SAbDab in the age of biotherapeutics: updates including SAbDab-nano, the nanobody structure tracker

Structural trends in antibody-antigen binding interfaces: a computational analysis of 1833 experimentally determined 3D structures

Antibodies are attractive therapeutic candidates due to their ability to bind cognate antigens with high affinity and specificity. Still, the underlying molecular rules governing the antibody-antigen interface remain poorly understood, making in silico antibody design inherently difficult and keeping the discovery and design of novel antibodies a costly and laborious process. This study investigates the characteristics of antibody-antigen binding interfaces through a computational analysis of more than 850,000 atom-atom contacts from the largest reported set of antibody-antigen complexes with 1833 nonredundant, experimentally determined structures. The analysis compares binding characteristics of conventional antibodies and single-domain antibodies (sdAbs) targeting both protein- and peptide antigens. We find clear patterns in the number antibody-antigen contacts and amino acid frequencies in the paratope. The direct comparison of sdAbs and conventional antibodies helps elucidate the mechanisms employed by sdAbs to compensate for their smaller size and the fact that they harbor only half the number of complementarity-determining regions compared to conventional antibodies. Furthermore, we pinpoint antibody interface hotspot residues that are often found at the binding interface and the amino acid frequencies at these positions. These findings have direct potential applications in antibody engineering and the design of improved antibody libraries.

Single-cell 5' RNA sequencing of camelid peripheral B cells provides insights into cellular basis of heavy-chain antibody production

Camelids produce both conventional tetrameric antibodies (Abs) and dimeric heavy-chain antibodies (HCAbs). Although B cells that generate these two types of Abs exhibit distinct B cell receptors (BCRs), whether these two B cell populations differ in their phenotypes and developmental processes remains unclear. Here, we performed single-cell 5' RNA profiling of peripheral blood mononuclear cell samples from Bactrian camels before and after immunization. We characterized the functional subtypes and differentiation trajectories of circulating B cells in camels, and reconstructed single-cell BCR sequences. We found that in contrast to humans, the proportion of T-bet+ B cells was high among camelid peripheral B cells. Several marker genes of human B cell subtypes, including CD27 and IGHD, were expressed at low levels in the corresponding camel B cell subtypes. Camelid B cells expressing variable genes of HACbs (VHH) were widely present in various functional subtypes and showed highly overlapping differentiation trajectories with B cells expressing variable genes of conventional Abs (VH). After immunization, the transcriptional changes in VHH+ and VH+ B cells were largely consistent. Through structure modeling, we identified a variety of scaffold types among the reconstructed VHH sequences. Our study provides insights into the cellular context of HCAb production in camels and lays the foundation for developing single-B cell-based camelid single-domain Ab screening.

Systematic investigation of machine learning on limited data: A study on predicting protein-protein binding strength

The application of machine learning techniques in biological research, especially when dealing with limited data availability, poses significant challenges. In this study, we leveraged advancements in method development for predicting protein-protein binding strength to conduct a systematic investigation into the application of machine learning on limited data. The binding strength, quantitatively measured as binding affinity, is vital for understanding the processes of recognition, association, and dysfunction that occur within protein complexes. By incorporating transfer learning, integrating domain knowledge, and employing both deep learning and traditional machine learning algorithms, we mitigated the impact of data limitations and made significant advancements in predicting protein-protein binding affinity. In particular, we developed over 20 models, ultimately selecting three representative best-performing ones that belong to distinct categories. The first model is structure-based, consisting of a random forest regression and thirteen handcrafted features. The second model is sequence-based, employing an architecture that combines transferred embedding features with a multilayer perceptron. Finally, we created an ensemble model by averaging the predictions of the two aforementioned models. The comparison with other predictors on three independent datasets confirms the significant improvements achieved by our models in predicting protein-protein binding affinity. The programs for running these three models are available at https://github.com/minghuilab/BindPPI.

Advancements in nanobody generation: Integrating conventional, in silico, and machine learning approaches

Nanobodies, derived from camelids and sharks, offer compact, single-variable heavy-chain antibodies with diverse biomedical potential. This review explores their generation methods, including display techniques on phages, yeast, or bacteria, and computational methodologies. Integrating experimental and computational approaches enhances understanding of nanobody structure and function. Future trends involve leveraging next-generation sequencing, machine learning, and artificial intelligence for efficient candidate selection and predictive modeling. The convergence of traditional and computational methods promises revolutionary advancements in precision biomedical applications such as targeted drug delivery and diagnostics. Embracing these technologies accelerates nanobody development, driving transformative breakthroughs in biomedicine and paving the way for precision medicine and biomedical innovation.

