1
|
Zhang G, Kuang X, Zhang Y, Liu Y, Su Z, Zhang T, Wu Y. Machine-learning-based structural analysis of interactions between antibodies and antigens. Biosystems 2024; 243:105264. [PMID: 38964652 DOI: 10.1016/j.biosystems.2024.105264] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2023] [Revised: 06/21/2024] [Accepted: 07/01/2024] [Indexed: 07/06/2024]
Abstract
Computational analysis of paratope-epitope interactions between antibodies and their corresponding antigens can facilitate our understanding of the molecular mechanism underlying humoral immunity and boost the design of new therapeutics for many diseases. The recent breakthrough in artificial intelligence has made it possible to predict protein-protein interactions and model their structures. Unfortunately, detecting antigen-binding sites associated with a specific antibody is still a challenging problem. To tackle this challenge, we implemented a deep learning model to characterize interaction patterns between antibodies and their corresponding antigens. With high accuracy, our model can distinguish between antibody-antigen complexes and other types of protein-protein complexes. More intriguingly, we can identify antigens from other common protein binding regions with an accuracy of higher than 70% even if we only have the epitope information. This indicates that antigens have distinct features on their surface that antibodies can recognize. Additionally, our model was unable to predict the partnerships between antibodies and their particular antigens. This result suggests that one antigen may be targeted by more than one antibody and that antibodies may bind to previously unidentified proteins. Taken together, our results support the precision of antibody-antigen interactions while also suggesting positive future progress in the prediction of specific pairing.
Collapse
Affiliation(s)
- Grace Zhang
- Staples High School, 70 North Avenue, Westport, CT, 06880, USA
| | - Xiaohan Kuang
- Data Science Institute, Vanderbilt University, 1001 19th Ave S, Nashville, TN, 37212, USA
| | - Yuhao Zhang
- Data Science Institute, Vanderbilt University, 1001 19th Ave S, Nashville, TN, 37212, USA
| | - Yunchao Liu
- Department of Computer Science, Vanderbilt University, 1400 18th Ave S, Nashville, TN, 37212, USA
| | - Zhaoqian Su
- Data Science Institute, Vanderbilt University, 1001 19th Ave S, Nashville, TN, 37212, USA
| | - Tom Zhang
- California Institute of Technology, 1200 East California Boulevard, Pasadena, CA, 91125, USA.
| | - Yinghao Wu
- Department of Systems and Computational Biology, Albert Einstein College of Medicine, 1300 Morris Park Avenue, Bronx, NY, 10461, USA.
| |
Collapse
|
2
|
El Salamouni NS, Cater JH, Spenkelink LM, Yu H. Nanobody engineering: computational modelling and design for biomedical and therapeutic applications. FEBS Open Bio 2024. [PMID: 38898362 DOI: 10.1002/2211-5463.13850] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2024] [Revised: 05/25/2024] [Accepted: 06/10/2024] [Indexed: 06/21/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Nehad S El Salamouni
- Molecular Horizons and School of Chemistry and Molecular Bioscience, University of Wollongong, Australia
| | - Jordan H Cater
- Molecular Horizons and School of Chemistry and Molecular Bioscience, University of Wollongong, Australia
| | - Lisanne M Spenkelink
- Molecular Horizons and School of Chemistry and Molecular Bioscience, University of Wollongong, Australia
| | - Haibo Yu
- Molecular Horizons and School of Chemistry and Molecular Bioscience, University of Wollongong, Australia
- ARC Centre of Excellence in Quantum Biotechnology, University of Wollongong, Australia
| |
Collapse
|
3
|
Rollins ZA, Widatalla T, Waight A, Cheng AC, Metwally E. AbLEF: antibody language ensemble fusion for thermodynamically empowered property predictions. Bioinformatics 2024; 40:btae268. [PMID: 38627249 PMCID: PMC11256947 DOI: 10.1093/bioinformatics/btae268] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Revised: 03/27/2024] [Accepted: 04/23/2024] [Indexed: 05/08/2024] Open
Abstract
