Protein binding site prediction using an empirical scoring function

Computational Prediction of Multiple Antigen Epitopes

Motivation

Identifying antigen epitopes is essential in medical applications, such as immunodiagnostic reagent discovery, vaccine design, and drug development. Computational approaches can complement low-throughput, time-consuming, and costly experimental determination of epitopes. Currently available prediction methods, however, have moderate success predicting epitopes, which limits their applicability. Epitope prediction is further complicated by the fact that multiple epitopes may be located on the same antigen and complete experimental data is often unavailable.

Results

Here, we introduce the antigen epitope prediction program ISPIPab that combines information from two feature-based methods and a docking-based method. We demonstrate that ISPIPab outperforms each of its individual classifiers as well as other state-of-the-art methods, including those designed specifically for epitope prediction. By combining the prediction algorithm with hierarchical clustering, we show that we can effectively capture epitopes that align with available experimental data while also revealing additional novel targets for future experimental investigations.

Contact

raji@yu.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

Leveraging machine learning models for peptide-protein interaction prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as docking and molecular dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

ANN based prediction of ligand binding sites outside deep cavities to facilitate drug designing

The ever-changing environmental conditions and pollution are the prime reasons for the onset of several emerging and re-merging diseases. This demands the faster designing of new drugs to curb the deadly diseases in less waiting time to cure the animals and humans. Drug molecules interact with only protein surface on specific locations termed as ligand binding sites (LBS). Therefore, the knowledge of LBS is required for rational drug designing. Existing geometrical LBS prediction methods rely on search of cavities based on the fact that 83% of the LBS found in deep cavities, however, these methods usually fail where LBS localize outside deep cavities. To overcome this challenge, the present work provides an artificial neural network (ANN) based method to predict LBS outside deep cavities in animal proteins including human to facilitate drug designing. In the present work a feed-forward backpropagation neural network was trained by utilizing 38 structural, atomic, physiochemical, and evolutionary discriminant features of LBS and non-LBS residues localized in the extracted roughest patch on protein surface. The performance of this ANN based prediction method was found 76% better for those proteins where cavity subspace (extracted by MetaPocket 2.0, a consensus method) failed to predict LBS due to their localization outside the deep cavities. The prediction of LBS outside deep cavities will facilitate in drug designing for the proteins where it is not possible due to lack of LBS information as the geometrical LBS prediction methods rely on extraction of deep cavities.

Leveraging Machine Learning Models for Peptide-Protein Interaction Prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as Docking and Molecular Dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

E(3) equivariant graph neural networks for robust and accurate protein-protein interaction site prediction

Artificial intelligence-powered protein structure prediction methods have led to a paradigm-shift in computational structural biology, yet contemporary approaches for predicting the interfacial residues (i.e., sites) of protein-protein interaction (PPI) still rely on experimental structures. Recent studies have demonstrated benefits of employing graph convolution for PPI site prediction, but ignore symmetries naturally occurring in 3-dimensional space and act only on experimental coordinates. Here we present EquiPPIS, an E(3) equivariant graph neural network approach for PPI site prediction. EquiPPIS employs symmetry-aware graph convolutions that transform equivariantly with translation, rotation, and reflection in 3D space, providing richer representations for molecular data compared to invariant convolutions. EquiPPIS substantially outperforms state-of-the-art approaches based on the same experimental input, and exhibits remarkable robustness by attaining better accuracy with predicted structural models from AlphaFold2 than what existing methods can achieve even with experimental structures. Freely available at https://github.com/Bhattacharya-Lab/EquiPPIS, EquiPPIS enables accurate PPI site prediction at scale.

Two point mutations in protocadherin-1 disrupt hantavirus recognition and afford protection against lethal infection

Andes virus (ANDV) and Sin Nombre virus (SNV) are the etiologic agents of severe hantavirus cardiopulmonary syndrome (HCPS) in the Americas for which no FDA-approved countermeasures are available. Protocadherin-1 (PCDH1), a cadherin-superfamily protein recently identified as a critical host factor for ANDV and SNV, represents a new antiviral target; however, its precise role remains to be elucidated. Here, we use computational and experimental approaches to delineate the binding surface of the hantavirus glycoprotein complex on PCDH1's first extracellular cadherin repeat domain. Strikingly, a single amino acid residue in this PCDH1 surface influences the host species-specificity of SNV glycoprotein-PCDH1 interaction and cell entry. Mutation of this and a neighboring residue substantially protects Syrian hamsters from pulmonary disease and death caused by ANDV. We conclude that PCDH1 is a bona fide entry receptor for ANDV and SNV whose direct interaction with hantavirus glycoproteins could be targeted to develop new interventions against HCPS.

Interplay between C1-inhibitor and group IIA secreted phospholipase A2 impairs their respective function

High levels of human group IIA secreted phospholipase A₂ (hGIIA) have been associated with various inflammatory disease conditions. We have recently shown that hGIIA activity and concentration are increased in the plasma of patients with hereditary angioedema due to C1-inhibitor deficiency (C1-INH-HAE) and negatively correlate with C1-INH plasma activity. In this study, we analyzed whether the presence of both hGIIA and C1-INH impairs their respective function on immune cells. hGIIA, but not recombinant and plasma-derived C1-INH, stimulates the production of IL-6, CXCL8, and TNF-α from peripheral blood mononuclear cells (PBMCs). PBMC activation mediated by hGIIA is blocked by RO032107A, a specific hGIIA inhibitor. Interestingly, C1-INH inhibits the hGIIA-induced production of IL-6, TNF-α, and CXCL8, while it does not affect hGIIA enzymatic activity. On the other hand, hGIIA reduces the capacity of C1-INH at inhibiting C1-esterase activity. Spectroscopic and molecular docking studies suggest a possible interaction between hGIIA and C1-INH but further experiments are needed to confirm this hypothesis. Together, these results provide evidence for a new interplay between hGIIA and C1-INH, which may be important in the pathophysiology of hereditary angioedema.

