ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction.

Predicting the functional sites of a protein from its structure, such as the binding sites of small molecules, other proteins or antibodies, sheds light on its function in vivo. Currently, two classes of methods prevail: machine learning models built on top of handcrafted features and comparative modeling. They are, respectively, limited by the expressivity of the handcrafted features and the availability of similar proteins. Here, we introduce ScanNet, an end-to-end, interpretable geometric deep learning model that learns features directly from 3D structures. ScanNet builds representations of atoms and amino acids based on the spatio-chemical arrangement of their neighbors. We train ScanNet for detecting protein-protein and protein-antibody binding sites, demonstrate its accuracy-including for unseen protein folds-and interpret the filters learned. Finally, we predict epitopes of the SARS-CoV-2 spike protein, validating known antigenic regions and predicting previously uncharacterized ones. Overall, ScanNet is a versatile, powerful and interpretable model suitable for functional site prediction tasks. A webserver for ScanNet is available from http://bioinfo3d.cs.tau.ac.il/ScanNet/ .

Funneling modulatory peptide design with generative models: Discovery and characterization of disruptors of calcineurin protein-protein interactions.

Design of peptide binders is an attractive strategy for targeting "undruggable" protein-protein interfaces. Current design protocols rely on the extraction of an initial sequence from one known protein interactor of the target protein, followed by in-silico or in-vitro mutagenesis-based optimization of its binding affinity. Wet lab protocols can explore only a minor portion of the vast sequence space and cannot efficiently screen for other desirable properties such as high specificity and low toxicity, while in-silico design requires intensive computational resources and often relies on simplified binding models. Yet, for a multivalent protein target, dozens to hundreds of natural protein partners already exist in the cellular environment. Here, we describe a peptide design protocol that harnesses this diversity via a machine learning generative model. After identifying putative natural binding fragments by literature and homology search, a compositional Restricted Boltzmann Machine is trained and sampled to yield hundreds of diverse candidate peptides. The latter are further filtered via flexible molecular docking and an in-vitro microchip-based binding assay. We validate and test our protocol on calcineurin, a calcium-dependent protein phosphatase involved in various cellular pathways in health and disease. In a single screening round, we identified multiple 16-length peptides with up to six mutations from their closest natural sequence that successfully interfere with the binding of calcineurin to its substrates. In summary, integrating protein interaction and sequence databases, generative modeling, molecular docking and interaction assays enables the discovery of novel protein-protein interaction modulators.

Discriminating physiological from non-physiological interfaces in structures of protein complexes: A community-wide study.

Reliably scoring and ranking candidate models of protein complexes and assigning their oligomeric state from the structure of the crystal lattice represent outstanding challenges. A community-wide effort was launched to tackle these challenges. The latest resources on protein complexes and interfaces were exploited to derive a benchmark dataset consisting of 1677 homodimer protein crystal structures, including a balanced mix of physiological and non-physiological complexes. The non-physiological complexes in the benchmark were selected to bury a similar or larger interface area than their physiological counterparts, making it more difficult for scoring functions to differentiate between them. Next, 252 functions for scoring protein-protein interfaces previously developed by 13 groups were collected and evaluated for their ability to discriminate between physiological and non-physiological complexes. A simple consensus score generated using the best performing score of each of the 13 groups, and a cross-validated Random Forest (RF) classifier were created. Both approaches showed excellent performance, with an area under the Receiver Operating Characteristic (ROC) curve of 0.93 and 0.94, respectively, outperforming individual scores developed by different groups. Additionally, AlphaFold2 engines recalled the physiological dimers with significantly higher accuracy than the non-physiological set, lending support to the reliability of our benchmark dataset annotations. Optimizing the combined power of interface scoring functions and evaluating it on challenging benchmark datasets appears to be a promising strategy.

Pep-Whisperer: Inhibitory peptide design.

