1
|
Benard-Valle M, Wouters Y, Ljungars A, Nguyen GTT, Ahmadi S, Ebersole TW, Dahl CH, Guadarrama-Martínez A, Jeppesen F, Eriksen H, Rodríguez-Barrera G, Boddum K, Jenkins TP, Bjørn SP, Schoffelen S, Voldborg BG, Alagón A, Laustsen AH. In vivo neutralization of coral snake venoms with an oligoclonal nanobody mixture in a murine challenge model. Nat Commun 2024; 15:4310. [PMID: 38773068 PMCID: PMC11109316 DOI: 10.1038/s41467-024-48539-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Accepted: 05/02/2024] [Indexed: 05/23/2024] Open
Abstract
Oligoclonal mixtures of broadly-neutralizing antibodies can neutralize complex compositions of similar and dissimilar antigens, making them versatile tools for the treatment of e.g., infectious diseases and animal envenomations. However, these biotherapeutics are complicated to develop due to their complex nature. In this work, we describe the application of various strategies for the discovery of cross-neutralizing nanobodies against key toxins in coral snake venoms using phage display technology. We prepare two oligoclonal mixtures of nanobodies and demonstrate their ability to neutralize the lethality induced by two North American coral snake venoms in mice, while individual nanobodies fail to do so. We thus show that an oligoclonal mixture of nanobodies can neutralize the lethality of venoms where the clinical syndrome is caused by more than one toxin family in a murine challenge model. The approaches described may find utility for the development of advanced biotherapeutics against snakebite envenomation and other pathologies where multi-epitope targeting is beneficial.
Collapse
Affiliation(s)
- Melisa Benard-Valle
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Yessica Wouters
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Anne Ljungars
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Giang Thi Tuyet Nguyen
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Shirin Ahmadi
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Tasja Wainani Ebersole
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Camilla Holst Dahl
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Alid Guadarrama-Martínez
- Departamento de Medicina Molecular y Bioprocesos, Instituto de Biotecnología, Universidad Nacional Autónoma de México, Avenida Universidad 2001, Cuernavaca, Mor, 62210, México
| | - Frederikke Jeppesen
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Helena Eriksen
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Gibran Rodríguez-Barrera
- Departamento de Medicina Molecular y Bioprocesos, Instituto de Biotecnología, Universidad Nacional Autónoma de México, Avenida Universidad 2001, Cuernavaca, Mor, 62210, México
| | - Kim Boddum
- Sophion Bioscience, DK-2750, Ballerup, Denmark
| | - Timothy Patrick Jenkins
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Sara Petersen Bjørn
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Sanne Schoffelen
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Bjørn Gunnar Voldborg
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark
| | - Alejandro Alagón
- Departamento de Medicina Molecular y Bioprocesos, Instituto de Biotecnología, Universidad Nacional Autónoma de México, Avenida Universidad 2001, Cuernavaca, Mor, 62210, México
| | - Andreas Hougaard Laustsen
- Department of Biotechnology and Biomedicine, Technical University of Denmark, DK-2800, Kongens, Lyngby, Denmark.
| |
Collapse
|
2
|
Barton J, Gaspariunas A, Galson JD, Leem J. Building Representation Learning Models for Antibody Comprehension. Cold Spring Harb Perspect Biol 2024; 16:a041462. [PMID: 38012013 PMCID: PMC10910360 DOI: 10.1101/cshperspect.a041462] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2023]
Abstract
Antibodies are versatile proteins with both the capacity to bind a broad range of targets and a proven track record as some of the most successful therapeutics. However, the development of novel antibody therapeutics is a lengthy and costly process. It is challenging to predict the functional and biophysical properties of antibodies from their amino acid sequence alone, requiring numerous experiments for full characterization. Machine learning, specifically deep representation learning, has emerged as a family of methods that can complement wet lab approaches and accelerate the overall discovery and engineering process. Here, we review advances in antibody sequence representation learning, and how this has improved antibody structure prediction and facilitated antibody optimization. We discuss challenges in the development and implementation of such models, such as the lack of publicly available, well-curated antibody function data and highlight opportunities for improvement. These and future advances in machine learning for antibody sequences have the potential to increase the success rate in developing new therapeutics, resulting in broader access to transformative medicines and improved patient outcomes.
