RhoMax: Computational Prediction of Rhodopsin Absorption Maxima Using Geometric Deep Learning.

Microbial rhodopsins (MRs) are a diverse and abundant family of photoactive membrane proteins that serve as model systems for biophysical techniques. Optogenetics utilizes genetic engineering to insert specialized proteins into specific neurons or brain regions, allowing for manipulation of their activity through light and enabling the mapping and control of specific brain areas in living organisms. The obstacle of optogenetics lies in the fact that light has a limited ability to penetrate biological tissues, particularly blue light in the visible spectrum. Despite this challenge, most optogenetic systems rely on blue light due to the scarcity of red-shifted opsins. Finding additional red-shifted rhodopsins would represent a major breakthrough in overcoming the challenge of limited light penetration in optogenetics. However, determining the wavelength absorption maxima for rhodopsins based on their protein sequence is a significant hurdle. Current experimental methods are time-consuming, while computational methods lack accuracy. The paper introduces a new computational approach called RhoMax that utilizes structure-based geometric deep learning to predict the absorption wavelength of rhodopsins solely based on their sequences. The method takes advantage of AlphaFold2 for accurate modeling of rhodopsin structures. Once trained on a balanced train set, RhoMax rapidly and precisely predicted the maximum absorption wavelength of more than half of the sequences in our test set with an accuracy of 0.03 eV. By leveraging computational methods for absorption maxima determination, we can drastically reduce the time needed for designing new red-shifted microbial rhodopsins, thereby facilitating advances in the field of optogenetics.

Integrative modeling meets deep learning: Recent advances in modeling protein assemblies.

Recent progress in protein structure prediction based on deep learning revolutionized the field of Structural Biology. Beyond single proteins, it also enabled high-throughput prediction of structures of protein-protein interactions. Despite the success in predicting complex structures, large macromolecular assemblies still require specialized approaches. Here we describe recent advances in modeling macromolecular assemblies using integrative and hierarchical approaches. We highlight applications that predict protein-protein interactions and challenges in modeling complexes based on the interaction networks, including the prediction of complex stoichiometry and heterogeneity.

CombFold: predicting structures of large protein assemblies using a combinatorial assembly algorithm and AlphaFold2.

Deep learning models, such as AlphaFold2 and RosettaFold, enable high-accuracy protein structure prediction. However, large protein complexes are still challenging to predict due to their size and the complexity of interactions between multiple subunits. Here we present CombFold, a combinatorial and hierarchical assembly algorithm for predicting structures of large protein complexes utilizing pairwise interactions between subunits predicted by AlphaFold2. CombFold accurately predicted (TM-score >0.7) 72% of the complexes among the top-10 predictions in two datasets of 60 large, asymmetric assemblies. Moreover, the structural coverage of predicted complexes was 20% higher compared to corresponding Protein Data Bank entries. We applied the method on complexes from Complex Portal with known stoichiometry but without known structure and obtained high-confidence predictions. CombFold supports the integration of distance restraints based on crosslinking mass spectrometry and fast enumeration of possible complex stoichiometries. CombFold's high accuracy makes it a promising tool for expanding structural coverage beyond monomeric proteins.

The Cdc48 N-terminal domain has a molecular switch that mediates the Npl4-Ufd1-Cdc48 complex formation.

Cdc48 (VCP/p97) is a major AAA-ATPase involved in protein quality control, along with its canonical cofactors Ufd1 and Npl4 (UN). Here, we present novel structural insights into the interactions within the Cdc48-Npl4-Ufd1 ternary complex. Using integrative modeling, we combine subunit structures with crosslinking mass spectrometry (XL-MS) to map the interaction between Npl4 and Ufd1, alone and in complex with Cdc48. We describe the stabilization of the UN assembly upon binding with the N-terminal-domain (NTD) of Cdc48 and identify a highly conserved cysteine, C115, at the Cdc48-Npl4-binding interface which is central to the stability of the Cdc48-Npl4-Ufd1 complex. Mutation of Cys115 to serine disrupts the interaction between Cdc48-NTD and Npl4-Ufd1 and leads to a moderate decrease in cellular growth and protein quality control in yeast. Our results provide structural insight into the architecture of the Cdc48-Npl4-Ufd1 complex as well as its in vivo implications.

Predicting structures of large protein assemblies using combinatorial assembly algorithm and AlphaFold2.