Designing peptides for protein-protein interaction inhibition is of significant interest in computer-aided drug design. Such inhibitory peptides could mimic and compete with the binding of the partner protein to the inhibition target. Experimental peptide design is a laborious, time consuming, and expensive multi-step process. Therefore, in silico peptide design can be beneficial for achieving this task. We present a novel algorithm, Pep-Whisperer, which aims to design inhibitory peptides for protein-protein interaction. The desirable peptides would have a relatively high predicted binding affinity to the target protein in a given protein-protein complex. The algorithm outputs linear peptides which are based on an initial template. The template could either be a peptide which is retrieved from the interaction site, or a patch of nonconsecutive amino acids from the protein-protein interface which is completed to a linear peptide by short polyalanine linkers. In addition, the algorithm takes into consideration the conservation of the amino acids in the ligand-protein binding site by using evolutionary information for choosing the preferred amino acids in each position of the designed peptide. Our algorithm was able to design peptides with high predicted binding affinity to the target protein. The method is fully automated and available as a web server at http://bioinfo3d.cs.tau.ac.il/PepWhisperer/.

SnapDock-template-based docking by Geometric Hashing.

MOTIVATION: A highly efficient template-based protein-protein docking algorithm, nicknamed SnapDock, is presented. It employs a Geometric Hashing-based structural alignment scheme to align the target proteins to the interfaces of non-redundant protein-protein interface libraries. Docking of a pair of proteins utilizing the 22 600 interface PIFACE library is performed in < 2 min on the average. A flexible version of the algorithm allowing hinge motion in one of the proteins is presented as well. RESULTS: To evaluate the performance of the algorithm a blind re-modelling of 3547 PDB complexes, which have been uploaded after the PIFACE publication has been performed with success ratio of about 35%. Interestingly, a similar experiment with the template free PatchDock docking algorithm yielded a success rate of about 23% with roughly 1/3 of the solutions different from those of SnapDock. Consequently, the combination of the two methods gave a 42% success ratio. AVAILABILITY AND IMPLEMENTATION: A web server of the application is under development. CONTACT: michaelestrin@gmail.com or wolfson@tau.ac.il.

Structure-based in silico identification of ubiquitin-binding domains provides insights into the ALIX-V:ubiquitin complex and retrovirus budding.

The ubiquitylation signal promotes trafficking of endogenous and retroviral transmembrane proteins. The signal is decoded by a large set of ubiquitin (Ub) receptors that tether Ub-binding domains (UBDs) to the trafficking machinery. We developed a structure-based procedure to scan the protein data bank for hidden UBDs. The screen retrieved many of the known UBDs. Intriguingly, new potential UBDs were identified, including the ALIX-V domain. Pull-down, cross-linking and E3-independent ubiquitylation assays biochemically corroborated the in silico findings. Guided by the output model, we designed mutations at the postulated ALIX-V:Ub interface. Biophysical affinity measurements using microscale-thermophoresis of wild-type and mutant proteins revealed some of the interacting residues of the complex. ALIX-V binds mono-Ub with a K(d) of 119 µM. We show that ALIX-V oligomerizes with a Hill coefficient of 5.4 and IC(50) of 27.6 µM and that mono-Ub induces ALIX-V oligomerization. Moreover, we show that ALIX-V preferentially binds K63 di-Ub compared with mono-Ub and K48 di-Ub. Finally, an in vivo functionality assay demonstrates the significance of ALIX-V:Ub interaction in equine infectious anaemia virus budding. These results not only validate the new procedure, but also demonstrate that ALIX-V directly interacts with Ub in vivo and that this interaction can influence retroviral budding.

PinaColada: peptide-inhibitor ant colony ad-hoc design algorithm.