Collapse
Affiliation(s)
- Justin Barton
- Alchemab Therapeutics Ltd, London N1C 4AX, United Kingdom
| | | | - Jacob D Galson
- Alchemab Therapeutics Ltd, London N1C 4AX, United Kingdom
| | - Jinwoo Leem
- Alchemab Therapeutics Ltd, London N1C 4AX, United Kingdom
| |
Collapse
|
3
|
Sedgwick R, Goertz JP, Stevens MM, Misener R, van der Wilk M. Transfer Learning Bayesian Optimization to Design Competitor DNA Molecules for Use in Diagnostic Assays. ARXIV 2024:arXiv:2402.17704v1. [PMID: 38463498 PMCID: PMC10925383] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 03/12/2024]
Abstract
With the rise in engineered biomolecular devices, there is an increased need for tailor-made biological sequences. Often, many similar biological sequences need to be made for a specific application meaning numerous, sometimes prohibitively expensive, lab experiments are necessary for their optimization. This paper presents a transfer learning design of experiments workflow to make this development feasible. By combining a transfer learning surrogate model with Bayesian optimization, we show how the total number of experiments can be reduced by sharing information between optimization tasks. We demonstrate the reduction in the number of experiments using data from the development of DNA competitors for use in an amplification-based diagnostic assay. We use cross-validation to compare the predictive accuracy of different transfer learning models, and then compare the performance of the models for both single objective and penalized optimization tasks.
Collapse
Affiliation(s)
- Ruby Sedgwick
- Department of Materials, Department of Bioengineering and Institute of Biomedical Engineering, Imperial College London, London
- Department of Computing, Imperial College London, London
| | - John P Goertz
- Department of Materials, Department of Bioengineering and Institute of Biomedical Engineering, Imperial College London, London
| | - Molly M Stevens
- Department of Materials, Department of Bioengineering and Institute of Biomedical Engineering, Imperial College London, London
- Department of Physiology, Anatomy and Genetics, Department of Engineering Science, and Kavli Institute for Nanoscience Discovery, University of Oxford, Oxford
| | - Ruth Misener
- Department of Computing, Imperial College London, London
| | | |
Collapse
|
4
|
Gallo E. Revolutionizing Synthetic Antibody Design: Harnessing Artificial Intelligence and Deep Sequencing Big Data for Unprecedented Advances. Mol Biotechnol 2024:10.1007/s12033-024-01064-2. [PMID: 38308755 DOI: 10.1007/s12033-024-01064-2] [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: 11/03/2023] [Accepted: 01/02/2024] [Indexed: 02/05/2024]
Abstract
Synthetic antibodies (Abs) represent a category of engineered proteins meticulously crafted to replicate the functions of their natural counterparts. Such Abs are generated in vitro, enabling advanced molecular alterations associated with antigen recognition, paratope site engineering, and biochemical refinements. In a parallel realm, deep sequencing has brought about a paradigm shift in molecular biology. It facilitates the prompt and cost-effective high-throughput sequencing of DNA and RNA molecules, enabling the comprehensive big data analysis of Ab transcriptomes, including specific regions of interest. Significantly, the integration of artificial intelligence (AI), based on machine- and deep- learning approaches, has fundamentally transformed our capacity to discern patterns hidden within deep sequencing big data, including distinctive Ab features and protein folding free energy landscapes. Ultimately, current AI advances can generate approximations of the most stable Ab structural configurations, enabling the prediction of de novo synthetic Abs. As a result, this manuscript comprehensively examines the latest and relevant literature concerning the intersection of deep sequencing big data and AI methodologies for the design and development of synthetic Abs. Together, these advancements have accelerated the exploration of antibody repertoires, contributing to the refinement of synthetic Ab engineering and optimizations, and facilitating advancements in the lead identification process.