Deep learning models, such as AlphaFold2 and RosettaFold, enable high-accuracy protein structure prediction. However, large protein complexes are still challenging to predict due to their size and the complexity of interactions between multiple subunits. Here we present CombFold, a combinatorial and hierarchical assembly algorithm for predicting structures of large protein complexes utilizing pairwise interactions between subunits predicted by AlphaFold2. CombFold accurately predicted (TM-score > 0.7) 72% of the complexes among the Top-10 predictions in two datasets of 60 large, asymmetric assemblies. Moreover, the structural coverage of predicted complexes was 20% higher compared to corresponding PDB entries. We applied the method on complexes from Complex Portal with known stoichiometry but without known structure and obtained high-confidence predictions. CombFold supports the integration of distance restraints based on crosslinking mass spectrometry and fast enumeration of possible complex stoichiometries. CombFold's high accuracy makes it a promising tool for expanding structural coverage beyond monomeric proteins.

A deep learning model for predicting optimal distance range in crosslinking mass spectrometry data.

Macromolecular assemblies play an important role in all cellular processes. While there has recently been significant progress in protein structure prediction based on deep learning, large protein complexes cannot be predicted with these approaches. The integrative structure modeling approach characterizes multi-subunit complexes by computational integration of data from fast and accessible experimental techniques. Crosslinking mass spectrometry is one such technique that provides spatial information about the proximity of crosslinked residues. One of the challenges in interpreting crosslinking datasets is designing a scoring function that, given a structure, can quantify how well it fits the data. Most approaches set an upper bound on the distance between Cα atoms of crosslinked residues and calculate a fraction of satisfied crosslinks. However, the distance spanned by the crosslinker greatly depends on the neighborhood of the crosslinked residues. Here, we design a deep learning model for predicting the optimal distance range for a crosslinked residue pair based on the structures of their neighborhoods. We find that our model can predict the distance range with the area under the receiver-operator curve of 0.86 and 0.7 for intra- and inter-protein crosslinks, respectively. Our deep scoring function can be used in a range of structure modeling applications.

Multi-state modeling of antibody-antigen complexes with SAXS profiles and deep-learning models.

Antibodies are an established class of human therapeutics. Epitope characterization is an important part of therapeutic antibody discovery. However, structural characterization of antibody-antigen complexes remains challenging. On the one hand, X-ray crystallography or cryo-electron microscopy provide atomic resolution characterization of the epitope, but the data collection process is typically long and the success rate is low. On the other hand, computational methods for modeling antibody-antigen structures from the individual components frequently suffer from a high false positive rate, rarely resulting in a unique solution. Recent deep learning models for structure prediction are also successful in predicting protein-protein complexes. However, they do not perform well for antibody-antigen complexes. Small Angle X-ray Scattering (SAXS) is a reliable technique for rapid structural characterization of protein samples in solution albeit at low resolution. Here, we present an integrative approach for modeling antigen-antibody complexes using the antibody sequence, antigen structure, and experimentally determined SAXS profiles of the antibody, antigen, and the complex. The method models antibody structures using a novel deep-learning approach, NanoNet. The structures of the antibodies and antigens are represented using multiple 3D conformations to account for compositional and conformational heterogeneity of the protein samples that are used to collect the SAXS data. The complexes are predicted by integrating the SAXS profiles with scoring functions for protein-protein interfaces that are based on statistical potentials and antibody-specific deep-learning models. We validated the method via application to four Fab:EGFR and one Fab:PCSK9 antibody:antigen complexes with experimentally available SAXS datasets. The integrative approach returns accurate predictions (interface RMSD<4Å) in the top five predictions for four out of five complexes (respective interface RMSD values of 1.95, 2.18, 2.66 and 3.87Å), providing support for the utility of such a computational pipeline for epitope characterization during therapeutic antibody discovery.

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.

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/.

NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning.