MOTIVATION: Design of protein-protein interaction (PPI) inhibitors is a major challenge in Structural Bioinformatics. Peptides, especially short ones (5-15 amino acid long), are natural candidates for inhibition of protein-protein complexes due to several attractive features such as high structural compatibility with the protein binding site (mimicking the surface of one of the proteins), small size and the ability to form strong hotspot binding connections with the protein surface. Efficient rational peptide design is still a major challenge in computer aided drug design, due to the huge space of possible sequences, which is exponential in the length of the peptide, and the high flexibility of peptide conformations. RESULTS: In this article we present PinaColada, a novel computational method for the design of peptide inhibitors for protein-protein interactions. We employ a version of the ant colony optimization heuristic, which is used to explore the exponential space ([Formula: see text]) of length n peptide sequences, in combination with our fast robotics motivated PepCrawler algorithm, which explores the conformational space for each candidate sequence. PinaColada is being run in parallel, on a DELL PowerEdge 2.8 GHZ computer with 20 cores and 256 GB memory, and takes up to 24 h to design a peptide of 5-15 amino acids length. AVAILABILITY AND IMPLEMENTATION: An online server available at: http://bioinfo3d.cs.tau.ac.il/PinaColada/. CONTACT: danielza@post.tau.ac.il; wolfson@tau.ac.il.

Memdock: an α-helical membrane protein docking algorithm.

MOTIVATION: A wide range of fundamental biological processes are mediated by membrane proteins. Despite their large number and importance, less than 1% of all 3D protein structures deposited in the Protein Data Bank are of membrane proteins. This is mainly due to the challenges of crystallizing such proteins or performing NMR spectroscopy analyses. All the more so, there is only a small number of membrane protein-protein complexes with known structure. Therefore, developing computational tools for docking membrane proteins is crucial. Numerous methods for docking globular proteins exist, however few have been developed especially for membrane proteins and designed to address docking within the lipid bilayer environment. RESULTS: We present a novel algorithm, Memdock, for docking α-helical membrane proteins which takes into consideration the lipid bilayer environment for docking as well as for refining and ranking the docking candidates. We show that our algorithm improves both the docking accuracy and the candidates ranking compared to a standard protein-protein docking algorithm. AVAILABILITY AND IMPLEMENTATION: http://bioinfo3d.cs.tau.ac.il/Memdock/ CONTACTS: namih@tau.ac.il or wolfson@tau.ac.il SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DockStar: a novel ILP-based integrative method for structural modeling of multimolecular protein complexes.

MOTIVATION: Atomic resolution modeling of large multimolecular assemblies is a key task in Structural Cell Biology. Experimental techniques can provide atomic resolution structures of single proteins and small complexes, or low resolution data of large multimolecular complexes. RESULTS: We present a novel integrative computational modeling method, which integrates both low and high resolution experimental data. The algorithm accepts as input atomic resolution structures of the individual subunits obtained from X-ray, NMR or homology modeling, and interaction data between the subunits obtained from mass spectrometry. The optimal assembly of the individual subunits is formulated as an Integer Linear Programming task. The method was tested on several representative complexes, both in the bound and unbound cases. It placed correctly most of the subunits of multimolecular complexes of up to 16 subunits and significantly outperformed the CombDock and Haddock multimolecular docking methods. AVAILABILITY AND IMPLEMENTATION: http://bioinfo3d.cs.tau.ac.il/DockStar CONTACT: naamaamir@mail.tau.ac.il or wolfson@tau.ac.il SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Conformational transitions in human translin enable nucleic acid binding.

Translin is a highly conserved RNA- and DNA-binding protein that plays essential roles in eukaryotic cells. Human translin functions as an octamer, but in the octameric crystallographic structure, the residues responsible for nucleic acid binding are not accessible. Moreover, electron microscopy data reveal very different octameric configurations. Consequently, the functional assembly and the mechanism of nucleic acid binding by the protein remain unclear. Here, we present an integrative study combining small-angle X-ray scattering (SAXS), site-directed mutagenesis, biochemical analysis and computational techniques to address these questions. Our data indicate a significant conformational heterogeneity for translin in solution, formed by a lesser-populated compact octameric state resembling the previously solved X-ray structure, and a highly populated open octameric state that had not been previously identified. On the other hand, our SAXS data and computational analyses of translin in complex with the RNA oligonucleotide (GU)12 show that the internal cavity found in the octameric assemblies can accommodate different nucleic acid conformations. According to this model, the nucleic acid binding residues become accessible for binding, which facilitates the entrance of the nucleic acids into the cavity. Our data thus provide a structural basis for the functions that translin performs in RNA metabolism and transport.