Collapse
Affiliation(s)
- Eugenio Gallo
- Avance Biologicals, Department of Medicinal Chemistry, 950 Dupont Street, Toronto, ON, M6H 1Z2, Canada.
- RevivAb, Department of Protein Engineering, Av. Ipiranga, 6681, Partenon, Porto Alegre, RS, 90619-900, Brazil.
| |
Collapse
|
5
|
Colliandre L, Muller C. Bayesian Optimization in Drug Discovery. Methods Mol Biol 2024; 2716:101-136. [PMID: 37702937 DOI: 10.1007/978-1-0716-3449-3_5] [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] [Indexed: 09/14/2023]
Abstract
Drug discovery deals with the search for initial hits and their optimization toward a targeted clinical profile. Throughout the discovery pipeline, the candidate profile will evolve, but the optimization will mainly stay a trial-and-error approach. Tons of in silico methods have been developed to improve and fasten this pipeline. Bayesian optimization (BO) is a well-known method for the determination of the global optimum of a function. In the last decade, BO has gained popularity in the early drug design phase. This chapter starts with the concept of black box optimization applied to drug design and presents some approaches to tackle it. Then it focuses on BO and explains its principle and all the algorithmic building blocks needed to implement it. This explanation aims to be accessible to people involved in drug discovery projects. A strong emphasis is made on the solutions to deal with the specific constraints of drug discovery. Finally, a large set of practical applications of BO is highlighted.
Collapse
|
6
|
Mullin M, McClory J, Haynes W, Grace J, Robertson N, van Heeke G. Applications and challenges in designing VHH-based bispecific antibodies: leveraging machine learning solutions. MAbs 2024; 16:2341443. [PMID: 38666503 PMCID: PMC11057648 DOI: 10.1080/19420862.2024.2341443] [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: 09/22/2023] [Accepted: 04/05/2024] [Indexed: 05/01/2024] Open
Abstract
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.
Collapse
|
7
|
Abstract
In attempts to simulate the protonation of proteins, a major challenge is that the number of protonation states grows rapidly as a function (2N) of the number of protonation sites (N). Expression on the free energy of the protonation state as an N-site Ising model ─ using an empirical Generalized-Born model ─ allows a quantum computer to efficiently determine the important states at a given pH value and subsequently reconstruct the pH titration process at all sites. Compared with the exact results painstakingly obtained with classical computers, the results obtained using quantum computers show good agreement for staphylococcal nuclease and excellent agreement for α-lactalbumin. This work illustrates the effectiveness of quantum computers in sampling important physical states, which may be useful in attacking challenging biomolecular problems.
Collapse
Affiliation(s)
- Hao Hu
- Department of Biochemistry and Biophysics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599, United States
- Polaris Quantum Biotech Inc., Suite 205, 201 W Main St., Durham, North Carolina 27701, United States
| |
Collapse
|
8
|
Bauer J, Rajagopal N, Gupta P, Gupta P, Nixon AE, Kumar S. How can we discover developable antibody-based biotherapeutics? Front Mol Biosci 2023; 10:1221626. [PMID: 37609373 PMCID: PMC10441133 DOI: 10.3389/fmolb.2023.1221626] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Accepted: 07/10/2023] [Indexed: 08/24/2023] Open
Abstract
Antibody-based biotherapeutics have emerged as a successful class of pharmaceuticals despite significant challenges and risks to their discovery and development. This review discusses the most frequently encountered hurdles in the research and development (R&D) of antibody-based biotherapeutics and proposes a conceptual framework called biopharmaceutical informatics. Our vision advocates for the syncretic use of computation and experimentation at every stage of biologic drug discovery, considering developability (manufacturability, safety, efficacy, and pharmacology) of potential drug candidates from the earliest stages of the drug discovery phase. The computational advances in recent years allow for more precise formulation of disease concepts, rapid identification, and validation of targets suitable for therapeutic intervention and discovery of potential biotherapeutics that can agonize or antagonize them. Furthermore, computational methods for de novo and epitope-specific antibody design are increasingly being developed, opening novel computationally driven opportunities for biologic drug discovery. Here, we review the opportunities and limitations of emerging computational approaches for optimizing antigens to generate robust immune responses, in silico generation of antibody sequences, discovery of potential antibody binders through virtual screening, assessment of hits, identification of lead drug candidates and their affinity maturation, and optimization for developability. The adoption of biopharmaceutical informatics across all aspects of drug discovery and development cycles should help bring affordable and effective biotherapeutics to patients more quickly.