Antibodies are a rapidly growing class of therapeutics. Recently, single domain camelid VHH antibodies, and their recognition nanobody domain (Nb) appeared as a cost-effective highly stable alternative to full-length antibodies. There is a growing need for high-throughput epitope mapping based on accurate structural modeling of the variable domains that share a common fold and differ in the Complementarity Determining Regions (CDRs). We develop a deep learning end-to-end model, NanoNet, that given a sequence directly produces the 3D coordinates of the backbone and Cß atoms of the entire VH domain. For the Nb test set, NanoNet achieves 3.16Å average RMSD for the most variable CDR3 loops and 2.65Å, 1.73Å for the CDR1, CDR2 loops, respectively. The accuracy for antibody VH domains is even higher: 2.38Å RMSD for CDR3 and 0.89Å, 0.96Å for the CDR1, CDR2 loops, respectively. NanoNet run times allow generation of ∼1M nanobody structures in less than 4 hours on a standard CPU computer enabling high-throughput structure modeling. NanoNet is available at GitHub: https://github.com/dina-lab3D/NanoNet.

Superimmunity by pan-sarbecovirus nanobodies.

Vaccine boosters and infection can facilitate the development of SARS-CoV-2 antibodies with improved potency and breadth. Here, we observe superimmunity in a camelid extensively immunized with the SARS-CoV-2 receptor-binding domain (RBD). We rapidly isolate a large repertoire of specific ultra-high-affinity nanobodies that bind strongly to all known sarbecovirus clades using integrative proteomics. These pan-sarbecovirus nanobodies (psNbs) are highly effective against SARS-CoV and SARS-CoV-2 variants, including Omicron, with the best median neutralization potency at single-digit nanograms per milliliter. A highly potent, inhalable, and bispecific psNb (PiN-31) is also developed. Structural determinations of 13 psNbs with the SARS-CoV-2 spike or RBD reveal five epitope classes, providing insights into the mechanisms and evolution of their broad activities. The highly evolved psNbs target small, flat, and flexible epitopes that contain over 75% of conserved RBD surface residues. Their potencies are strongly and negatively correlated with the distance of the epitopes from the receptor binding sites.

Integrative structure determination reveals functional global flexibility for an ultra-multimodular arabinanase.

AbnA is an extracellular GH43 α-L-arabinanase from Geobacillus stearothermophilus, a key bacterial enzyme in the degradation and utilization of arabinan. We present herein its full-length crystal structure, revealing the only ultra-multimodular architecture and the largest structure to be reported so far within the GH43 family. Additionally, the structure of AbnA appears to contain two domains belonging to new uncharacterized carbohydrate-binding module (CBM) families. Three crystallographic conformational states are determined for AbnA, and this conformational flexibility is thoroughly investigated further using the "integrative structure determination" approach, integrating molecular dynamics, metadynamics, normal mode analysis, small angle X-ray scattering, dynamic light scattering, cross-linking, and kinetic experiments to reveal large functional conformational changes for AbnA, involving up to ~100 Å movement in the relative positions of its domains. The integrative structure determination approach demonstrated here may apply also to the conformational study of other ultra-multimodular proteins of diverse functions and structures.

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/ .

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.

A resource of high-quality and versatile nanobodies for drug delivery.

Therapeutic and diagnostic efficacies of small biomolecules and chemical compounds are hampered by suboptimal pharmacokinetics. Here, we developed a repertoire of robust and high-affinity antihuman serum albumin nanobodies (NbHSA) that can be readily fused to small biologics for half-life extension. We characterized the thermostability, binding kinetics, and cross-species reactivity of NbHSAs, mapped their epitopes, and structurally resolved a tetrameric HSA-Nb complex. We parallelly determined the half-lives of a cohort of selected NbHSAs in an HSA mouse model by quantitative proteomics. Compared to short-lived control nanobodies, the half-lives of NbHSAs were drastically prolonged by 771-fold. NbHSAs have distinct and diverse pharmacokinetics, positively correlating with their albumin binding affinities at the endosomal pH. We then generated stable and highly bioactive NbHSA-cytokine fusion constructs "Duraleukin" and demonstrated Duraleukin's high preclinical efficacy for cancer treatment in a melanoma model. This high-quality and versatile Nb toolkit will help tailor drug half-life to specific medical needs.

Potent neutralizing nanobodies resist convergent circulating variants of SARS-CoV-2 by targeting diverse and conserved epitopes.