Blind prediction of interfacial water positions in CAPRI.

We report the first assessment of blind predictions of water positions at protein-protein interfaces, performed as part of the critical assessment of predicted interactions (CAPRI) community-wide experiment. Groups submitting docking predictions for the complex of the DNase domain of colicin E2 and Im2 immunity protein (CAPRI Target 47), were invited to predict the positions of interfacial water molecules using the method of their choice. The predictions-20 groups submitted a total of 195 models-were assessed by measuring the recall fraction of water-mediated protein contacts. Of the 176 high- or medium-quality docking models-a very good docking performance per se-only 44% had a recall fraction above 0.3, and a mere 6% above 0.5. The actual water positions were in general predicted to an accuracy level no better than 1.5 Å, and even in good models about half of the contacts represented false positives. This notwithstanding, three hotspot interface water positions were quite well predicted, and so was one of the water positions that is believed to stabilize the loop that confers specificity in these complexes. Overall the best interface water predictions was achieved by groups that also produced high-quality docking models, indicating that accurate modelling of the protein portion is a determinant factor. The use of established molecular mechanics force fields, coupled to sampling and optimization procedures also seemed to confer an advantage. Insights gained from this analysis should help improve the prediction of protein-water interactions and their role in stabilizing protein complexes.

ParaDock: a flexible non-specific DNA--rigid protein docking algorithm.

Accurate prediction of protein-DNA complexes could provide an important stepping stone towards a thorough comprehension of vital intracellular processes. Few attempts were made to tackle this issue, focusing on binding patch prediction, protein function classification and distance constraints-based docking. We introduce ParaDock: a novel ab initio protein-DNA docking algorithm. ParaDock combines short DNA fragments, which have been rigidly docked to the protein based on geometric complementarity, to create bent planar DNA molecules of arbitrary sequence. Our algorithm was tested on the bound and unbound targets of a protein-DNA benchmark comprised of 47 complexes. With neither addressing protein flexibility, nor applying any refinement procedure, CAPRI acceptable solutions were obtained among the 10 top ranked hypotheses in 83% of the bound complexes, and 70% of the unbound. Without requiring prior knowledge of DNA length and sequence, and within <2 h per target on a standard 2.0 GHz single processor CPU, ParaDock offers a fast ab initio docking solution.

MultiFit: a web server for fitting multiple protein structures into their electron microscopy density map.

Advances in electron microscopy (EM) allow for structure determination of large biological assemblies at increasingly higher resolutions. A key step in this process is fitting multiple component structures into an EM-derived density map of their assembly. Here, we describe a web server for this task. The server takes as input a set of protein structures in the PDB format and an EM density map in the MRC format. The output is an ensemble of models ranked by their quality of fit to the density map. The models can be viewed online or downloaded from the website. The service is available at; http://salilab.org/multifit/ and http://bioinfo3d.cs.tau.ac.il/.

EvoRator2: Predicting Site-specific Amino Acid Substitutions Based on Protein Structural Information Using Deep Learning.