B-Cell Epitope Predictions Using Computational Methods

Identifying protein antigenic epitopes that are recognizable by antibodies is a key step in immunologic research. This type of research has broad medical applications, such as new immunodiagnostic reagent discovery, vaccine design, and antibody design. However, due to the countless possibilities of potential epitopes, the experimental search through trial and error would be too costly and time-consuming to be practical. To facilitate this process and improve its efficiency, computational methods were developed to predict both linear epitopes and discontinuous antigenic epitopes. For linear B-cell epitope prediction, many methods were developed, including PREDITOP, PEOPLE, BEPITOPE, BepiPred, COBEpro, ABCpred, AAP, BCPred, BayesB, BEOracle/BROracle, BEST, LBEEP, DRREP, iBCE-EL, SVMTriP, etc. For the more challenging yet important task of discontinuous epitope prediction, methods were also developed, including CEP, DiscoTope, PEPITO, ElliPro, SEPPA, EPITOPIA, PEASE, EpiPred, SEPIa, EPCES, EPSVR, etc. In this chapter, we will discuss computational methods for B-cell epitope predictions of both linear and discontinuous epitopes. SVMTriP and EPCES/EPCSVR, the most successful among the methods for each type of the predictions, will be used as model methods to detail the standard protocols. For linear epitope prediction, SVMTriP was reported to achieve a sensitivity of 80.1% and a precision of 55.2% with a fivefold cross-validation based on a large dataset, yielding an AUC of 0.702. For discontinuous or conformational B-cell epitope prediction, EPCES and EPCSVR were both benchmarked by a curated independent test dataset in which all antigens had no complex structures with the antibody. The identified epitopes by these methods were later independently validated by various biochemical experiments. For these three model methods, webservers and all datasets are publicly available at http://sysbio.unl.edu/SVMTriP , http://sysbio.unl.edu/EPCES/ , and http://sysbio.unl.edu/EPSVR/ .

Evaluation of the Effectiveness of Derived Features of AlphaFold2 on Single-Sequence Protein Binding Site Prediction

Simple Summary

With the development of artificial intelligence, researchers can roughly predict the crystal structure of a protein by computer without the need for biological experiments, which provides new ideas and solutions to problems, such as protein-protein interaction and drug-target predictions. In this study, we proposed strategies to combine predicted protein structures with deep learning networks and evaluated them on different protein binding site prediction tasks. Our computational experiment results showed that all proposed strategies could effectively encode structural information for deep learning models.

Abstract

Though AlphaFold2 has attained considerably high precision on protein structure prediction, it is reported that directly inputting coordinates into deep learning networks cannot achieve desirable results on downstream tasks. Thus, how to process and encode the predicted results into effective forms that deep learning models can understand to improve the performance of downstream tasks is worth exploring. In this study, we tested the effects of five processing strategies of coordinates on two single-sequence protein binding site prediction tasks. These five strategies are spatial filtering, the singular value decomposition of a distance map, calculating the secondary structure feature, and the relative accessible surface area feature of proteins. The computational experiment results showed that all strategies were suitable and effective methods to encode structural information for deep learning models. In addition, by performing a case study of a mutated protein, we showed that the spatial filtering strategy could introduce structural changes into HHblits profiles and deep learning networks when protein mutation happens. In sum, this work provides new insight into the downstream tasks of protein-molecule interaction prediction, such as predicting the binding residues of proteins and estimating the effects of mutations.

Protein-protein interaction prediction with deep learning: A comprehensive review

Most proteins perform their biological function by interacting with themselves or other molecules. Thus, one may obtain biological insights into protein functions, disease prevalence, and therapy development by identifying protein-protein interactions (PPI). However, finding the interacting and non-interacting protein pairs through experimental approaches is labour-intensive and time-consuming, owing to the variety of proteins. Hence, protein-protein interaction and protein-ligand binding problems have drawn attention in the fields of bioinformatics and computer-aided drug discovery. Deep learning methods paved the way for scientists to predict the 3-D structure of proteins from genomes, predict the functions and attributes of a protein, and modify and design new proteins to provide desired functions. This review focuses on recent deep learning methods applied to problems including predicting protein functions, protein-protein interaction and their sites, protein-ligand binding, and protein design.

Integrated structure-based protein interface prediction

Background

Identifying protein interfaces can inform how proteins interact with their binding partners, uncover the regulatory mechanisms that control biological functions and guide the development of novel therapeutic agents. A variety of computational approaches have been developed for predicting a protein’s interfacial residues from its known sequence and structure. Methods using the known three-dimensional structures of proteins can be template-based or template-free. Template-based methods have limited success in predicting interfaces when homologues with known complex structures are not available to use as templates. The prediction performance of template-free methods that only rely only upon proteins’ intrinsic properties is limited by the amount of biologically relevant features that can be included in an interface prediction model.

Results

We describe the development of an integrated method for protein interface prediction (ISPIP) to explore the hypothesis that the efficacy of a computational prediction method of protein binding sites can be enhanced by using a combination of methods that rely on orthogonal structure-based properties of a query protein, combining and balancing both template-free and template-based features. ISPIP is a method that integrates these approaches through simple linear or logistic regression models and more complex decision tree models. On a diverse test set of 156 query proteins, ISPIP outperforms each of its individual classifiers in identifying protein binding interfaces.

Conclusions

The integrated method captures the best performance of individual classifiers and delivers an improved interface prediction. The method is robust and performs well even when one of the individual classifiers performs poorly on a particular query protein. This work demonstrates that integrating orthogonal methods that depend on different structural properties of proteins performs better at interface prediction than any individual classifier alone.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04852-2.