Analytical Post-Embedding Immunogold-Electron Microscopy with Direct Gold-Labelled Monoclonal Primary Antibodies against RIBEYE A- and B-Domain Suggests a Refined Model of Synaptic Ribbon Assembly

Synaptic ribbons are the eponymous specializations of continuously active ribbon synapses. They are primarily composed of the RIBEYE protein that consists of a unique amino-terminal A-domain and carboxy-terminal B-domain that is largely identical to the ubiquitously expressed transcriptional regulator protein CtBP2. Both RIBEYE A-domain and RIBEYE B-domain are essential for the assembly of the synaptic ribbon, as shown by previous analyses of RIBEYE knockout and knockin mice and related investigations. How exactly the synaptic ribbon is assembled from RIBEYE subunits is not yet clear. To achieve further insights into the architecture of the synaptic ribbon, we performed analytical post-embedding immunogold-electron microscopy with direct gold-labelled primary antibodies against RIBEYE A-domain and RIBEYE B-domain for improved ultrastructural resolution. With direct gold-labelled monoclonal antibodies against RIBEYE A-domain and RIBEYE B-domain, we found that both domains show a very similar localization within the synaptic ribbon of mouse photoreceptor synapses, with no obvious differential gradient between the centre and surface of the synaptic ribbon. These data favour a model of the architecture of the synaptic ribbon in which the RIBEYE A-domain and RIBEYE B-domain are located similar distances from the midline of the synaptic ribbon.

A Comparison of Antibody-Antigen Complex Sequence-to-Structure Prediction Methods and their Systematic Biases

The ability to accurately predict antibody-antigen complex structures from their sequences could greatly advance our understanding of the immune system and would aid in the development of novel antibody therapeutics. There have been considerable recent advancements in predicting protein-protein interactions (PPIs) fueled by progress in machine learning (ML). To understand the current state of the field, we compare six representative methods for predicting antibody-antigen complexes from sequence, including two deep learning approaches trained to predict PPIs in general (AlphaFold-Multimer, RoseTTAFold), two composite methods that initially predict antibody and antigen structures separately and dock them (using antibody-mode ClusPro), local refinement in Rosetta (SnugDock) of globally docked poses from ClusPro, and a pipeline combining homology modeling with rigid-body docking informed by ML-based epitope and paratope prediction (AbAdapt). We find that AlphaFold-Multimer outperformed other methods, although the absolute performance leaves considerable room for improvement. AlphaFold-Multimer models of lower-quality display significant structural biases at the level of tertiary motifs (TERMs) towards having fewer structural matches in non-antibody containing structures from the Protein Data Bank (PDB). Specifically, better models exhibit more common PDB-like TERMs at the antibody-antigen interface than worse ones. Importantly, the clear relationship between performance and the commonness of interfacial TERMs suggests that scarcity of interfacial geometry data in the structural database may currently limit application of machine learning to the prediction of antibody-antigen interactions.

Nanobody engineering: computational modelling and design for biomedical and therapeutic applications

Nanobodies, the smallest functional antibody fragment derived from camelid heavy-chain-only antibodies, have emerged as powerful tools for diverse biomedical applications. In this comprehensive review, we discuss the structural characteristics, functional properties, and computational approaches driving the design and optimisation of synthetic nanobodies. We explore their unique antigen-binding domains, highlighting the critical role of complementarity-determining regions in target recognition and specificity. This review further underscores the advantages of nanobodies over conventional antibodies from a biosynthesis perspective, including their small size, stability, and solubility, which make them ideal candidates for economical antigen capture in diagnostics, therapeutics, and biosensing. We discuss the recent advancements in computational methods for nanobody modelling, epitope prediction, and affinity maturation, shedding light on their intricate antigen-binding mechanisms and conformational dynamics. Finally, we examine a direct example of how computational design strategies were implemented for improving a nanobody-based immunosensor, known as a Quenchbody. Through combining experimental findings and computational insights, this review elucidates the transformative impact of nanobodies in biotechnology and biomedical research, offering a roadmap for future advancements and applications in healthcare and diagnostics.

Accurate prediction of antibody function and structure using bio-inspired antibody language model

In recent decades, antibodies have emerged as indispensable therapeutics for combating diseases, particularly viral infections. However, their development has been hindered by limited structural information and labor-intensive engineering processes. Fortunately, significant advancements in deep learning methods have facilitated the precise prediction of protein structure and function by leveraging co-evolution information from homologous proteins. Despite these advances, predicting the conformation of antibodies remains challenging due to their unique evolution and the high flexibility of their antigen-binding regions. Here, to address this challenge, we present the Bio-inspired Antibody Language Model (BALM). This model is trained on a vast dataset comprising 336 million 40% nonredundant unlabeled antibody sequences, capturing both unique and conserved properties specific to antibodies. Notably, BALM showcases exceptional performance across four antigen-binding prediction tasks. Moreover, we introduce BALMFold, an end-to-end method derived from BALM, capable of swiftly predicting full atomic antibody structures from individual sequences. Remarkably, BALMFold outperforms those well-established methods like AlphaFold2, IgFold, ESMFold and OmegaFold in the antibody benchmark, demonstrating significant potential to advance innovative engineering and streamline therapeutic antibody development by reducing the need for unnecessary trials. The BALMFold structure prediction server is freely available at https://beamlab-sh.com/models/BALMFold.