MOTIVATION Pre-trained protein language and/or structural models are often fine-tuned on drug development properties (i.e. developability properties) to accelerate drug discovery initiatives. However, these models generally rely on a single structural conformation and/or a single sequence as a molecular representation. We present a physics-based model, whereby 3D conformational ensemble representations are fused by a transformer-based architecture and concatenated to a language representation to predict antibody protein properties. Antibody language ensemble fusion enables the direct infusion of thermodynamic information into latent space and this enhances property prediction by explicitly infusing dynamic molecular behavior that occurs during experimental measurement. RESULTS We showcase the antibody language ensemble fusion model on two developability properties: hydrophobic interaction chromatography retention time and temperature of aggregation (Tagg). We find that (i) 3D conformational ensembles that are generated from molecular simulation can further improve antibody property prediction for small datasets, (ii) the performance benefit from 3D conformational ensembles matches shallow machine learning methods in the small data regime, and (iii) fine-tuned large protein language models can match smaller antibody-specific language models at predicting antibody properties. AVAILABILITY AND IMPLEMENTATION AbLEF codebase is available at https://github.com/merck/AbLEF.
Collapse
Affiliation(s)
- Zachary A Rollins
- Modeling and Informatics, Merck & Co., Inc, South San Francisco, CA, 94080, United States
| | - Talal Widatalla
- Modeling and Informatics, Merck & Co., Inc, South San Francisco, CA, 94080, United States
| | - Andrew Waight
- Discovery Biologics, Merck & Co., Inc, South San Francisco, CA, 94080, United States
| | - Alan C Cheng
- Modeling and Informatics, Merck & Co., Inc, South San Francisco, CA, 94080, United States
| | - Essam Metwally
- Modeling and Informatics, Merck & Co., Inc, South San Francisco, CA, 94080, United States
| |
Collapse
|
4
|
Bravi B. Development and use of machine learning algorithms in vaccine target selection. NPJ Vaccines 2024; 9:15. [PMID: 38242890 PMCID: PMC10798987 DOI: 10.1038/s41541-023-00795-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Accepted: 12/07/2023] [Indexed: 01/21/2024] Open
Abstract
Computer-aided discovery of vaccine targets has become a cornerstone of rational vaccine design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in rational vaccine design concerned with the identification of B and T cell epitopes and correlates of protection. I provide examples of ML models, as well as types of data and predictions for which they are built. I argue that interpretable ML has the potential to improve the identification of immunogens also as a tool for scientific discovery, by helping elucidate the molecular processes underlying vaccine-induced immune responses. I outline the limitations and challenges in terms of data availability and method development that need to be addressed to bridge the gap between advances in ML predictions and their translational application to vaccine design.
Collapse
Affiliation(s)
- Barbara Bravi
- Department of Mathematics, Imperial College London, London, SW7 2AZ, UK.
| |
Collapse
|
5
|
Gopinath SCB, Ramanathan S, More M, Patil K, Patil SJ, Patil N, Mahajan M, Madhavi V. A Review on Graphene Analytical Sensors for Biomarker-based Detection of Cancer. Curr Med Chem 2024; 31:1464-1484. [PMID: 37702170 DOI: 10.2174/0929867331666230912101634] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Revised: 05/01/2023] [Accepted: 06/22/2023] [Indexed: 09/14/2023]
Abstract
The engineering of nanoscale materials has broadened the scope of nanotechnology in a restricted functional system. Today, significant priority is given to immediate health diagnosis and monitoring tools for point-of-care testing and patient care. Graphene, as a one-atom carbon compound, has the potential to detect cancer biomarkers and its derivatives. The atom-wide graphene layer specialises in physicochemical characteristics, such as improved electrical and thermal conductivity, optical transparency, and increased chemical and mechanical strength, thus making it the best material for cancer biomarker detection. The outstanding mechanical, electrical, electrochemical, and optical properties of two-dimensional graphene can fulfil the scientific goal of any biosensor development, which is to develop a more compact and portable point-of-care device for quick and early cancer diagnosis. The bio-functionalisation of recognised biomarkers can be improved by oxygenated graphene layers and their composites. The significance of graphene that gleans its missing data for its high expertise to be evaluated, including the variety in surface modification and analytical reports. This review provides critical insights into graphene to inspire research that would address the current and remaining hurdles in cancer diagnosis.