In Silico Identification of Potential Sites for a Plastic-Degrading Enzyme by a Reverse Screening through the Protein Sequence Space and Molecular Dynamics Simulations

The accumulation of polyethylene terephthalate (PET) seriously harms the environment because of its high resistance to degradation. The recent discovery of the bacteria-secreted biodegradation enzyme, PETase, sheds light on PET recycling; however, the degradation efficiency is far from practical use. Here, in silico alanine scanning mutagenesis (ASM) and site-saturation mutagenesis (SSM) were employed to construct the protein sequence space from binding energy of the PETase–PET interaction to identify the number and position of mutation sites and their appropriate side-chain properties that could improve the PETase–PET interaction. The binding mechanisms of the potential PETase variant were investigated through atomistic molecular dynamics simulations. The results show that up to two mutation sites of PETase are preferable for use in protein engineering to enhance the PETase activity, and the proper side chain property depends on the mutation sites. The predicted variants agree well with prior experimental studies. Particularly, the PETase variants with S238C or Q119F could be a potential candidate for improving PETase. Our combination of in silico ASM and SSM could serve as an alternative protocol for protein engineering because of its simplicity and reliability. In addition, our findings could lead to PETase improvement, offering an important contribution towards a sustainable future.

Structure-aware protein-protein interaction site prediction using deep graph convolutional network

MOTIVATION

Protein-protein interactions (PPI) play crucial roles in many biological processes, and identifying PPI sites is an important step for mechanistic understanding of diseases and design of novel drugs. Since experimental approaches for PPI site identification are expensive and time-consuming, many computational methods have been developed as screening tools. However, these methods are mostly based on neighbored features in sequence, and thus limited to capture spatial information.

RESULTS

We propose a deep graph-based framework deep Graph convolutional network for Protein-Protein-Interacting Site prediction (GraphPPIS) for PPI site prediction, where the PPI site prediction problem was converted into a graph node classification task and solved by deep learning using the initial residual and identity mapping techniques. We showed that a deeper architecture (up to eight layers) allows significant performance improvement over other sequence-based and structure-based methods by more than 12.5% and 10.5% on AUPRC and MCC, respectively. Further analyses indicated that the predicted interacting sites by GraphPPIS are more spatially clustered and closer to the native ones even when false-positive predictions are made. The results highlight the importance of capturing spatially neighboring residues for interacting site prediction.

AVAILABILITY AND IMPLEMENTATION

The datasets, the pre-computed features, and the source codes along with the pre-trained models of GraphPPIS are available at https://github.com/biomed-AI/GraphPPIS. The GraphPPIS web server is freely available at https://biomed.nscc-gz.cn/apps/GraphPPIS.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites

Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-protein interaction sites. In this article, we presented a method based on deep learning and XGBoost (called DeepPPISP-XGB) for predicting protein-protein interaction sites. The deep learning model served as a feature extractor to remove redundant information from protein sequences. The Extreme Gradient Boosting algorithm was used to construct a classifier for predicting protein-protein interaction sites. The DeepPPISP-XGB achieved the following results: area under the receiver operating characteristic curve of 0.681, a recall of 0.624, and area under the precision-recall curve of 0.339, being competitive with the state-of-the-art methods. We also validated the positive role of global features in predicting protein-protein interaction sites.

Dissecting and predicting different types of binding sites in nucleic acids based on structural information

The biological functions of DNA and RNA generally depend on their interactions with other molecules, such as small ligands, proteins and nucleic acids. However, our knowledge of the nucleic acid binding sites for different interaction partners is very limited, and identification of these critical binding regions is not a trivial work. Herein, we performed a comprehensive comparison between binding and nonbinding sites and among different categories of binding sites in these two nucleic acid classes. From the structural perspective, RNA may interact with ligands through forming binding pockets and contact proteins and nucleic acids using protruding surfaces, while DNA may adopt regions closer to the middle of the chain to make contacts with other molecules. Based on structural information, we established a feature-based ensemble learning classifier to identify the binding sites by fully using the interplay among different machine learning algorithms, feature spaces and sample spaces. Meanwhile, we designed a template-based classifier by exploiting structural conservation. The complementarity between the two classifiers motivated us to build an integrative framework for improving prediction performance. Moreover, we utilized a post-processing procedure based on the random walk algorithm to further correct the integrative predictions. Our unified prediction framework yielded promising results for different binding sites and outperformed existing methods.

An interpretable machine learning method for homo-trimeric protein interface residue-residue interaction prediction

Protein-protein interaction plays an important role in life activities. A more fine-grained analysis, such as residues and atoms level, will better benefit us to understand the mechanism for inter-protein interaction and drug design. The development of efficient computational methods to reduce trials and errors, as well as assisting experimental researchers to determine the complex structure are some of the ongoing studies in the field. The research of trimer protein interface, especially homotrimer, has been rarely studied. In this paper, we proposed an interpretable machine learning method for homo-trimeric protein interface residue pairs prediction. The structure, sequence, and physicochemical information are intergraded as feature input fed to model for training. Graph model is utilized to present spatial information for intra-protein. Matrix factorization captures the different features' interactions. Kernel function is designed to auto-acquire the adjacent information of our target residue pairs. The accuracy rate achieves 54.5% in an independent test set. Sequence and structure alignment exhibit the ability of model self-study. Our model indicates the biological significance between sequence and structure, and could be auxiliary for reducing trials and errors in the fields of protein complex determination and protein-protein docking, etc. SIGNIFICANCE: Protein complex structures are significant for understanding protein function and promising functional protein design. With data increasing, some computational tools have been developed for protein complex residue contact prediction, which is one of the most significant steps for complex structure prediction. But for homo-trimeric protein, the sequence-based deep learning predictors are infeasible for homologous sequences, and the algorithm black box prevents us from understanding of each step operation. In this way, we propose an interpreting machine learning method for homo-trimeric protein interface residue-residue interaction prediction, and the predictor shows a good performance. Our work provides a computational auxiliary way for determining the homo-trimeric proteins interface residue pairs which will be further verified by wet experiments, and and gives a hand for the downstream works, such as protein-protein docking, protein complex structure prediction and drug design.