Single-sequence protein structure prediction by integrating protein language models

Protein structure prediction has been greatly improved by deep learning in the past few years. However, the most successful methods rely on multiple sequence alignment (MSA) of the sequence homologs of the protein under prediction. In nature, a protein folds in the absence of its sequence homologs and thus, a MSA-free structure prediction method is desired. Here, we develop a single-sequence-based protein structure prediction method RaptorX-Single by integrating several protein language models and a structure generation module and then study its advantage over MSA-based methods. Our experimental results indicate that in addition to running much faster than MSA-based methods such as AlphaFold2, RaptorX-Single outperforms AlphaFold2 and other MSA-free methods in predicting the structure of antibodies (after fine-tuning on antibody data), proteins of very few sequence homologs, and single mutation effects. By comparing different protein language models, our results show that not only the scale but also the training data of protein language models will impact the performance. RaptorX-Single also compares favorably to MSA-based AlphaFold2 when the protein under prediction has a large number of sequence homologs.

Investigating the ability of deep learning-based structure prediction to extrapolate and/or enrich the set of antibody CDR canonical forms

Deep learning models have been shown to accurately predict protein structure from sequence, allowing researchers to explore protein space from the structural viewpoint. In this paper we explore whether "novel" features, such as distinct loop conformations can arise from these predictions despite not being present in the training data. Here we have used ABodyBuilder2, a deep learning antibody structure predictor, to predict the structures of ~1.5M paired antibody sequences. We examined the predicted structures of the canonical CDR loops and found that most of these predictions fall into the already described CDR canonical form structural space. We also found a small number of "new" canonical clusters composed of heterogeneous sequences united by a common sequence motif and loop conformation. Analysis of these novel clusters showed their origins to be either shapes seen in the training data at very low frequency or shapes seen at high frequency but at a shorter sequence length. To evaluate explicitly the ability of ABodyBuilder2 to extrapolate, we retrained several models whilst withholding all antibody structures of a specific CDR loop length or canonical form. These "starved" models showed evidence of generalisation across CDRs of different lengths, but they did not extrapolate to loop conformations which were highly distinct from those present in the training data. However, the models were able to accurately predict a canonical form even if only a very small number of examples of that shape were in the training data. Our results suggest that deep learning protein structure prediction methods are unable to make completely out-of-domain predictions for CDR loops. However, in our analysis we also found that even minimal amounts of data of a structural shape allow the method to recover its original predictive abilities. We have made the ~1.5 M predicted structures used in this study available to download at https://doi.org/10.5281/zenodo.10280181.

Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody-Antigen Interactions

This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein-protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.

NanoLAS: a comprehensive nanobody database with data integration, consolidation and application

Nanobodies, a unique subclass of antibodies first discovered in camelid animals, are composed solely of a single heavy chain's variable region. Their significantly reduced molecular weight, in comparison to conventional antibodies, confers numerous advantages in the treatment of various diseases. As research and applications involving nanobodies expand, the quantity of identified nanobodies is also rapidly growing. However, the existing antibody databases are deficient in type and coverage, failing to satisfy the comprehensive needs of researchers and thus impeding progress in nanobody research. In response to this, we have amalgamated data from multiple sources to successfully assemble a new and comprehensive nanobody database. This database has currently included the latest nanobody data and provides researchers with an excellent search and data display interface, thus facilitating the progression of nanobody research and their application in disease treatment. In summary, the newly constructed Nanobody Library and Archive System may significantly enhance the retrieval efficiency and application potential of nanobodies. We envision that Nanobody Library and Archive System will serve as an accessible, robust and efficient tool for nanobody research and development, propelling advancements in the field of biomedicine. Database URL: https://www.nanolas.cloud.

