Monte Carlo Thompson sampling-guided design for antibody engineering

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 unfe...

Full description

Saved in:
Bibliographic Details
Main Authors: Taro Kakuzaki, Hikaru Koga, Shuuki Takizawa, Shoichi Metsugi, Hirotake Shiraiwa, Zenjiro Sampei, Kenji Yoshida, Hiroyuki Tsunoda, Reiji Teramoto
Format: Article
Language:English
Published: Taylor & Francis Group 2023-12-01
Series:mAbs
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19420862.2023.2244214
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387595896717312
author Taro Kakuzaki
Hikaru Koga
Shuuki Takizawa
Shoichi Metsugi
Hirotake Shiraiwa
Zenjiro Sampei
Kenji Yoshida
Hiroyuki Tsunoda
Reiji Teramoto
author_facet Taro Kakuzaki
Hikaru Koga
Shuuki Takizawa
Shoichi Metsugi
Hirotake Shiraiwa
Zenjiro Sampei
Kenji Yoshida
Hiroyuki Tsunoda
Reiji Teramoto
author_sort Taro Kakuzaki
collection DOAJ
description 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.
format Article
id doaj-art-464d1ce6486045f391b77c27fa515809
institution Kabale University
issn 1942-0862
1942-0870
language English
publishDate 2023-12-01
publisher Taylor & Francis Group
record_format Article
series mAbs
spelling doaj-art-464d1ce6486045f391b77c27fa5158092025-08-20T03:51:35ZengTaylor & Francis GroupmAbs1942-08621942-08702023-12-0115110.1080/19420862.2023.2244214Monte Carlo Thompson sampling-guided design for antibody engineeringTaro Kakuzaki0Hikaru Koga1Shuuki Takizawa2Shoichi Metsugi3Hirotake Shiraiwa4Zenjiro Sampei5Kenji Yoshida6Hiroyuki Tsunoda7Reiji Teramoto8Research Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanResearch Division, Chugai Pharmaceutical Co., Ltd., Yokohama, JapanAntibodies 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.https://www.tandfonline.com/doi/10.1080/19420862.2023.2244214Antibody engineeringBayesian optimizationmachine learningMonte Carlo methodprotein engineeringThompson sampling
spellingShingle Taro Kakuzaki
Hikaru Koga
Shuuki Takizawa
Shoichi Metsugi
Hirotake Shiraiwa
Zenjiro Sampei
Kenji Yoshida
Hiroyuki Tsunoda
Reiji Teramoto
Monte Carlo Thompson sampling-guided design for antibody engineering
mAbs
Antibody engineering
Bayesian optimization
machine learning
Monte Carlo method
protein engineering
Thompson sampling
title Monte Carlo Thompson sampling-guided design for antibody engineering
title_full Monte Carlo Thompson sampling-guided design for antibody engineering
title_fullStr Monte Carlo Thompson sampling-guided design for antibody engineering
title_full_unstemmed Monte Carlo Thompson sampling-guided design for antibody engineering
title_short Monte Carlo Thompson sampling-guided design for antibody engineering
title_sort monte carlo thompson sampling guided design for antibody engineering
topic Antibody engineering
Bayesian optimization
machine learning
Monte Carlo method
protein engineering
Thompson sampling
url https://www.tandfonline.com/doi/10.1080/19420862.2023.2244214
work_keys_str_mv AT tarokakuzaki montecarlothompsonsamplingguideddesignforantibodyengineering
AT hikarukoga montecarlothompsonsamplingguideddesignforantibodyengineering
AT shuukitakizawa montecarlothompsonsamplingguideddesignforantibodyengineering
AT shoichimetsugi montecarlothompsonsamplingguideddesignforantibodyengineering
AT hirotakeshiraiwa montecarlothompsonsamplingguideddesignforantibodyengineering
AT zenjirosampei montecarlothompsonsamplingguideddesignforantibodyengineering
AT kenjiyoshida montecarlothompsonsamplingguideddesignforantibodyengineering
AT hiroyukitsunoda montecarlothompsonsamplingguideddesignforantibodyengineering
AT reijiteramoto montecarlothompsonsamplingguideddesignforantibodyengineering