CATH functional families predict functional sites in proteins

MOTIVATION

Identification of functional sites in proteins is essential for functional characterization, variant interpretation and drug design. Several methods are available for predicting either a generic functional site, or specific types of functional site. Here, we present FunSite, a machine learning predictor that identifies catalytic, ligand-binding and protein-protein interaction functional sites using features derived from protein sequence and structure, and evolutionary data from CATH functional families (FunFams).

RESULTS

FunSite's prediction performance was rigorously benchmarked using cross-validation and a holdout dataset. FunSite outperformed other publicly available functional site prediction methods. We show that conserved residues in FunFams are enriched in functional sites. We found FunSite's performance depends greatly on the quality of functional site annotations and the information content of FunFams in the training data. Finally, we analyze which structural and evolutionary features are most predictive for functional sites.

AVAILABILITYAND IMPLEMENTATION

https://github.com/UCL/cath-funsite-predictor.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Mechanisms of allosteric and mixed mode aromatase inhibitors

Aromatase (CYP19) catalyzes the last biosynthetic step of estrogens in mammals and is a primary drug target for hormone-related breast cancer. However, treatment with aromatase inhibitors is often associated with adverse effects and drug resistance. In this study, we used virtual screening targeting a predicted cytochrome P450 reductase binding site on aromatase to discover four novel non-steroidal aromatase inhibitors. The inhibitors have potencies comparable to the noncompetitive tamoxifen metabolite, endoxifen. Our two most potent inhibitors, AR11 and AR13, exhibit both mixed-type and competitive-type inhibition. The cytochrome P450 reductase-CYP19 coupling interface likely acts as a transient binding site. Our modeling shows that our inhibitors bind better at different sites near the catalytic site. Our results predict the location of multiple ligand binding sites on aromatase. The combination of modeling and experimental results supports the important role of the reductase binding interface as a low affinity, promiscuous ligand binding site. Our new inhibitors may be useful as alternative chemical scaffolds that may show different adverse effects profiles than current clinically used aromatase inhibitors.

DeepDISE: DNA Binding Site Prediction Using a Deep Learning Method

It is essential for future research to develop a new, reliable prediction method of DNA binding sites because DNA binding sites on DNA-binding proteins provide critical clues about protein function and drug discovery. However, the current prediction methods of DNA binding sites have relatively poor accuracy. Using 3D coordinates and the atom-type of surface protein atom as the input, we trained and tested a deep learning model to predict how likely a voxel on the protein surface is to be a DNA-binding site. Based on three different evaluation datasets, the results show that our model not only outperforms several previous methods on two commonly used datasets, but also demonstrates its robust performance to be consistent among the three datasets. The visualized prediction outcomes show that the binding sites are also mostly located in correct regions. We successfully built a deep learning model to predict the DNA binding sites on target proteins. It demonstrates that 3D protein structures plus atom-type information on protein surfaces can be used to predict the potential binding sites on a protein. This approach should be further extended to develop the binding sites of other important biological molecules.

In silico Approaches for the Design and Optimization of Interfering Peptides Against Protein-Protein Interactions

Large contact surfaces of protein-protein interactions (PPIs) remain to be an ongoing issue in the discovery and design of small molecule modulators. Peptides are intrinsically capable of exploring larger surfaces, stable, and bioavailable, and therefore bear a high therapeutic value in the treatment of various diseases, including cancer, infectious diseases, and neurodegenerative diseases. Given these promising properties, a long way has been covered in the field of targeting PPIs via peptide design strategies. In silico tools have recently become an inevitable approach for the design and optimization of these interfering peptides. Various algorithms have been developed to scrutinize the PPI interfaces. Moreover, different databases and software tools have been created to predict the peptide structures and their interactions with target protein complexes. High-throughput screening of large peptide libraries against PPIs; "hotspot" identification; structure-based and off-structure approaches of peptide design; 3D peptide modeling; peptide optimization strategies like cyclization; and peptide binding energy evaluation are among the capabilities of in silico tools. In the present study, the most recent advances in the field of in silico approaches for the design of interfering peptides against PPIs will be reviewed. The future perspective of the field and its advantages and limitations will also be pinpointed.

Decoding Protein-protein Interactions: An Overview

Drug discovery has focused on the paradigm "one drug, one target" for a long time. However, small molecules can act at multiple macromolecular targets, which serves as the basis for drug repurposing. In an effort to expand the target space, and given advances in X-ray crystallography, protein-protein interactions have become an emerging focus area of drug discovery enterprises. Proteins interact with other biomolecules and it is this intricate network of interactions that determines the behavior of the system and its biological processes. In this review, we briefly discuss networks in disease, followed by computational methods for protein-protein complex prediction. Computational methodologies and techniques employed towards objectives such as protein-protein docking, protein-protein interactions, and interface predictions are described extensively. Docking aims at producing a complex between proteins, while interface predictions identify a subset of residues on one protein that could interact with a partner, and protein-protein interaction sites address whether two proteins interact. In addition, approaches to predict hot spots and binding sites are presented along with a representative example of our internal project on the chemokine CXC receptor 3 B-isoform and predictive modeling with IP10 and PF4.

A public-private partnership for the express development of antiviral leads: a perspective view

INTRODUCTION

The COVID-19 pandemic raises the question of strategic readiness for emergent pathogens. The current case illustrates that the cost of inaction can be higher in the future. The perspective article proposes a dedicated, government-sponsored agency developing anti-viral leads against all potentially dangerous pathogen species.

AREAS COVERED

The author explores the methods of computational drug screening and in-silico synthesis and proposes a specialized government-sponsored agency focusing on leads and functioning in collaboration with a network of labs, pharma, biotech firms, and academia, in order to test each lead against multiple viral species. The agency will employ artificial intelligence and machine learning tools to cut the costs further. The algorithms are expected to receive continuous feedback from the network of partners conducting the tests.

EXPERT OPINION

The author proposes a bionic principle, emulating antibody response by producing a combinatorial diversity of high q uality generic antiviral leads, suitable for multiple potentially emerging species. The availability of multiple pre-tested agents and an even greater number of combinations would reduce the impact of the next outbreak. The methodologies developed in this effort are likely to find utility in the design of chronic disease therapeutics.