Contextualising the developability risk of antibodies with lambda light chains using enhanced therapeutic antibody profiling

Antibodies with lambda light chains (λ-antibodies) are generally considered to be less developable than those with kappa light chains (κ-antibodies). Though this hypothesis has not been formally established, it has led to substantial systematic biases in drug discovery pipelines and thus contributed to kappa dominance amongst clinical-stage therapeutics. However, the identification of increasing numbers of epitopes preferentially engaged by λ-antibodies shows there is a functional cost to neglecting to consider them as potential lead candidates. Here, we update our Therapeutic Antibody Profiler (TAP) tool to use the latest data and machine learning-based structure prediction, and apply it to evaluate developability risk profiles for κ-antibodies and λ-antibodies based on their surface physicochemical properties. We find that while human λ-antibodies on average have a higher risk of developability issues than κ-antibodies, a sizeable proportion are assigned lower-risk profiles by TAP and should represent more tractable candidates for therapeutic development. Through a comparative analysis of the low- and high-risk populations, we highlight opportunities for strategic design that TAP suggests would enrich for more developable λ-antibodies. Overall, we provide context to the differing developability of κ- and λ-antibodies, enabling a rational approach to incorporate more diversity into the initial pool of immunotherapeutic candidates.

The Patent and Literature Antibody Database (PLAbDab): an evolving reference set of functionally diverse, literature-annotated antibody sequences and structures

Antibodies are key proteins of the adaptive immune system, and there exists a large body of academic literature and patents dedicated to their study and concomitant conversion into therapeutics, diagnostics, or reagents. These documents often contain extensive functional characterisations of the sets of antibodies they describe. However, leveraging these heterogeneous reports, for example to offer insights into the properties of query antibodies of interest, is currently challenging as there is no central repository through which this wide corpus can be mined by sequence or structure. Here, we present PLAbDab (the Patent and Literature Antibody Database), a self-updating repository containing over 150,000 paired antibody sequences and 3D structural models, of which over 65 000 are unique. We describe the methods used to extract, filter, pair, and model the antibodies in PLAbDab, and showcase how PLAbDab can be searched by sequence, structure, or keyword. PLAbDab uses include annotating query antibodies with potential antigen information from similar entries, analysing structural models of existing antibodies to identify modifications that could improve their properties, and facilitating the compilation of bespoke datasets of antibody sequences/structures that bind to a specific antigen. PLAbDab is freely available via Github (https://github.com/oxpig/PLAbDab) and as a searchable webserver (https://opig.stats.ox.ac.uk/webapps/plabdab/).

Applications and challenges in designing VHH-based bispecific antibodies: leveraging machine learning solutions

The development of bispecific antibodies that bind at least two different targets relies on bringing together multiple binding domains with different binding properties and biophysical characteristics to produce a drug-like therapeutic. These building blocks play an important role in the overall quality of the molecule and can influence many important aspects from potency and specificity to stability and half-life. Single-domain antibodies, particularly camelid-derived variable heavy domain of heavy chain (VHH) antibodies, are becoming an increasingly popular choice for bispecific construction due to their single-domain modularity, favorable biophysical properties, and potential to work in multiple antibody formats. Here, we review the use of VHH domains as building blocks in the construction of multispecific antibodies and the challenges in creating optimized molecules. In addition to exploring traditional approaches to VHH development, we review the integration of machine learning techniques at various stages of the process. Specifically, the utilization of machine learning for structural prediction, lead identification, lead optimization, and humanization of VHH antibodies.

Conformational features and interaction mechanisms of VH H antibodies with β-hairpin CDR3: A case of Nb8-HigB2 interaction

The β-hairpin conformation is regarded as an important basic motif to form and regulate protein-protein interactions. Single-domain VH H antibodies are potential therapeutic and diagnostic tools, and the third complementarity-determining regions of the heavy chains (CDR3s) of these antibodies are critical for antigen recognition. Although the sequences and conformations of the CDR3s are diverse, CDR3s sometimes adopt β-hairpin conformations. However, characteristic features and interaction mechanisms of β-hairpin CDR3s remain to be fully elucidated. In this study, we investigated the molecular recognition of the anti-HigB2 VH H antibody Nb8, which has a CDR3 that forms a β-hairpin conformation. The interaction was analyzed by evaluation of alanine-scanning mutants, molecular dynamics simulations, and hydrogen/deuterium exchange mass spectrometry. These experiments demonstrated that positions 93 and 94 (Chothia numbering) in framework region 3, which is right outside CDR3 by definition, play pivotal roles in maintaining structural stability and binding properties of Nb8. These findings will facilitate the design and optimization of single-domain antibodies.

Recent advances in structural mass spectrometry methods in the context of biosimilarity assessment: from sequence heterogeneities to higher order structures

Biotherapeutics and their biosimilar versions have been flourishing in the biopharmaceutical market for several years. Structural and functional characterization is needed to achieve analytical biosimilarity through the assessment of critical quality attributes as required by regulatory authorities. The role of analytical strategies, particularly mass spectrometry-based methods, is pivotal to gathering valuable information for the in-depth characterization of biotherapeutics and biosimilarity assessment. Structural mass spectrometry methods (native MS, HDX-MS, top-down MS, etc.) provide information ranging from primary sequence assessment to higher order structure evaluation. This review focuses on recent developments and applications in structural mass spectrometry for biotherapeutic and biosimilar characterization.