Collapse
Affiliation(s)
- Joschka Bauer
- Early Stage Pharmaceutical Development Biologicals, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach/Riss, Germany
- In Silico Team, Boehringer Ingelheim, Hannover, Germany
| | - Nandhini Rajagopal
- In Silico Team, Boehringer Ingelheim, Hannover, Germany
- Biotherapeutics Discovery, Boehringer Ingelheim Pharmaceuticals Inc., Ridgefield, CT, United States
| | - Priyanka Gupta
- In Silico Team, Boehringer Ingelheim, Hannover, Germany
- Biotherapeutics Discovery, Boehringer Ingelheim Pharmaceuticals Inc., Ridgefield, CT, United States
| | - Pankaj Gupta
- In Silico Team, Boehringer Ingelheim, Hannover, Germany
- Biotherapeutics Discovery, Boehringer Ingelheim Pharmaceuticals Inc., Ridgefield, CT, United States
| | - Andrew E. Nixon
- Biotherapeutics Discovery, Boehringer Ingelheim Pharmaceuticals Inc., Ridgefield, CT, United States
| | - Sandeep Kumar
- In Silico Team, Boehringer Ingelheim, Hannover, Germany
- Biotherapeutics Discovery, Boehringer Ingelheim Pharmaceuticals Inc., Ridgefield, CT, United States
| |
Collapse
|
9
|
Li L, Gupta E, Spaeth J, Shing L, Jaimes R, Engelhart E, Lopez R, Caceres RS, Bepler T, Walsh ME. Machine learning optimization of candidate antibody yields highly diverse sub-nanomolar affinity antibody libraries. Nat Commun 2023; 14:3454. [PMID: 37308471 DOI: 10.1038/s41467-023-39022-2] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Accepted: 05/23/2023] [Indexed: 06/14/2023] Open
Abstract
Therapeutic antibodies are an important and rapidly growing drug modality. However, the design and discovery of early-stage antibody therapeutics remain a time and cost-intensive endeavor. Here we present an end-to-end Bayesian, language model-based method for designing large and diverse libraries of high-affinity single-chain variable fragments (scFvs) that are then empirically measured. In a head-to-head comparison with a directed evolution approach, we show that the best scFv generated from our method represents a 28.7-fold improvement in binding over the best scFv from the directed evolution. Additionally, 99% of designed scFvs in our most successful library are improvements over the initial candidate scFv. By comparing a library's predicted success to actual measurements, we demonstrate our method's ability to explore tradeoffs between library success and diversity. Results of our work highlight the significant impact machine learning models can have on scFv development. We expect our method to be broadly applicable and provide value to other protein engineering tasks.