Protein–Protein Interaction Methods and Protein Phase Separation

In the last decade, newly developed experimental methods have made it possible to highlight that macromolecules in the cell milieu physically interact to support physiology. This has shifted the problem of protein–protein interaction from a microscopic, electron-density scale to a mesoscopic one. Further, nowadays there is increasing evidence that proteins in the nucleus and in the cytoplasm can aggregate in membraneless organelles for different physiological reasons. In this scenario, it is urgent to face the problem of biomolecule functional annotation with efficient computational methods, suited to extract knowledge from reliable data and transfer information across different domains of investigation. Here, we revise the present state of the art of our knowledge of protein–protein interaction and the computational methods that differently implement it. Furthermore, we explore experimental and computational features of a set of proteins involved in phase separation.

In-silico analysis to identify the role of MEN1 missense mutations in breast cancer

Background: The multiple endocrine neoplasia type 1 (MEN1) gene located on chromosome 11q13 encodes menin protein. Previously reported mutations were thought to result in loss of function of menin protein and that they are associated with multiple endocrine neoplasia 1 disorder. However, recently menin has also been characterized as an oncosuppressor protein and it was suggested that mutations in it are associated with various other tumors. Studies indicate that the menin protein stimulates the estrogen receptor (ER) that in turn increases the predisposition for inherited breast cancer.

Methods: Here, we used our supervised in-house combinatory in-silico predictor method to investigate the impact of unclassified missense mutations in MEN1 gene found in breast cancer tissue. We also examined the biophysical and biochemical properties to predict the effects of these missense variants on the menin protein stability and interactions. The results are compared with the effects of known pathogenic mutations in menin causing neoplasia.

Results: Our analysis indicates that some of the variants found in breast cancer tissue show similar pattern of destabilizing the menin protein and its interactions as the pathogenic variants associated with neoplasia. Taking together with the results of our in-silico consensus predictor, we classify missense mutations in menin protein found in breast cancer tissue into pathogenic and benign, and thus, suggesting as an indicator for early detection of elevated breast cancer risk.

CoRNeA: A Pipeline to Decrypt the Inter-Protein Interfaces from Amino Acid Sequence Information

Decrypting the interface residues of the protein complexes provides insight into the functions of the proteins and, hence, the overall cellular machinery. Computational methods have been devised in the past to predict the interface residues using amino acid sequence information, but all these methods have been majorly applied to predict for prokaryotic protein complexes. Since the composition and rate of evolution of the primary sequence is different between prokaryotes and eukaryotes, it is important to develop a method specifically for eukaryotic complexes. Here, we report a new hybrid pipeline for predicting the protein-protein interaction interfaces in a pairwise manner from the amino acid sequence information of the interacting proteins. It is based on the framework of Co-evolution, machine learning (Random Forest), and Network Analysis named CoRNeA trained specifically on eukaryotic protein complexes. We use Co-evolution, physicochemical properties, and contact potential as major group of features to train the Random Forest classifier. We also incorporate the intra-contact information of the individual proteins to eliminate false positives from the predictions keeping in mind that the amino acid sequence of a protein also holds information for its own folding and not only the interface propensities. Our prediction on example datasets shows that CoRNeA not only enhances the prediction of true interface residues but also reduces false positive rates significantly.

Structural Characterization of Carbonic Anhydrase VIII and Effects of Missense Single Nucleotide Variations to Protein Structure and Function

Human carbonic anhydrase 8 (CA-VIII) is an acatalytic isoform of the α -CA family. Though the protein cannot hydrate CO2, CA-VIII is essential for calcium (Ca2+) homeostasis within the body, and achieves this by allosterically inhibiting the binding of inositol 1,4,5-triphosphate (IP3) to the IP3 receptor type 1 (ITPR1) protein. However, the mechanism of interaction of CA-VIII to ITPR1 is not well understood. In addition, functional defects to CA-VIII due to non-synonymous single nucleotide polymorphisms (nsSNVs) result in Ca2+ dysregulation and the development of the phenotypes such as cerebellar ataxia, mental retardation and disequilibrium syndrome 3 (CAMRQ3). The pathogenesis of CAMRQ3 is also not well understood. The structure and function of CA-VIII was characterised, and pathogenesis of CAMRQ3 investigated. Structural and functional characterisation of CA-VIII was conducted through SiteMap and CPORT to identify potential binding site residues. The effects of four pathogenic nsSNVs, S100A, S100P, G162R and R237Q, and two benign S100L and E109D variants on CA-VIII structure and function was then investigated using molecular dynamics (MD) simulations, dynamic cross correlation (DCC) and dynamic residue network (DRN) analysis. SiteMap and CPORT analyses identified 38 unique CA-VIII residues that could potentially bind to ITPR1. MD analysis revealed less conformational sampling within the variant proteins and highlighted potential increases to variant protein rigidity. Dynamic cross correlation (DCC) showed that wild-type (WT) protein residue motion is predominately anti-correlated, with variant proteins showing no correlation to greater residue correlation. DRN revealed variant-associated increases to the accessibility of the N-terminal binding site residues, which could have implications for associations with ITPR1, and further highlighted differences to the mechanism of benign and pathogenic variants. SNV presence is associated with a reduction to the usage of Trp37 in all variants, which has implications for CA-VIII stability. The differences to variant mechanisms can be further investigated to understand pathogenesis of CAMRQ3, enhancing precision medicine-related studies into CA-VIII.

Analysis of protein missense alterations by combining sequence- and structure-based methods

BACKGROUND

Different types of in silico approaches can be used to predict the phenotypic consequence of missense variants. Such algorithms are often categorized as sequence based or structure based, when they necessitate 3D structural information. In addition, many other in silico tools, not dedicated to the analysis of variants, can be used to gain additional insights about the possible mechanisms at play.