DG-Affinity: predicting antigen-antibody affinity with language models from sequences

BACKGROUND

Antibody-mediated immune responses play a crucial role in the immune defense of human body. The evolution of bioengineering has led the progress of antibody-derived drugs, showing promising efficacy in cancer and autoimmune disease therapy. A critical step of this development process is obtaining the affinity between antibodies and their binding antigens.

RESULTS

In this study, we introduce a novel sequence-based antigen-antibody affinity prediction method, named DG-Affinity. DG-Affinity uses deep neural networks to efficiently and accurately predict the affinity between antibodies and antigens from sequences, without the need for structural information. The sequences of both the antigen and the antibody are first transformed into embedding vectors by two pre-trained language models, then these embeddings are concatenated into an ConvNeXt framework with a regression task. The results demonstrate the superiority of DG-Affinity over the existing structure-based prediction methods and the sequence-based tools, achieving a Pearson's correlation of over 0.65 on an independent test dataset.

CONCLUSIONS

Compared to the baseline methods, DG-Affinity achieves the best performance and can advance the development of antibody design. It is freely available as an easy-to-use web server at https://www.digitalgeneai.tech/solution/affinity .

Improved computational epitope profiling using structural models identifies a broader diversity of antibodies that bind to the same epitope

The function of an antibody is intrinsically linked to the epitope it engages. Clonal clustering methods, based on sequence identity, are commonly used to group antibodies that will bind to the same epitope. However, such methods neglect the fact that antibodies with highly diverse sequences can exhibit similar binding site geometries and engage common epitopes. In a previous study, we described SPACE1, a method that structurally clustered antibodies in order to predict their epitopes. This methodology was limited by the inaccuracies and incomplete coverage of template-based modeling. In addition, it was only benchmarked at the level of domain-consistency on one virus class. Here, we present SPACE2, which uses the latest machine learning-based structure prediction technology combined with a novel clustering protocol, and benchmark it on binding data that have epitope-level resolution. On six diverse sets of antigen-specific antibodies, we demonstrate that SPACE2 accurately clusters antibodies that engage common epitopes and achieves far higher dataset coverage than clonal clustering and SPACE1. Furthermore, we show that the functionally consistent structural clusters identified by SPACE2 are even more diverse in sequence, genetic lineage, and species origin than those found by SPACE1. These results reiterate that structural data improve our ability to identify antibodies that bind to the same epitope, adding information to sequence-based methods, especially in datasets of antibodies from diverse sources. SPACE2 is openly available on GitHub (https://github.com/oxpig/SPACE2).

Experimentally Observed Conformational Changes in Antibodies Due to Binding and Paratope-epitope Asymmetries

Understanding binding related changes in antibody conformations is important for epitope prediction and antibody refinement. The increase of available data in the PDB allowed a more detailed investigation of the conformational landscape for free and bound antibodies. A dataset containing a total of 835 unique PDB entries of antibodies that were crystallized in complex with their antigen and in a free state was constructed. It was examined for binding related conformation changes. We present further evidence supporting the theory of a pre-existing-equilibrium in experimental data. Multiple sequence alignments did not show binding induced tendencies in the solvent accessibility of residues in any specific position. Evaluating the changes in solvent accessibility per residue revealed a certain binding induced increase for several amino acids. Antibody-antigen interaction statistics were established and quantify a significant directional asymmetry between many interacting antibody and antigen residue pairs, especially a richness in tyrosine in the antibody epitope compared to its paratope. This asymmetry could potentially facilitate an increase in the success rate of computationally guided antibody refinement.

Development of a new recombinant antibody, selected by phage-display technology from a celiac patient library, for detection of gluten in foods

Gluten, a group of ethanol-soluble proteins present in the endosperm of cereals, is extensively used in the food industry due to its ability to improve dough properties. However, gluten is also associated with a range of gluten-related diseases (GRDs), such as wheat allergies, celiac disease, and gluten intolerance. The recommended treatment for GRDs patients is a gluten-free diet. To monitor adherence to this diet, it is necessary to develop gluten-detection systems in food products. Among the available methods, immunodetection systems are the most popular due to their simplicity, reproducibility, and accuracy. The aim of this study was to generate novel high-affinity antibodies against gluten to be used as the primary reactant in an enzyme-linked immunosorbent assay (ELISA) test. These antibodies were developed by constructing an immune library from mRNA obtained from two celiac patients with a high humoral response to gluten-related proteins. The resulting library (composed by 1.1x107) was subjected to selection against gliadin using phage display technology. Following several rounds of selection, the Fab-C was selected, and demonstrated good functionality in ELISA tests, presenting a limit of detection of 15 mg/kg for detection of gluten in spiked mixtures and food products. The methodology can discriminate gluten-free products according to the current legislation.