Interventions against variants of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are urgently needed. Stable and potent nanobodies (Nbs) that target the receptor binding domain (RBD) of SARS-CoV-2 spike are promising therapeutics. However, it is unknown if Nbs broadly neutralize circulating variants. We found that RBD Nbs are highly resistant to variants of concern (VOCs). High-resolution cryoelectron microscopy determination of eight Nb-bound structures reveals multiple potent neutralizing epitopes clustered into three classes: Class I targets ACE2-binding sites and disrupts host receptor binding. Class II binds highly conserved epitopes and retains activity against VOCs and RBDSARS-CoV. Cass III recognizes unique epitopes that are likely inaccessible to antibodies. Systematic comparisons of neutralizing antibodies and Nbs provided insights into how Nbs target the spike to achieve high-affinity and broadly neutralizing activity. Structure-function analysis of Nbs indicates a variety of antiviral mechanisms. Our study may guide the rational design of pan-coronavirus vaccines and therapeutics.

Targeted in situ cross-linking mass spectrometry and integrative modeling reveal the architectures of three proteins from SARS-CoV-2.

Atomic structures of several proteins from the coronavirus family are still partial or unavailable. A possible reason for this gap is the instability of these proteins outside of the cellular context, thereby prompting the use of in-cell approaches. In situ cross-linking and mass spectrometry (in situ CLMS) can provide information on the structures of such proteins as they occur in the intact cell. Here, we applied targeted in situ CLMS to structurally probe Nsp1, Nsp2, and nucleocapsid (N) proteins from severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and obtained cross-link sets with an average density of one cross-link per 20 residues. We then employed integrative modeling that computationally combined the cross-linking data with domain structures to determine full-length atomic models. For the Nsp2, the cross-links report on a complex topology with long-range interactions. Integrative modeling with structural prediction of individual domains by the AlphaFold2 system allowed us to generate a single consistent all-atom model of the full-length Nsp2. The model reveals three putative metal binding sites and suggests a role for Nsp2 in zinc regulation within the replication-transcription complex. For the N protein, we identified multiple intra- and interdomain cross-links. Our integrative model of the N dimer demonstrates that it can accommodate three single RNA strands simultaneously, both stereochemically and electrostatically. For the Nsp1, cross-links with the 40S ribosome were highly consistent with recent cryogenic electron microscopy structures. These results highlight the importance of cellular context for the structural probing of recalcitrant proteins and demonstrate the effectiveness of targeted in situ CLMS and integrative modeling.

Potent neutralizing nanobodies resist convergent circulating variants of SARS-CoV-2 by targeting novel and conserved epitopes.

There is an urgent need to develop effective interventions resistant to the evolving variants of SARS-CoV-2. Nanobodies (Nbs) are stable and cost-effective agents that can be delivered by novel aerosolization route to treat SARS-CoV-2 infections efficiently. However, it remains unknown if they possess broadly neutralizing activities against the prevalent circulating strains. We found that potent neutralizing Nbs are highly resistant to the convergent variants of concern that evade a large panel of neutralizing antibodies (Abs) and significantly reduce the activities of convalescent or vaccine-elicited sera. Subsequent determination of 9 high-resolution structures involving 6 potent neutralizing Nbs by cryoelectron microscopy reveals conserved and novel epitopes on virus spike inaccessible to Abs. Systematic structural comparison of neutralizing Abs and Nbs provides critical insights into how Nbs uniquely target the spike to achieve high-affinity and broadly neutralizing activity against the evolving virus. Our study will inform the rational design of novel pan-coronavirus vaccines and therapeutics.

Integrative proteomics identifies thousands of distinct, multi-epitope, and high-affinity nanobodies.

The antibody immune response is essential for the survival of mammals. However, we still lack a systematic understanding of the antibody repertoire. Here, we developed a proteomic strategy to survey, at an unprecedented scale, the landscape of antigen-engaged, circulating camelid heavy-chain antibodies, whose minimal binding fragments are called VHH antibodies or nanobodies. The sensitivity and robustness of this approach were validated with three antigens spanning orders of magnitude in immune responses; thousands of distinct, high-affinity nanobody families were reliably identified and quantified. Using high-throughput structural modeling, cross-linking mass spectrometry, mutagenesis, and deep learning, we mapped and analyzed the epitopes of >100,000 antigen-nanobody complexes. Our results revealed a surprising diversity of ultrahigh-affinity camelid nanobodies for specific antigen binding on various dominant epitope clusters. Nanobodies utilize both shape and charge complementarity to enable highly selective antigen binding. Interestingly, we found that nanobody-antigen binding can mimic conserved intracellular protein-protein interactions. A record of this paper's Transparent Peer Review process is included in the Supplemental information.