Binding affinity prediction for antibody–protein antigen complexes: A machine learning analysis based on interface and surface areas

Yang, Yong; Wang, Pan; Zhu, Bao Ting

doi:10.1016/j.jmgm.2022.108364

Cited by 18 publications

(44 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We employed a middle-dropped-out (MDO) dataset refinement, wherein all antibodies with affinity within one order-of-magnitude of the dataset median were removed to maximize the signal of features that best describe high- or low-affinity interactions spanning five logs of affinity. A classifier was selected instead of affinity regression ( Myung et al, 2022 ; Yang et al, 2023 ) toward globally differentiating high- and low-affinity binders rather than predicting specific antibody

values or

values associated with point mutations.…”

Section: Resultsmentioning

confidence: 99%

“…For example, the number of charged and aromatic CDR-H3 residues likely provides better regressive value for datasets that include a number of highly-homologous antibodies with identical light chains + CDR-H1/H2, whereas in this study all homologous antibodies were removed to maximize diveristy and minimize data leakage. Similarly, Yang et al utilize a regression-based approach, employing area- and contact-based features to measure the predictive accuracy of numerous linear and non-linear models ( Yang et al, 2023 ). Yang et al show, amongst other findings, that Random Forests are superior to neural networks for this dataset size and featurization technique.…”

Section: Discussionmentioning

confidence: 99%

“…Importantly, this task is distinct from both our previous efforts to engineer antibodies toward higher affinity and recent efforts to develop machine learning models for prediction of antibody affinity ( Myung et al, 2022 ; Yang et al, 2023 ). Specifically, these related works employ regression models trained on mutagenesis datasets, and as such perform best on antibodies with high homology to antibodies in the training set and spanning relatively narrow ranges of affinity from within two logs in the nM range, as the bulk of available structural data fall within this range.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learned features of antibody-antigen binding affinity

Miller

Clark

Raman

et al. 2023

Front. Mol. Biosci.

View full text Add to dashboard Cite

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.

show abstract

values or

values associated with point mutations.…”

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learned features of antibody-antigen binding affinity

Miller

Clark

Raman

et al. 2023

Front. Mol. Biosci.

View full text Add to dashboard Cite

show abstract

“…, PRODIGY (PROtein binDIng enerGY) . In our recent work, the area-based protein–protein binding affinity prediction methods were developed using different interface and surface areas present in the structure of a protein–protein complex. , The performances of the area-based methods were found to be superior or at least comparable to those of PRODIGY and LISA (Local Interaction Signal Analysis), which are considered the best existing methods based on linear and nonlinear models, respectively, for prediction of protein–protein binding affinity.…”

Section: Introductionmentioning

confidence: 99%

“…Certainly, more effective models are needed for improved prediction of the binding affinities of the antibody–protein antigen complexes. Recently, we have constructed area-based affinity predictive models specific for antibody–protein antigen complexes . The performances of these area-based models are better than the performance of CSM-AB, a graph-based antibody–antigen binding affinity predictive model …”

Section: Introductionmentioning

confidence: 99%

AREA-AFFINITY: A Web Server for Machine Learning-Based Prediction of Protein–Protein and Antibody–Protein Antigen Binding Affinities

Yang

Huang

Wang

et al. 2023

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Protein–Protein binding affinity reflects the binding strength between the binding partners. The prediction of protein–protein binding affinity is important for elucidating protein functions and also for designing protein-based therapeutics. The geometric characteristics such as area (both interface and surface areas) in the structure of a protein–protein complex play an important role in determining protein–protein interactions and their binding affinity. Here, we present a free web server for academic use, AREA-AFFINITY, for prediction of protein–protein or antibody–protein antigen binding affinity based on interface and surface areas in the structure of a protein–protein complex. AREA-AFFINITY implements 60 effective area-based protein–protein affinity predictive models and 37 effective area-based models specific for antibody–protein antigen binding affinity prediction developed in our recent studies. These models take into consideration the roles of interface and surface areas in binding affinity by using areas classified according to different amino acid types with different biophysical nature. The models with the best performances integrate machine learning methods such as neural network or random forest. These newly developed models have superior or comparable performance compared to the commonly used existing methods. AREA-AFFINITY is available for free at: .

show abstract

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

El Salamouni,

Cater,

Spenkelink

et al. 2024

FEBS Open Bio

View full text Add to dashboard Cite

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.

show abstract

Binding affinity prediction for antibody–protein antigen complexes: A machine learning analysis based on interface and surface areas

Cited by 18 publications

References 54 publications

Learned features of antibody-antigen binding affinity

Learned features of antibody-antigen binding affinity

AREA-AFFINITY: A Web Server for Machine Learning-Based Prediction of Protein–Protein and Antibody–Protein Antigen Binding Affinities

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

Contact Info

Product

Resources

About