A comparison of the binding sites of antibodies and single-domain antibodies

Antibodies are the largest class of biotherapeutics. However, in recent years, single-domain antibodies have gained traction due to their smaller size and comparable binding affinity. Antibodies (Abs) and single-domain antibodies (sdAbs) differ in the structures of their binding sites: most significantly, single-domain antibodies lack a light chain and so have just three CDR loops. Given this inherent structural difference, it is important to understand whether Abs and sdAbs are distinguishable in how they engage a binding partner and thus, whether they are suited to different types of epitopes. In this study, we use non-redundant sequence and structural datasets to compare the paratopes, epitopes and antigen interactions of Abs and sdAbs. We demonstrate that even though sdAbs have smaller paratopes, they target epitopes of equal size to those targeted by Abs. To achieve this, the paratopes of sdAbs contribute more interactions per residue than the paratopes of Abs. Additionally, we find that conserved framework residues are of increased importance in the paratopes of sdAbs, suggesting that they include non-specific interactions to achieve comparable affinity. Furthermore, the epitopes of sdAbs are only marginally less accessible than those of Abs: we posit that this may be explained by differences in the orientation and compaction of sdAb and Ab CDR-H3 loops. Overall, our results have important implications for the engineering and humanization of sdAbs, as well as the selection of the best modality for targeting a particular epitope.

ImmuneBuilder: Deep-Learning models for predicting the structures of immune proteins

Immune receptor proteins play a key role in the immune system and have shown great promise as biotherapeutics. The structure of these proteins is critical for understanding their antigen binding properties. Here, we present ImmuneBuilder, a set of deep learning models trained to accurately predict the structure of antibodies (ABodyBuilder2), nanobodies (NanoBodyBuilder2) and T-Cell receptors (TCRBuilder2). We show that ImmuneBuilder generates structures with state of the art accuracy while being far faster than AlphaFold2. For example, on a benchmark of 34 recently solved antibodies, ABodyBuilder2 predicts CDR-H3 loops with an RMSD of 2.81Å, a 0.09Å improvement over AlphaFold-Multimer, while being over a hundred times faster. Similar results are also achieved for nanobodies, (NanoBodyBuilder2 predicts CDR-H3 loops with an average RMSD of 2.89Å, a 0.55Å improvement over AlphaFold2) and TCRs. By predicting an ensemble of structures, ImmuneBuilder also gives an error estimate for every residue in its final prediction. ImmuneBuilder is made freely available, both to download ( https://github.com/oxpig/ImmuneBuilder ) and to use via our webserver ( http://opig.stats.ox.ac.uk/webapps/newsabdab/sabpred ). We also make available structural models for ~150 thousand non-redundant paired antibody sequences ( https://doi.org/10.5281/zenodo.7258553 ).

Germline-encoded amino acid-binding motifs drive immunodominant public antibody responses

Despite the vast diversity of the antibody repertoire, infected individuals often mount antibody responses to precisely the same epitopes within antigens. The immunological mechanisms underpinning this phenomenon remain unknown. By mapping 376 immunodominant "public epitopes" at high resolution and characterizing several of their cognate antibodies, we concluded that germline-encoded sequences in antibodies drive recurrent recognition. Systematic analysis of antibody-antigen structures uncovered 18 human and 21 partially overlapping mouse germline-encoded amino acid-binding (GRAB) motifs within heavy and light V gene segments that in case studies proved critical for public epitope recognition. GRAB motifs represent a fundamental component of the immune system's architecture that promotes recognition of pathogens and leads to species-specific public antibody responses that can exert selective pressure on pathogens.

Toward real-world automated antibody design with combinatorial Bayesian optimization

Antibodies are multimeric proteins capable of highly specific molecular recognition. The complementarity determining region 3 of the antibody variable heavy chain (CDRH3) often dominates antigen-binding specificity. Hence, it is a priority to design optimal antigen-specific CDRH3 to develop therapeutic antibodies. The combinatorial structure of CDRH3 sequences makes it impossible to query binding-affinity oracles exhaustively. Moreover, antibodies are expected to have high target specificity and developability. Here, we present AntBO, a combinatorial Bayesian optimization framework utilizing a CDRH3 trust region for an in silico design of antibodies with favorable developability scores. The in silico experiments on 159 antigens demonstrate that AntBO is a step toward practically viable in vitro antibody design. In under 200 calls to the oracle, AntBO suggests antibodies outperforming the best binding sequence from 6.9 million experimentally obtained CDRH3s. Additionally, AntBO finds very-high-affinity CDRH3 in only 38 protein designs while requiring no domain knowledge.