Collapse
Affiliation(s)
- Lin Li
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA.
| | - Esther Gupta
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA
| | - John Spaeth
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA
| | - Leslie Shing
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA
| | - Rafael Jaimes
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA
| | | | | | - Rajmonda S Caceres
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA
| | - Tristan Bepler
- Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA, USA
- Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY, USA
| | - Matthew E Walsh
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA
- Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA
| |
Collapse
|
10
|
Parkinson J, Hard R, Wang W. The RESP AI model accelerates the identification of tight-binding antibodies. Nat Commun 2023; 14:454. [PMID: 36709319 PMCID: PMC9884274 DOI: 10.1038/s41467-023-36028-8] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2022] [Accepted: 01/13/2023] [Indexed: 01/30/2023] Open
Abstract
High-affinity antibodies are often identified through directed evolution, which may require many iterations of mutagenesis and selection to find an optimal candidate. Deep learning techniques hold the potential to accelerate this process but the existing methods cannot provide the confidence interval or uncertainty needed to assess the reliability of the predictions. Here we present a pipeline called RESP for efficient identification of high affinity antibodies. We develop a learned representation trained on over 3 million human B-cell receptor sequences to encode antibody sequences. We then develop a variational Bayesian neural network to perform ordinal regression on a set of the directed evolution sequences binned by off-rate and quantify their likelihood to be tight binders against an antigen. Importantly, this model can assess sequences not present in the directed evolution library and thus greatly expand the search space to uncover the best sequences for experimental evaluation. We demonstrate the power of this pipeline by achieving a 17-fold improvement in the KD of the PD-L1 antibody Atezolizumab and this success illustrates the potential of RESP in facilitating general antibody development.
Collapse
Affiliation(s)
- Jonathan Parkinson
- Department of Chemistry and Biochemistry, University of California, San Diego, La Jolla, CA, 92093-0359, USA
| | - Ryan Hard
- Department of Chemistry and Biochemistry, University of California, San Diego, La Jolla, CA, 92093-0359, USA
| | - Wei Wang
- Department of Chemistry and Biochemistry, University of California, San Diego, La Jolla, CA, 92093-0359, USA. .,Department of Cellular and Molecular Medicine, University of California, San Diego, La Jolla, CA, 92093-0359, USA.
| |
Collapse
|
11
|
Fernández-Quintero ML, Ljungars A, Waibl F, Greiff V, Andersen JT, Gjølberg TT, Jenkins TP, Voldborg BG, Grav LM, Kumar S, Georges G, Kettenberger H, Liedl KR, Tessier PM, McCafferty J, Laustsen AH. Assessing developability early in the discovery process for novel biologics. MAbs 2023; 15:2171248. [PMID: 36823021 PMCID: PMC9980699 DOI: 10.1080/19420862.2023.2171248] [Citation(s) in RCA: 12] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2022] [Accepted: 01/18/2023] [Indexed: 02/25/2023] Open
Abstract
Beyond potency, a good developability profile is a key attribute of a biological drug. Selecting and screening for such attributes early in the drug development process can save resources and avoid costly late-stage failures. Here, we review some of the most important developability properties that can be assessed early on for biologics. These include the influence of the source of the biologic, its biophysical and pharmacokinetic properties, and how well it can be expressed recombinantly. We furthermore present in silico, in vitro, and in vivo methods and techniques that can be exploited at different stages of the discovery process to identify molecules with liabilities and thereby facilitate the selection of the most optimal drug leads. Finally, we reflect on the most relevant developability parameters for injectable versus orally delivered biologics and provide an outlook toward what general trends are expected to rise in the development of biologics.