METHODS

Here we applied different computational approaches to a set of 20 known missense variants present on different proteins (CYP, complement factor B, antithrombin and blood coagulation factor VIII). The tools that were used include fast computational approaches and web servers such as PolyPhen-2, PopMusic, DUET, MaestroWeb, SAAFEC, Missense3D, VarSite, FlexPred, PredyFlexy, Clustal Omega, meta-PPISP, FTMap, ClusPro, pyDock, PPM, RING, Cytoscape, and ChannelsDB.

RESULTS

We observe some conflicting results among the methods but, most of the time, the combination of several engines helped to clarify the potential impacts of the amino acid substitutions.

CONCLUSION

Combining different computational approaches including some that were not developed to investigate missense variants help to predict the possible impact of the amino acid substitutions. Yet, when the modified residues are involved in a salt-bridge, the tools tend to fail, even when the analysis is performed in 3D. Thus, interactive structural analysis with molecular graphics packages such as Chimera or PyMol or others are still needed to clarify automatic prediction.

Prediction and targeting of GPCR oligomer interfaces

GPCR oligomerization has emerged as a hot topic in the GPCR field in the last years. Receptors that are part of these oligomers can influence each other's function, although it is not yet entirely understood how these interactions work. The existence of such a highly complex network of interactions between GPCRs generates the possibility of alternative targets for new therapeutic approaches. However, challenges still exist in the characterization of these complexes, especially at the interface level. Different experimental approaches, such as FRET or BRET, are usually combined to study GPCR oligomer interactions. Computational methods have been applied as a useful tool for retrieving information from GPCR sequences and the few X-ray-resolved oligomeric structures that are accessible, as well as for predicting new and trustworthy GPCR oligomeric interfaces. Machine-learning (ML) approaches have recently helped with some hindrances of other methods. By joining and evaluating multiple structure-, sequence- and co-evolution-based features on the same algorithm, it is possible to dilute the issues of particular structures and residues that arise from the experimental methodology into all-encompassing algorithms capable of accurately predict GPCR-GPCR interfaces. All these methods used as a single or a combined approach provide useful information about GPCR oligomerization and its role in GPCR function and dynamics. Altogether, we present experimental, computational and machine-learning methods used to study oligomers interfaces, as well as strategies that have been used to target these dynamic complexes.

Multiepitope Subunit Vaccine Design against COVID-19 Based on the Spike Protein of SARS-CoV-2: An In Silico Analysis

The global health crisis caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causal agent of COVID-19, has resulted in a negative impact on human health and on social and economic activities worldwide. Researchers around the globe need to design and develop successful therapeutics as well as vaccines against the novel COVID-19 disease. In the present study, we conducted comprehensive computer-assisted analysis on the spike glycoprotein of SARS-CoV-2 in order to design a safe and potent multiepitope vaccine. In silico epitope prioritization shortlisted six HLA I epitopes and six B-cell-derived HLA II epitopes. These high-ranked epitopes were all connected to each other via flexible GPGPG linkers, and at the N-terminus side, the sequence of Cholera Toxin β subunit was attached via an EAAAK linker. Structural modeling of the vaccine was performed, and molecular docking analysis strongly suggested a positive association of a multiepitope vaccine with Toll-like Receptor 3. The structural investigations of the vaccine-TLR3 complex revealed the formation of fifteen interchain hydrogen bonds, thus validating its integrity and stability. Moreover, it was found that this interaction was thermodynamically feasible. In conclusion, our data supports the proposition that a multiepitope vaccine will provide protective immunity against COVID-19. However, further in vivo and in vitro experiments are needed to validate the immunogenicity and safety of the candidate vaccine.

EPCES and EPSVR: Prediction of B-Cell Antigenic Epitopes on Protein Surfaces with Conformational Information

Accurate prediction of discontinuous antigenic epitopes is important for immunologic research and medical applications, but it is not an easy problem. Currently, there are only a few prediction servers available, though discontinuous epitopes constitute the majority of all B-cell antigenic epitopes. In this chapter, we describe two online servers, EPCES and EPSVR, for discontinuous epitope prediction. All methods were benchmarked by a curated independent test set, in which all antigens had no complex structures with the antibody, and their epitopes were identified by various biochemical experiments. The servers and all datasets are available at http://sysbio.unl.edu/EPCES/ and http://sysbio.unl.edu/EPSVR/ .

Identifying protein-protein interface via a novel multi-scale local sequence and structural representation

Background

Protein-protein interaction plays a key role in a multitude of biological processes, such as signal transduction, de novo drug design, immune responses, and enzymatic activities. Gaining insights of various binding abilities can deepen our understanding of the interaction. It is of great interest to understand how proteins in a complex interact with each other. Many efficient methods have been developed for identifying protein-protein interface.

Results

In this paper, we obtain the local information on protein-protein interface, through multi-scale local average block and hexagon structure construction. Given a pair of proteins, we use a trained support vector regression (SVR) model to select best configurations. On Benchmark v4.0, our method achieves average I_rmsd value of 3.28Å and overall F_nat value of 63%, which improves upon I_rmsd of 3.89Å and F_nat of 49% for ZRANK, and I_rmsd of 3.99Å and F_nat of 46% for ClusPro. On CAPRI targets, our method achieves average I_rmsd value of 3.45Å and overall F_nat value of 46%, which improves upon I_rmsd of 4.18Å and F_nat of 40% for ZRANK, and I_rmsd of 5.12Å and F_nat of 32% for ClusPro. The success rates by our method, FRODOCK 2.0, InterEvDock and SnapDock on Benchmark v4.0 are 41.5%, 29.0%, 29.4% and 37.0%, respectively.

Conclusion

Experiments show that our method performs better than some state-of-the-art methods, based on the prediction quality improved in terms of CAPRI evaluation criteria. All these results demonstrate that our method is a valuable technological tool for identifying protein-protein interface.