Computationally profiling peptide:MHC recognition by T-cell receptors and T-cell receptor-mimetic antibodies

T-cell receptor-mimetic antibodies (TCRms) targeting disease-associated peptides presented by Major Histocompatibility Complexes (pMHCs) are set to become a major new drug modality. However, we lack a general understanding of how TCRms engage pMHC targets, which is crucial for predicting their specificity and safety. Several new structures of TCRm:pMHC complexes have become available in the past year, providing sufficient initial data for a holistic analysis of TCRms as a class of pMHC binding agents. Here, we profile the complete set of TCRm:pMHC complexes against representative TCR:pMHC complexes to quantify the TCR-likeness of their pMHC engagement. We find that intrinsic molecular differences between antibodies and TCRs lead to fundamentally different roles for their heavy/light chains and Complementarity-Determining Region loops during antigen recognition. The idiotypic properties of antibodies may increase the likelihood of TCRms engaging pMHCs with less peptide selectivity than TCRs. However, the pMHC recognition features of some TCRms, including the two TCRms currently in clinical trials, can be remarkably TCR-like. The insights gained from this study will aid in the rational design and optimisation of next-generation TCRms.

Paragraph-antibody paratope prediction using graph neural networks with minimal feature vectors

SUMMARY

The development of new vaccines and antibody therapeutics typically takes several years and requires over $1bn in investment. Accurate knowledge of the paratope (antibody binding site) can speed up and reduce the cost of this process by improving our understanding of antibody-antigen binding. We present Paragraph, a structure-based paratope prediction tool that outperforms current state-of-the-art tools using simpler feature vectors and no antigen information.

AVAILABILITY AND IMPLEMENTATION

Source code is freely available at www.github.com/oxpig/Paragraph.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Approaches to expand the conventional toolbox for discovery and selection of antibodies with drug-like physicochemical properties

Antibody drugs should exhibit not only high-binding affinity for their target antigens but also favorable physicochemical drug-like properties. Such drug-like biophysical properties are essential for the successful development of antibody drug products. The traditional approaches used in antibody drug development require significant experimentation to produce, optimize, and characterize many candidates. Therefore, it is attractive to integrate new methods that can optimize the process of selecting antibodies with both desired target-binding and drug-like biophysical properties. Here, we summarize a selection of techniques that can complement the conventional toolbox used to de-risk antibody drug development. These techniques can be integrated at different stages of the antibody development process to reduce the frequency of physicochemical liabilities in antibody libraries during initial discovery and to co-optimize multiple antibody features during early-stage antibody engineering and affinity maturation. Moreover, we highlight biophysical and computational approaches that can be used to predict physical degradation pathways relevant for long-term storage and in-use stability to reduce the need for extensive experimentation.

Deep learning of protein sequence design of protein-protein interactions

MOTIVATION

As more data of experimentally determined protein structures are becoming available, data-driven models to describe protein sequence-structure relationships become more feasible. Within this space, the amino acid sequence design of protein-protein interactions is still a rather challenging subproblem with very low success rates-yet, it is central to most biological processes.

RESULTS

We developed an attention-based deep learning model inspired by algorithms used for image-caption assignments to design peptides or protein fragment sequences. Our trained model can be applied for the redesign of natural protein interfaces or the designed protein interaction fragments. Here, we validate the potential by recapitulating naturally occurring protein-protein interactions including antibody-antigen complexes. The designed interfaces accurately capture essential native interactions and have comparable native-like binding affinities in silico. Furthermore, our model does not need a precise backbone location, making it an attractive tool for working with de novo design of protein-protein interactions.

AVAILABILITY AND IMPLEMENTATION

The source code of the method is available at https://github.com/strauchlab/iNNterfaceDesign.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Learned features of antibody-antigen binding affinity

Defining predictors of antigen-binding affinity of antibodies is valuable for engineering therapeutic antibodies with high binding affinity to their targets. However, this task is challenging owing to the huge diversity in the conformations of the complementarity determining regions of antibodies and the mode of engagement between antibody and antigen. In this study, we used the structural antibody database (SAbDab) to identify features that can discriminate high- and low-binding affinity across a 5-log scale. First, we abstracted features based on previously learned representations of protein-protein interactions to derive 'complex' feature sets, which include energetic, statistical, network-based, and machine-learned features. Second, we contrasted these complex feature sets with additional 'simple' feature sets based on counts of contacts between antibody and antigen. By investigating the predictive potential of 700 features contained in the eight complex and simple feature sets, we observed that simple feature sets perform comparably to complex feature sets in classification of binding affinity. Moreover, combining features from all eight feature-sets provided the best classification performance (median cross-validation AUROC and F1-score of 0.72). Of note, classification performance is substantially improved when several sources of data leakage (e.g., homologous antibodies) are not removed from the dataset, emphasizing a potential pitfall in this task. We additionally observe a classification performance plateau across diverse featurization approaches, highlighting the need for additional affinity-labeled antibody-antigen structural data. The findings from our present study set the stage for future studies aimed at multiple-log enhancement of antibody affinity through feature-guided engineering.