Collapse
Affiliation(s)
- Subash Chandra Bose Gopinath
- Faculty of Chemical Engineering & Technology, Universiti Malaysia Perlis (UniMAP), 02600 Arau, Perlis, Malaysia
- Institute of Nano Electronic Engineering, Universiti Malaysia Perlis (UniMAP), 01000 Kangar, Perlis, Malaysia
- Micro System Technology, Centre of Excellence (CoE), Universiti Malaysia Perlis (UniMAP), 02600 Arau, Perlis, Malaysia
| | - Santheraleka Ramanathan
- Department of Biomedical Engineering and Health Sciences, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310, Skudai, Johor, Malaysia
| | - Mahesh More
- Department of Pharmaceutics, Sanjivani College of Pharmaceutical Education and Research, Kopargaon, India
| | - Ketan Patil
- Department of Pharmaceutics, Ahinsa Institute of Pharmacy, Dondaicha, India
| | | | - Narendra Patil
- Department of Pharmacology, Dr. A.P.J. Abdul Kalam University, Indore, India
| | - Mahendra Mahajan
- Department of Pharmaceutical Chemistry, H.R. Patel Institute of Pharmacy, Shirpur, India
| | - Vemula Madhavi
- BVRIT Hyderabad college of Engineering for Women, Hyderabad, India
| |
Collapse
|
6
|
Zhang G, Su Z, Zhang T, Wu Y. Machine-learning-based Structural Analysis of Interactions between Antibodies and Antigens. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.12.06.570397. [PMID: 38106177 PMCID: PMC10723427 DOI: 10.1101/2023.12.06.570397] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/19/2023]
Abstract
Computational analysis of paratope-epitope interactions between antibodies and their corresponding antigens can facilitate our understanding of the molecular mechanism underlying humoral immunity and boost the design of new therapeutics for many diseases. The recent breakthrough in artificial intelligence has made it possible to predict protein-protein interactions and model their structures. Unfortunately, detecting antigen-binding sites associated with a specific antibody is still a challenging problem. To tackle this challenge, we implemented a deep learning model to characterize interaction patterns between antibodies and their corresponding antigens. With high accuracy, our model can distinguish between antibody-antigen complexes and other types of protein-protein complexes. More intriguingly, we can identify antigens from other common protein binding regions with an accuracy of higher than 70% even if we only have the epitope information. This indicates that antigens have distinct features on their surface that antibodies can recognize. Additionally, our model was unable to predict the partnerships between antibodies and their particular antigens. This result suggests that one antigen may be targeted by more than one antibody and that antibodies may bind to previously unidentified proteins. Taken together, our results support the precision of antibody-antigen interactions while also suggesting positive future progress in the prediction of specific pairing.