Collapse
Affiliation(s)
- Monica L. Fernández-Quintero
- Center for Molecular Biosciences Innsbruck (CMBI), Department of General, Inorganic and Theoretical Chemistry, University of Innsbruck, Innsbruck, Austria
| | - Anne Ljungars
- Department of Biotechnology and Biomedicine, Technical University of Denmark, Kongens Lyngby, Denmark
| | - Franz Waibl
- Center for Molecular Biosciences Innsbruck (CMBI), Department of General, Inorganic and Theoretical Chemistry, University of Innsbruck, Innsbruck, Austria
| | - Victor Greiff
- Department of Immunology, University of Oslo, Oslo, Norway
| | - Jan Terje Andersen
- Department of Immunology, University of Oslo, Oslo University Hospital Rikshospitalet, Oslo, Norway
- Institute of Clinical Medicine and Department of Pharmacology, University of Oslo, Oslo, Norway
| | | | - Timothy P. Jenkins
- Department of Biotechnology and Biomedicine, Technical University of Denmark, Kongens Lyngby, Denmark
| | - Bjørn Gunnar Voldborg
- National Biologics Facility, Department of Biotechnology and Biomedicine, Technical University of Denmark, Kongens Lyngby, Denmark
| | - Lise Marie Grav
- Department of Biotechnology and Biomedicine, Technical University of Denmark, Kongens Lyngby, Denmark
| | - Sandeep Kumar
- Biotherapeutics Discovery, Boehringer Ingelheim Pharmaceuticals Inc, Ridgefield, CT, USA
| | - Guy Georges
- Roche Pharma Research and Early Development, Large Molecule Research, Roche Innovation Center Munich, Penzberg, Germany
| | - Hubert Kettenberger
- Roche Pharma Research and Early Development, Large Molecule Research, Roche Innovation Center Munich, Penzberg, Germany
| | - Klaus R. Liedl
- Center for Molecular Biosciences Innsbruck (CMBI), Department of General, Inorganic and Theoretical Chemistry, University of Innsbruck, Innsbruck, Austria
| | - Peter M. Tessier
- Department of Chemical Engineering, Pharmaceutical Sciences and Biomedical Engineering, Biointerfaces Institute, University of Michigan, Ann Arbor, Michigan, USA
| | - John McCafferty
- Department of Medicine, Cambridge Institute of Therapeutic Immunology and Infectious Disease, University of Cambridge, Cambridge, UK
- Maxion Therapeutics, Babraham Research Campus, Cambridge, UK
| | - Andreas H. Laustsen
- Department of Biotechnology and Biomedicine, Technical University of Denmark, Kongens Lyngby, Denmark
| |
Collapse
|
12
|
Kakuzaki T, Koga H, Takizawa S, Metsugi S, Shiraiwa H, Sampei Z, Yoshida K, Tsunoda H, Teramoto R. Monte Carlo Thompson sampling-guided design for antibody engineering. MAbs 2023; 15:2244214. [PMID: 37605371 PMCID: PMC10446805 DOI: 10.1080/19420862.2023.2244214] [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: 12/22/2022] [Revised: 07/27/2023] [Accepted: 07/29/2023] [Indexed: 08/23/2023] Open
Abstract
Antibodies are one of the predominant treatment modalities for various diseases. To improve the characteristics of a lead antibody, such as antigen-binding affinity and stability, we conducted comprehensive substitutions and exhaustively explored their sequence space. However, it is practically unfeasible to evaluate all possible combinations of mutations owing to combinatorial explosion when multiple amino acid residues are incorporated. It was recently reported that a machine-learning guided protein engineering approach such as Thompson sampling (TS) has been used to efficiently explore sequence space in the framework of Bayesian optimization. For TS, over-exploration occurs when the initial data are biasedly distributed in the vicinity of the lead antibody. We handle a large-scale virtual library that includes numerous mutations. When the number of experiments is limited, this over-exploration causes a serious issue. Thus, we conducted Monte Carlo Thompson sampling (MTS) to balance the exploration-exploitation trade-off by defining the posterior distribution via the Monte Carlo method and compared its performance with TS in antibody engineering. Our results demonstrated that MTS largely outperforms TS in discovering desirable candidates at an earlier round when over-exploration occurs on TS. Thus, the MTS method is a powerful technique for efficiently discovering antibodies with desired characteristics when the number of rounds is limited.
Collapse
Affiliation(s)
- Taro Kakuzaki
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| | - Hikaru Koga
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| | - Shuuki Takizawa
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| | - Shoichi Metsugi
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| | | | - Zenjiro Sampei
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| | - Kenji Yoshida
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| | - Hiroyuki Tsunoda
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| | - Reiji Teramoto
- Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, Japan
| |
Collapse
|