A machine learning strategy for the identification of key in silico descriptors and prediction models for IgG monoclonal antibody developability properties

Identification of favorable biophysical properties for protein therapeutics as part of developability assessment is a crucial part of the preclinical development process. Successful prediction of such properties and bioassay results from calculated in silico features has potential to reduce the time and cost of delivering clinical-grade material to patients, but nevertheless has remained an ongoing challenge to the field. Here, we demonstrate an automated and flexible machine learning workflow designed to compare and identify the most powerful features from computationally derived physiochemical feature sets, generated from popular commercial software packages. We implement this workflow with medium-sized datasets of human and humanized IgG molecules to generate predictive regression models for two key developability endpoints, hydrophobicity and poly-specificity. The most important features discovered through the automated workflow corroborate several previous literature reports, and newly discovered features suggest directions for further research and potential model improvement.

Research progress on unique paratope structure, antigen binding modes, and systematic mutagenesis strategies of single-domain antibodies

Single-domain antibodies (sdAbs) showed the incredible advantages of small molecular weight, excellent affinity, specificity, and stability compared with traditional IgG antibodies, so their potential in binding hidden antigen epitopes and hazard detection in food, agricultural and veterinary fields were gradually explored. Moreover, its low immunogenicity, easy-to-carry target drugs, and penetration of the blood-brain barrier have made sdAbs remarkable achievements in medical treatment, toxin neutralization, and medical imaging. With the continuous development and maturity of modern molecular biology, protein analysis software and database with different algorithms, and next-generation sequencing technology, the unique paratope structure and different antigen binding modes of sdAbs compared with traditional IgG antibodies have aroused the broad interests of researchers with the increased related studies. However, the corresponding related summaries are lacking and needed. Different antigens, especially hapten antigens, show distinct binding modes with sdAbs. So, in this paper, the unique paratope structure of sdAbs, different antigen binding cases, and the current maturation strategy of sdAbs were classified and summarized. We hope this review lays a theoretical foundation to elucidate the antigen-binding mechanism of sdAbs and broaden the further application of sdAbs.

Antibody-Antigen Binding Interface Analysis in the Big Data Era

Antibodies have become the Swiss Army tool for molecular biology and nanotechnology. Their outstanding ability to specifically recognise molecular antigens allows their use in many different applications from medicine to the industry. Moreover, the improvement of conventional structural biology techniques (e.g., X-ray, NMR) as well as the emergence of new ones (e.g., Cryo-EM), have permitted in the last years a notable increase of resolved antibody-antigen structures. This offers a unique opportunity to perform an exhaustive structural analysis of antibody-antigen interfaces by employing the large amount of data available nowadays. To leverage this factor, different geometric as well as chemical descriptors were evaluated to perform a comprehensive characterization.

Advances in computational structure-based antibody design

Antibodies are currently the most important class of biotherapeutics and are used to treat numerous diseases. Recent advances in computational methods are ushering in a new era of antibody design, driven in part by accurate structure prediction. Previously, structure-based antibody design has been limited to a relatively small number of cases where accurate structures or models of both the target antigen and antibody were available. As we move towards a time where it is possible to accurately model most antibodies and antigens, and to reliably predict their binding site, there is vast potential for true computational antibody design. In this review, we describe the latest methods that promise to launch a paradigm shift towards entirely in silico structure-based antibody design.

VHH Structural Modelling Approaches: A Critical Review

V_HH, i.e., VH domains of camelid single-chain antibodies, are very promising therapeutic agents due to their significant physicochemical advantages compared to classical mammalian antibodies. The number of experimentally solved V_HH structures has significantly improved recently, which is of great help, because it offers the ability to directly work on 3D structures to humanise or improve them. Unfortunately, most V_HHs do not have 3D structures. Thus, it is essential to find alternative ways to get structural information. The methods of structure prediction from the primary amino acid sequence appear essential to bypass this limitation. This review presents the most extensive overview of structure prediction methods applied for the 3D modelling of a given V_HH sequence (a total of 21). Besides the historical overview, it aims at showing how model software programs have been shaping the structural predictions of V_HHs. A brief explanation of each methodology is supplied, and pertinent examples of their usage are provided. Finally, we present a structure prediction case study of a recently solved V_HH structure. According to some recent studies and the present analysis, AlphaFold 2 and NanoNet appear to be the best tools to predict a structural model of V_HH from its sequence.