Identification and visualization of protein binding regions with the ArDock server

ArDock (ardock.ibcp.fr) is a structural bioinformatics web server for the prediction and the visualization of potential interaction regions at protein surfaces. ArDock ranks the surface residues of a protein according to their tendency to form interfaces in a set of predefined docking experiments between the query protein and a set of arbitrary protein probes. The ArDock methodology is derived from large scale cross-docking studies where it was observed that randomly chosen proteins tend to dock in a non-random way at protein surfaces. The method predicts interaction site of the protein, or alternate interfaces in the case of proteins with multiple interaction modes. The server takes a protein structure as input and computes a score for each surface residue. Its output focuses on the interactive visualization of results and on interoperability with other services.

Gain of native conformation of Aurora A S155R mutant by small molecules

Aurora A is a mitotic serine/threonine kinase protein that is a proposed target of the first-line anticancer drug design. It has been found to be overexpressed in many human cancer cells, including hematological, breast, and colorectal. Here, we focus on a particular somatic mutant S155R of Aurora kinase A protein, whose activity decreases because of loss of interaction with a TPX2 protein that results in ectopic expression of the Aurora kinase A protein, which contributes chromosome instability, centrosome amplification, and oncogenic transformation. The primary target of this study is to select a drug molecule whose binding results in gaining S155R mutant interaction with TPX2. The computational methodology applied in this study involves mapping of hotspots (for uncompetitive binding), virtual screening, protein-ligand docking, postdocking optimization, and protein-protein docking approach. In this study, we screen and validate ZINC968264, which acts as a potential molecule that can improve the loss of function occurred because of mutation (S155R) in Aurora A. Our approaches pave a suitable path to design a potential drug against physiological condition manifested because of S155R mutant in Aurora A.

Advances in In-silico B-cell Epitope Prediction

Identification of B-cell epitopes in target antigens is one of the most crucial steps for epitopebased vaccine development, immunodiagnostic tests, antibody production, and disease diagnosis and therapy. Experimental methods for B-cell epitope mapping are time consuming, costly and labor intensive; in the meantime, various in-silico methods are proposed to predict both linear and conformational B-cell epitopes. The accurate identification of B-cell epitopes presents major challenges for immunoinformaticians. In this paper, we have comprehensively reviewed in-silico methods for B-cell epitope identification. The aim of this review is to stimulate the development of better tools which could improve the identification of B-cell epitopes, and further for the development of therapeutic antibodies and diagnostic tools.

Predicting protein-ligand binding residues with deep convolutional neural networks

Background

Ligand-binding proteins play key roles in many biological processes. Identification of protein-ligand binding residues is important in understanding the biological functions of proteins. Existing computational methods can be roughly categorized as sequence-based or 3D-structure-based methods. All these methods are based on traditional machine learning. In a series of binding residue prediction tasks, 3D-structure-based methods are widely superior to sequence-based methods. However, due to the great number of proteins with known amino acid sequences, sequence-based methods have considerable room for improvement with the development of deep learning. Therefore, prediction of protein-ligand binding residues with deep learning requires study.

Results

In this study, we propose a new sequence-based approach called DeepCSeqSite for ab initio protein-ligand binding residue prediction. DeepCSeqSite includes a standard edition and an enhanced edition. The classifier of DeepCSeqSite is based on a deep convolutional neural network. Several convolutional layers are stacked on top of each other to extract hierarchical features. The size of the effective context scope is expanded as the number of convolutional layers increases. The long-distance dependencies between residues can be captured by the large effective context scope, and stacking several layers enables the maximum length of dependencies to be precisely controlled. The extracted features are ultimately combined through one-by-one convolution kernels and softmax to predict whether the residues are binding residues. The state-of-the-art ligand-binding method COACH and some of its submethods are selected as baselines. The methods are tested on a set of 151 nonredundant proteins and three extended test sets. Experiments show that the improvement of the Matthews correlation coefficient (MCC) is no less than 0.05. In addition, a training data augmentation method that slightly improves the performance is discussed in this study.

Conclusions

Without using any templates that include 3D-structure data, DeepCSeqSite significantlyoutperforms existing sequence-based and 3D-structure-based methods, including COACH. Augmentation of the training sets slightly improves the performance. The model, code and datasets are available at https://github.com/yfCuiFaith/DeepCSeqSite.

Protein-protein binding supersites

The lack of a deep understanding of how proteins interact remains an important roadblock in advancing efforts to identify binding partners and uncover the corresponding regulatory mechanisms of the functions they mediate. Understanding protein-protein interactions is also essential for designing specific chemical modifications to develop new reagents and therapeutics. We explored the hypothesis of whether protein interaction sites serve as generic biding sites for non-cognate protein ligands, just as it has been observed for small-molecule-binding sites in the past. Using extensive computational docking experiments on a test set of 241 protein complexes, we found that indeed there is a strong preference for non-cognate ligands to bind to the cognate binding site of a receptor. This observation appears to be robust to variations in docking programs, types of non-cognate protein probes, sizes of binding patches, relative sizes of binding patches and full-length proteins, and the exploration of obligate and non-obligate complexes. The accuracy of the docking scoring function appears to play a role in defining the correct site. The frequency of interaction of unrelated probes recognizing the binding interface was utilized in a simple prediction algorithm that showed accuracy competitive with other state of the art methods.

Protein-protein interaction specificity is captured by contact preferences and interface composition

Motivation

Large-scale computational docking will be increasingly used in future years to discriminate protein–protein interactions at the residue resolution. Complete cross-docking experiments make in silico reconstruction of protein–protein interaction networks a feasible goal. They ask for efficient and accurate screening of the millions structural conformations issued by the calculations.

Results

We propose CIPS (Combined Interface Propensity for decoy Scoring), a new pair potential combining interface composition with residue–residue contact preference. CIPS outperforms several other methods on screening docking solutions obtained either with all-atom or with coarse-grain rigid docking. Further testing on 28 CAPRI targets corroborates CIPS predictive power over existing methods. By combining CIPS with atomic potentials, discrimination of correct conformations in all-atom structures reaches optimal accuracy. The drastic reduction of candidate solutions produced by thousands of proteins docked against each other makes large-scale docking accessible to analysis.

