Advances in computational structure-based antibody design

Hummer, Alissa; Abanades, Brennan; Deane, Charlotte M.

doi:10.1016/j.sbi.2022.102379

Cited by 61 publications

(41 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The antibodies recognize the antigens using the hypervariable complementarity-determining region (CDR) loops. The main issue in antibody structure prediction is the modeling of the CDRs, especially the CDR-H3 loop 39, 40 , and the conformations of these loops may even change upon binding 41 . Indeed, our failures to predict the antibody-antigen complexes seem to be related to incorrect positioning of CDR loops in the antibody structures (Supplementary Figure S7).…”

Section: Resultsmentioning

confidence: 99%

Prediction of protein assemblies by structure sampling followed by interface-focused scoring

Olechnovič

Valančauskas

Dapkūnas

et al. 2023

Preprint

View full text Add to dashboard Cite

Proteins often function as part of permanent or transient multimeric complexes, and understanding function of these assemblies requires knowledge of their three-dimensional structures. While the ability of AlphaFold to predict structures of individual proteins with unprecedented accuracy has revolutionized structural biology, modeling structures of protein assemblies remains challenging. To address this challenge, we developed a protocol for predicting structures of protein complexes involving model sampling followed by scoring focused on the subunit-subunit interaction interface. In this protocol, we diversified AlphaFold models by varying construction and pairing of multiple sequence alignments as well as increasing the number of recycles. In cases when AlphaFold failed to assemble a full protein complex or produced unreliable results, additional diverse models were constructed by docking of monomers or subcomplexes. All the models were then scored using a newly developed method, VoroIF-jury, which relies only on structural information. Notably, VoroIF-jury is independent of AlphaFold self-assessment scores and therefore can be used to rank models originating from different structure prediction methods. We tested our protocol in CASP15 and obtained top results, significantly outperforming the standard AlphaFold-Multimer pipeline. Analysis of our results showed that the accuracy of our assembly models was capped mainly by structure sampling rather than model scoring. This observation suggests that better sampling, especially for the antibody-antigen complexes, may lead to further improvement. Our protocol is expected to be useful for modeling and/or scoring protein assemblies.

show abstract

Section: Resultsmentioning

confidence: 99%

Prediction of protein assemblies by structure sampling followed by interface-focused scoring

Olechnovič

Valančauskas

Dapkūnas

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For a better comprehension of assay specificity, an in-silico model was used to compare the experimental results with computational data. Computational modelling methods for the in-silico construction of the 3D structure of monoclonal antibodies (mAbs) have been already developed and applied in drug discovery [ 60 , 61 ], while their exploitation to support immunosensor development is not yet widespread. Furthermore, many immunosensors employ polyclonal antibodies (pAbs) rather than mAbs, taking advantage of their higher binding avidity and affinity [ 62 , 63 ].…”

Section: Resultsmentioning

confidence: 99%

An Origami Paper-Based Biosensor for Allergen Detection by Chemiluminescence Immunoassay on Magnetic Microbeads

et al. 2022

View full text Add to dashboard Cite

Food allergies are adverse health effects that arise from specific immune responses, occurring upon exposure to given foods, even if present in traces. Egg allergy is one of the most common food allergies, mainly caused by egg white proteins, with ovalbumin being the most abundant. As allergens can also be present in foodstuff due to unintended contamination, there is a need for analytical tools that are able to rapidly detect allergens in food products at the point-of-use. Herein, we report an origami paper-based device for detecting ovalbumin in food samples, based on a competitive immunoassay with chemiluminescence detection. In this biosensor, magnetic microbeads have been employed for easy and efficient immobilization of ovalbumin on paper. Immobilized ovalbumin competes with the ovalbumin present in the sample for a limited amount of enzyme-labelled anti-ovalbumin antibody. By exploiting the origami approach, a multistep analytical procedure could be performed using reagents preloaded on paper layers, thus providing a ready-to-use immunosensing platform. The assay provided a limit of detection (LOD) of about 1 ng mL−1 for ovalbumin and, when tested on ovalbumin-spiked food matrices (chocolate chip cookies), demonstrated good assay specificity and accuracy, as compared with a commercial immunoassay kit.

show abstract

“…Learnings from antibodies are being transferred to their sisterly format such as nanobodies [ 18 , 135 , 141 ]. Of note, synergies between existing data sources provide novel findings, such as employing structural information to annotate large NGS datasets [ 76 , 95 , 142–144 ]. The increasing momentum of computational methods is therefore encouraging to speed up the development of therapeutics by the biotechnology industry.…”

Section: Discussionmentioning

confidence: 99%

“…Such virtual screening attempts in the field of small molecules are often combined with large-scale docking [ 90 ]. Deep learning models are increasingly used to score the different docking poses for protein–protein functions in general [ 91–93 ], with antibody–antigen docking treated as a separate case [ 85 , 94 ] (reviewed recently [ 95 ]). Docking was employed recently by deep learning for antibodies (DLAB) to address virtual screening by rescoring ZDOCK [ 96 ] poses in an antibody-specific fashion.…”

Section: Embedding the Ab-ag Space: Prediction Of Antibody–antigen Bi...mentioning

confidence: 99%

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Wilman¹,

Wróbel²,

Bielska³

et al. 2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

Antibodies are versatile molecular binders with an established and growing role as therapeutics. Computational approaches to developing and designing these molecules are being increasingly used to complement traditional lab-based processes. Nowadays, in silico methods fill multiple elements of the discovery stage, such as characterizing antibody–antigen interactions and identifying developability liabilities. Recently, computational methods tackling such problems have begun to follow machine learning paradigms, in many cases deep learning specifically. This paradigm shift offers improvements in established areas such as structure or binding prediction and opens up new possibilities such as language-based modeling of antibody repertoires or machine-learning-based generation of novel sequences. In this review, we critically examine the recent developments in (deep) machine learning approaches to therapeutic antibody design with implications for fully computational antibody design.

show abstract

Advances in computational structure-based antibody design

Cited by 61 publications

References 60 publications

Prediction of protein assemblies by structure sampling followed by interface-focused scoring

Prediction of protein assemblies by structure sampling followed by interface-focused scoring

An Origami Paper-Based Biosensor for Allergen Detection by Chemiluminescence Immunoassay on Magnetic Microbeads

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Contact Info

Product

Resources

About