Multiple sequence alignments (MSAs) are the workhorse of molecular evolution and structural biology research. From MSAs, the amino acids that are tolerated at each site during protein evolution can be inferred. However, little is known regarding the repertoire of tolerated amino acids in proteins when only a few or no sequence homologs are available, such as orphan and de novo designed proteins. Here we present EvoRator2, a deep-learning algorithm trained on over 15,000 protein structures that can predict which amino acids are tolerated at any given site, based exclusively on protein structural information mined from atomic coordinate files. We show that EvoRator2 obtained satisfying results for the prediction of position-weighted scoring matrices (PSSM). We further show that EvoRator2 obtained near state-of-the-art performance on proteins with high quality structures in predicting the effect of mutations in deep mutation scanning (DMS) experiments and that for certain DMS targets, EvoRator2 outperformed state-of-the-art methods. We also show that by combining EvoRator2's predictions with those obtained by a state-of-the-art deep-learning method that accounts for the information in the MSA, the prediction of the effect of mutation in DMS experiments was improved in terms of both accuracy and stability. EvoRator2 is designed to predict which amino-acid substitutions are tolerated in such proteins without many homologous sequences, including orphan or de novo designed proteins. We implemented our approach in the EvoRator web server (https://evorator.tau.ac.il).

PepCrawler: a fast RRT-based algorithm for high-resolution refinement and binding affinity estimation of peptide inhibitors.

MOTIVATION: Design of protein-protein interaction (PPI) inhibitors is a key challenge in structural bioinformatics and computer-aided drug design. Peptides, which partially mimic the interface area of one of the interacting proteins, are natural candidates to form protein-peptide complexes competing with the original PPI. The prediction of such complexes is especially challenging due to the high flexibility of peptide conformations. RESULTS: In this article, we present PepCrawler, a new tool for deriving binding peptides from protein-protein complexes and prediction of peptide-protein complexes, by performing high-resolution docking refinement and estimation of binding affinity. By using a fast path planning approach, PepCrawler rapidly generates large amounts of flexible peptide conformations, allowing backbone and side chain flexibility. A newly introduced binding energy funnel 'steepness score' was applied for the evaluation of the protein-peptide complexes binding affinity. PepCrawler simulations predicted high binding affinity for native protein-peptide complexes benchmark and low affinity for low-energy decoy complexes. In three cases, where wet lab data are available, the PepCrawler predictions were consistent with the data. Comparing to other state of the art flexible peptide-protein structure prediction algorithms, our algorithm is very fast, and takes only minutes to run on a single PC. AVAILABILITY: http://bioinfo3d.cs.tau.ac.il/PepCrawler/ CONTACT: eladdons@tau.ac.il; wolfson@tau.ac.il.

FiberDock: a web server for flexible induced-fit backbone refinement in molecular docking.

Protein-protein docking algorithms aim to predict the structure of a complex given the atomic structures of the proteins that assemble it. The docking procedure usually consists of two main steps: docking candidate generation and their refinement. The refinement stage aims to improve the accuracy of the candidate solutions and to identify near-native solutions among them. During protein-protein interaction, both side chains and backbone change their conformation. Refinement methods should model these conformational changes in order to obtain a more accurate model of the complex. Handling protein backbone flexibility is a major challenge for docking methodologies, since backbone flexibility adds a huge number of degrees of freedom to the search space. FiberDock is the first docking refinement web server, which accounts for both backbone and side-chain flexibility. Given a set of up to 100 potential docking candidates, FiberDock models the backbone and side-chain movements that occur during the interaction, refines the structures and scores them according to an energy function. The FiberDock web server is free and available with no login requirement at http://bioinfo3d.cs.tau.ac.il/FiberDock/.

ScanNet: A Web Server for Structure-based Prediction of Protein Binding Sites with Geometric Deep Learning.

Predicting the various binding sites of a protein from its structure sheds light on its function and paves the way towards design of interaction inhibitors. Here, we report ScanNet, a freely available web server for prediction of protein-protein, protein - disordered protein and protein - antibody binding sites from structure. ScanNet (Spatio-Chemical Arrangement of Neighbors Network) is an end-to-end, interpretable geometric deep learning model that learns spatio-chemical patterns directly from 3D structures. ScanNet consistently outperforms Machine Learning models based on handcrafted features and comparative modeling approaches. The web server is linked to both the PDB and AlphaFoldDB, and supports user-provided structure files. Predictions can be readily visualized on the website via the Molstar web app and locally via ChimeraX. ScanNet is available at http://bioinfo3d.cs.tau.ac.il/ScanNet/.