Availability and implementation

CIPS source code is freely available at http://www.lcqb.upmc.fr/CIPS.

Supplementary information

Supplementary data are available at Bioinformatics online.

Evolution of In Silico Strategies for Protein-Protein Interaction Drug Discovery

The advent of advanced molecular modeling software, big data analytics, and high-speed processing units has led to the exponential evolution of modern drug discovery and better insights into complex biological processes and disease networks. This has progressively steered current research interests to understanding protein-protein interaction (PPI) systems that are related to a number of relevant diseases, such as cancer, neurological illnesses, metabolic disorders, etc. However, targeting PPIs are challenging due to their "undruggable" binding interfaces. In this review, we focus on the current obstacles that impede PPI drug discovery, and how recent discoveries and advances in in silico approaches can alleviate these barriers to expedite the search for potential leads, as shown in several exemplary studies. We will also discuss about currently available information on PPI compounds and systems, along with their usefulness in molecular modeling. Finally, we conclude by presenting the limits of in silico application in drug discovery and offer a perspective in the field of computer-aided PPI drug discovery.

Sequence-based prediction of physicochemical interactions at protein functional sites using a function-and-interaction-annotated domain profile database

Background

Identifying protein functional sites (PFSs) and, particularly, the physicochemical interactions at these sites is critical to understanding protein functions and the biochemical reactions involved. Several knowledge-based methods have been developed for the prediction of PFSs; however, accurate methods for predicting the physicochemical interactions associated with PFSs are still lacking.

Results

In this paper, we present a sequence-based method for the prediction of physicochemical interactions at PFSs. The method is based on a functional site and physicochemical interaction-annotated domain profile database, called fiDPD, which was built using protein domains found in the Protein Data Bank. This method was applied to 13 target proteins from the very recent Critical Assessment of Structure Prediction (CASP10/11), and our calculations gave a Matthews correlation coefficient (MCC) value of 0.66 for PFS prediction and an 80% recall in the prediction of the associated physicochemical interactions.

Conclusions

Our results show that, in addition to the PFSs, the physical interactions at these sites are also conserved in the evolution of proteins. This work provides a valuable sequence-based tool for rational drug design and side-effect assessment. The method is freely available and can be accessed at http://202.119.249.49.

Heterodimer Binding Scaffolds Recognition via the Analysis of Kinetically Hot Residues

Physical interactions between proteins are often difficult to decipher. The aim of this paper is to present an algorithm that is designed to recognize binding patches and supporting structural scaffolds of interacting heterodimer proteins using the Gaussian Network Model (GNM). The recognition is based on the (self) adjustable identification of kinetically hot residues and their connection to possible binding scaffolds. The kinetically hot residues are residues with the lowest entropy, i.e., the highest contribution to the weighted sum of the fastest modes per chain extracted via GNM. The algorithm adjusts the number of fast modes in the GNM's weighted sum calculation using the ratio of predicted and expected numbers of target residues (contact and the neighboring first-layer residues). This approach produces very good results when applied to dimers with high protein sequence length ratios. The protocol's ability to recognize near native decoys was compared to the ability of the residue-level statistical potential of Lu and Skolnick using the Sternberg and Vakser decoy dimers sets. The statistical potential produced better overall results, but in a number of cases its predicting ability was comparable, or even inferior, to the prediction ability of the adjustable GNM approach. The results presented in this paper suggest that in heterodimers at least one protein has interacting scaffold determined by the immovable, kinetically hot residues. In many cases, interacting proteins (especially if being of noticeably different sizes) either behave as a rigid lock and key or, presumably, exhibit the opposite dynamic behavior. While the binding surface of one protein is rigid and stable, its partner's interacting scaffold is more flexible and adaptable.

Hot-spot analysis for drug discovery targeting protein-protein interactions

INTRODUCTION

Protein-protein interactions are important for biological processes and pathological situations, and are attractive targets for drug discovery. However, rational drug design targeting protein-protein interactions is still highly challenging. Hot-spot residues are seen as the best option to target such interactions, but their identification requires detailed structural and energetic characterization, which is only available for a tiny fraction of protein interactions. Areas covered: In this review, the authors cover a variety of computational methods that have been reported for the energetic analysis of protein-protein interfaces in search of hot-spots, and the structural modeling of protein-protein complexes by docking. This can help to rationalize the discovery of small-molecule inhibitors of protein-protein interfaces of therapeutic interest. Computational analysis and docking can help to locate the interface, molecular dynamics can be used to find suitable cavities, and hot-spot predictions can focus the search for inhibitors of protein-protein interactions. Expert opinion: A major difficulty for applying rational drug design methods to protein-protein interactions is that in the majority of cases the complex structure is not available. Fortunately, computational docking can complement experimental data. An interesting aspect to explore in the future is the integration of these strategies for targeting PPIs with large-scale mutational analysis.

Interactome INSIDER: a structural interactome browser for genomic studies

We present Interactome INSIDER, a tool to link genomic variant information with structural protein-protein interactomes. Underlying this tool is the application of machine learning to predict protein interaction interfaces for 185,957 protein interactions with previously unresolved interfaces, in human and 7 model organisms, including the entire experimentally determined human binary interactome. Predicted interfaces exhibit similar functional properties as known interfaces, including enrichment for disease mutations and recurrent cancer mutations. Through 2,164 de novo mutagenesis experiments, we show that mutations of predicted and known interface residues disrupt interactions at a similar rate, and much more frequently than mutations outside of predicted interfaces. To spur functional genomic studies, Interactome INSIDER (http://interactomeinsider.yulab.org) enables users to identify whether variants or disease mutations are enriched in known and predicted interaction interfaces at various resolutions. Users may explore known population variants, disease mutations, and somatic cancer mutations, or upload their own set of mutations for this purpose.