Collapse
Affiliation(s)
- Grace Zhang
- Staples High School, 70 North Avenue, Westport, CT 06880
| | - Zhaoqian Su
- Data Science Institute, Vanderbilt University, 1001 19th Ave S, Nashville, TN, 37212
| | - Tom Zhang
- California Institute of Technology, 1200 East California Boulevard, Pasadena, CA 91125
| | - Yinghao Wu
- Department of Systems and Computational Biology, Albert Einstein College of Medicine, 1300 Morris Park Avenue, Bronx, NY 10461
| |
Collapse
|
7
|
Sun H, Zhou P, Su B. Electrochemiluminescence of Semiconductor Quantum Dots and Its Biosensing Applications: A Comprehensive Review. BIOSENSORS 2023; 13:708. [PMID: 37504107 PMCID: PMC10377090 DOI: 10.3390/bios13070708] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 06/26/2023] [Accepted: 07/03/2023] [Indexed: 07/29/2023]
Abstract
Electrochemiluminescence (ECL) is the chemiluminescence triggered by electrochemical reactions. Due to the unique excitation mode and inherent low background, ECL has been a powerful analytical technique to be widely used in biosensing and imaging. As an emerging ECL luminophore, semiconductor quantum dots (QDs) have apparent advantages over traditional molecular luminophores in terms of luminescence efficiency and signal modulation ability. Therefore, the development of an efficient ECL system with QDs as luminophores is of great significance to improve the sensitivity and detection flux of ECL biosensors. In this review, we give a comprehensive summary of recent advances in ECL using semiconductor QDs as luminophores. The luminescence process and ECL mechanism of semiconductor QDs with various coreactants are discussed first. Specifically, the influence of surface defects on ECL performance of semiconductor QDs is emphasized and several typical ECL enhancement strategies are summarized. Then, the applications of semiconductor QDs in ECL biosensing are overviewed, including immunoassay, nucleic acid analysis and the detection of small molecules. Finally, the challenges and prospects of semiconductor QDs as ECL luminophores in biosensing are featured.
Collapse
Affiliation(s)
- Hui Sun
- Key Laboratory of Excited-State Materials of Zhejiang Province, Institute of Analytical Chemistry, Department of Chemistry, Zhejiang University, Hangzhou 310058, China
| | - Ping Zhou
- Key Laboratory of Excited-State Materials of Zhejiang Province, Institute of Analytical Chemistry, Department of Chemistry, Zhejiang University, Hangzhou 310058, China
| | - Bin Su
- Key Laboratory of Excited-State Materials of Zhejiang Province, Institute of Analytical Chemistry, Department of Chemistry, Zhejiang University, Hangzhou 310058, China
| |
Collapse
|
8
|
Yang YX, Huang JY, Wang P, Zhu BT. AREA-AFFINITY: A Web Server for Machine Learning-Based Prediction of Protein-Protein and Antibody-Protein Antigen Binding Affinities. J Chem Inf Model 2023; 63:3230-3237. [PMID: 37235532 PMCID: PMC10268951 DOI: 10.1021/acs.jcim.2c01499] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Indexed: 05/28/2023]
Abstract
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: https://affinity.cuhk.edu.cn/.
Collapse
Affiliation(s)
- Yong Xiao Yang
- Shenzhen
Key Laboratory of Steroid Drug Discovery and Development, School of
Medicine, The Chinese University of Hong
Kong, Shenzhen, Guangdong 518172, China
| | - Jin Yan Huang
- Shenzhen
Key Laboratory of Steroid Drug Discovery and Development, School of
Medicine, The Chinese University of Hong
Kong, Shenzhen, Guangdong 518172, China
| | - Pan Wang
- Shenzhen
Key Laboratory of Steroid Drug Discovery and Development, School of
Medicine, The Chinese University of Hong
Kong, Shenzhen, Guangdong 518172, China
| | - Bao Ting Zhu
- Shenzhen
Key Laboratory of Steroid Drug Discovery and Development, School of
Medicine, The Chinese University of Hong
Kong, Shenzhen, Guangdong 518172, China
- Shenzhen
Bay Laboratory, Shenzhen, 518055, China
| |
Collapse
|
9
|
Miller NL, Clark T, Raman R, Sasisekharan R. Learned features of antibody-antigen binding affinity. Front Mol Biosci 2023; 10:1112738. [PMID: 36895805 PMCID: PMC9989197 DOI: 10.3389/fmolb.2023.1112738] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Accepted: 01/18/2023] [Indexed: 02/23/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Nathaniel L Miller
- Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States.,Koch Institute of Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Thomas Clark
- Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States.,Koch Institute of Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Rahul Raman
- Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States.,Koch Institute of Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Ram Sasisekharan
- Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States.,Koch Institute of Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA, United States
| |
Collapse
|