Reduced antigenicity of Omicron lowers host serologic response.

SARS-CoV-2 Omicron variant of concern (VOC) contains fifteen mutations on the receptor binding domain (RBD), evading most neutralizing antibodies from vaccinated sera. Emerging evidence suggests that Omicron breakthrough cases are associated with substantially lower antibody titers than other VOC cases. However, the mechanism remains unclear. Here, using a novel geometric deep-learning model, we discovered that the antigenic profile of Omicron RBD is distinct from the prior VOCs, featuring reduced antigenicity in its remodeled receptor binding sites (RBS). To substantiate our deep-learning prediction, we immunized mice with different recombinant RBD variants and found that the Omicron's extensive mutations can lead to a drastically attenuated serologic response with limited neutralizing activity in vivo , while the T cell response remains potent. Analyses of serum cross-reactivity and competitive ELISA with epitope-specific nanobodies revealed that the antibody response to Omicron was reduced across RBD epitopes, including both the variable RBS and epitopes without any known VOC mutations. Moreover, computational modeling confirmed that the RBS is highly versatile with a capacity to further decrease antigenicity while retaining efficient receptor binding. Longitudinal analysis showed that this evolutionary trend of decrease in antigenicity was also found in hCoV229E, a common cold coronavirus that has been circulating in humans for decades. Thus, our study provided unprecedented insights into the reduced antibody titers associated with Omicron infection, revealed a possible trajectory of future viral evolution and may inform the vaccine development against future outbreaks.

Reduced B cell antigenicity of Omicron lowers host serologic response.

The SARS-CoV-2 Omicron variant evades most neutralizing vaccine-induced antibodies and is associated with lower antibody titers upon breakthrough infections than previous variants. However, the mechanism remains unclear. Here, we find using a geometric deep-learning model that Omicron's extensively mutated receptor binding site (RBS) features reduced antigenicity compared with previous variants. Mice immunization experiments with different recombinant receptor binding domain (RBD) variants confirm that the serological response to Omicron is drastically attenuated and less potent. Analyses of serum cross-reactivity and competitive ELISA reveal a reduction in antibody response across both variable and conserved RBD epitopes. Computational modeling confirms that the RBS has a potential for further antigenicity reduction while retaining efficient receptor binding. Finally, we find a similar trend of antigenicity reduction over decades for hCoV229E, a common cold coronavirus. Thus, our study explains the reduced antibody titers associated with Omicron infection and reveals a possible trajectory of future viral evolution.

SymmRef: a flexible refinement method for symmetric multimers.

Symmetric protein complexes are abundant in the living cell. Predicting their atomic structure can shed light on the mechanism of many important biological processes. Symmetric docking methods aim to predict the structure of these complexes given the unbound structure of a single monomer, or its model. Symmetry constraints reduce the search-space of these methods and make the prediction easier compared to asymmetric protein-protein docking. However, the challenge of modeling the conformational changes that the monomer might undergo is a major obstacle. In this article, we present SymmRef, a novel method for refinement and reranking of symmetric docking solutions. The method models backbone and side-chain movements and optimizes the rigid-body orientations of the monomers. The backbone movements are modeled by normal modes minimization and the conformations of the side-chains are modeled by selecting optimal rotamers. Since solved structures of symmetric multimers show asymmetric side-chain conformations, we do not use symmetry constraints in the side-chain optimization procedure. The refined models are re-ranked according to an energy score. We tested the method on a benchmark of unbound docking challenges. The results show that the method significantly improves the accuracy and the ranking of symmetric rigid docking solutions. SymmRef is available for download at http:// bioinfo3d.cs.tau.ac.il/SymmRef/download.html.