help to understand the disease pathogenesis, which has not yet been studied. In this study, we have used molecular-dynamics simulations to characterize the structural changes in disordered regions of the spike protein that result from ACE2 binding. We observed that the disordered regions undergo disorder-to-order transition (DOT) upon binding with ACE2, and the DOT residues are located at functionally important regions of RBD. Although the RBD is having rigid structure, DOT residues make conformational rearrangements for the spike protein to attach with ACE2. The binding is strengthened via hydrophilic and aromatic amino acids mainly present in the DOTs. The positively correlated motions of the DOT residues with its nearby residues also explain the binding profile of RBD with ACE2, and the residues are observed to be contributing more favorable binding energies for the spike-ACE2 complex formation. This study emphasizes that intrinsically disordered residues in the RBD of spike protein may provide insights into its etiology and be useful for drug and vaccine discovery.

Why are ACE2 binding coronavirus strains SARS-CoV/SARS-CoV-2 wild and NL63 mild?

Coronaviruses are responsible for several epidemics, including the 2002 SARS, 2012 MERS, and COVID-19. The emergence of recent COVID-19 pandemic due to SARS-CoV-2 virus in December 2019 has resulted in considerable research efforts to design antiviral drugs and other therapeutics against coronaviruses. In this context, it is crucial to understand the biophysical and structural features of the major proteins that are involved in virus-host interactions. In the current study, we have compared spike proteins from three strains of coronaviruses NL63, SARS-CoV, and SARS-CoV, known to bind human angiotensin-converting enzyme 2 (ACE2), in terms of sequence/structure conservation, hydrophobic cluster formation and importance of binding site residues. The study reveals that the severity of coronavirus strains correlates positively with the interaction area, surrounding hydrophobicity and interaction energy and inversely correlate with the flexibility of the binding interface. Also, we identify the conserved residues in the binding interface of spike proteins in all three strains. The systematic point mutations show that these conserved residues in the respective strains are evolutionarily favored at their respective positions. The similarities and differences in the spike proteins of the three viruses indicated in this study may help researchers to deeply understand the structural behavior, binding site properties and etiology of ACE2 binding, accelerating the screening of potential lead molecules and the development/repurposing of therapeutic drugs.

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

MOTIVATION: Protein-protein interactions are essential for the cell and mediate various functions. However, mutations can disrupt these interactions and may cause diseases. Currently available computational methods require a complex structure as input for predicting the change in binding affinity. Further, they have not included the functional class information for the protein-protein complex. To address this, we have developed a method, ProAffiMuSeq, which predicts the change in binding free energy using sequence-based features and functional class. RESULTS: Our method shows an average correlation between predicted and experimentally determined ΔΔG of 0.73 and mean absolute error (MAE) of 0.86 kcal/mol in 10-fold cross-validation and correlation of 0.75 with MAE of 0.94 kcal/mol in the test dataset. ProAffiMuSeq was also tested on an external validation set and showed results comparable to structure-based methods. Our method can be used for large-scale analysis of disease-causing mutations in protein-protein complexes without structural information. AVAILABILITY AND IMPLEMENTATION: Users can access the method at https://web.iitm.ac.in/bioinfo2/proaffimuseq/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.