EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimization

The identification and optimization of mutations in nanobodies are crucial for enhancing their therapeutic potential in disease prevention and control. However, this process is often complex and time-consuming, which limit its widespread application in practice. In this study, we developed a workflo...

Full description

Saved in:
Bibliographic Details
Main Authors: Danyang Xiong, Yongfan Ming, Yuting Li, Shuhan Li, Kexin Chen, Jinfeng Liu, Lili Duan, Honglin Li, Min Li, Xiao He
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Journal of Pharmaceutical Analysis
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2095177925000772
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318429323952128
author Danyang Xiong
Yongfan Ming
Yuting Li
Shuhan Li
Kexin Chen
Jinfeng Liu
Lili Duan
Honglin Li
Min Li
Xiao He
author_facet Danyang Xiong
Yongfan Ming
Yuting Li
Shuhan Li
Kexin Chen
Jinfeng Liu
Lili Duan
Honglin Li
Min Li
Xiao He
author_sort Danyang Xiong
collection DOAJ
description The identification and optimization of mutations in nanobodies are crucial for enhancing their therapeutic potential in disease prevention and control. However, this process is often complex and time-consuming, which limit its widespread application in practice. In this study, we developed a workflow, named Evolutionary-Nanobody (EvoNB), to predict key mutation sites of nanobodies by combining protein language models (PLMs) and molecular dynamic (MD) simulations. By fine-tuning the ESM2 model on a large-scale nanobody dataset, the ability of EvoNB to capture specific sequence features of nanobodies was significantly enhanced. The fine-tuned EvoNB model demonstrated higher predictive accuracy in the conserved framework and highly variable complementarity-determining regions of nanobodies. Additionally, we selected four widely representative nanobody–antigen complexes to verify the predicted effects of mutations. MD simulations analyzed the energy changes caused by these mutations to predict their impact on binding affinity to the targets. The results showed that multiple mutations screened by EvoNB significantly enhanced the binding affinity between nanobody and its target, further validating the potential of this workflow for designing and optimizing nanobody mutations. Additionally, sequence-based predictions are generally less dependent on structural absence, allowing them to be more easily integrated with tools for structural predictions, such as AlphaFold 3. Through mutation prediction and systematic analysis of key sites, we can quickly predict the most promising variants for experimental validation without relying on traditional evolutionary or selection processes. The EvoNB workflow provides an effective tool for the rapid optimization of nanobodies and facilitates the application of PLMs in the biomedical field.
format Article
id doaj-art-d69eb9606c5e4eaa90a148d24a171cae
institution Kabale University
issn 2095-1779
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Journal of Pharmaceutical Analysis
spelling doaj-art-d69eb9606c5e4eaa90a148d24a171cae2025-08-20T03:50:50ZengElsevierJournal of Pharmaceutical Analysis2095-17792025-06-0115610126010.1016/j.jpha.2025.101260EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimizationDanyang Xiong0Yongfan Ming1Yuting Li2Shuhan Li3Kexin Chen4Jinfeng Liu5Lili Duan6Honglin Li7Min Li8Xiao He9Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai, 200062, ChinaSchool of Computer Science and Engineering, Central South University, Changsha, 410083, ChinaShanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai, 200062, ChinaShanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai, 200062, ChinaSchool of Computer Science and Engineering, Central South University, Changsha, 410083, ChinaShanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai, 200062, China; School of Science, Department of Basic Medicine and Clinical Pharmacy, State Key Laboratory of Natural Medicines, China Pharmaceutical University, Nanjing, 210009, China; Corresponding author. School of Science, Department of Basic Medicine and Clinical Pharmacy, State Key Laboratory of Natural Medicines, China Pharmaceutical University, Nanjing, 210009, China.School of Physics and Electronics, Shandong Normal University, Jinan, 250014, China; Corresponding author.Innovation Center for Artificial Intelligence and Drug Discovery, East China Normal University, Shanghai, 200062, China; Lingang Laboratory, Shanghai, 200062, ChinaSchool of Computer Science and Engineering, Central South University, Changsha, 410083, China; Corresponding author.Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai, 200062, China; Chongqing Key Laboratory of Precision Optics, Chongqing Institute of East China Normal University, Chongqing, 401120, China; New York University–East China Normal University Center for Computational Chemistry, New York University Shanghai, Shanghai, 200062, China; Corresponding author. Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai, 200062, China.The identification and optimization of mutations in nanobodies are crucial for enhancing their therapeutic potential in disease prevention and control. However, this process is often complex and time-consuming, which limit its widespread application in practice. In this study, we developed a workflow, named Evolutionary-Nanobody (EvoNB), to predict key mutation sites of nanobodies by combining protein language models (PLMs) and molecular dynamic (MD) simulations. By fine-tuning the ESM2 model on a large-scale nanobody dataset, the ability of EvoNB to capture specific sequence features of nanobodies was significantly enhanced. The fine-tuned EvoNB model demonstrated higher predictive accuracy in the conserved framework and highly variable complementarity-determining regions of nanobodies. Additionally, we selected four widely representative nanobody–antigen complexes to verify the predicted effects of mutations. MD simulations analyzed the energy changes caused by these mutations to predict their impact on binding affinity to the targets. The results showed that multiple mutations screened by EvoNB significantly enhanced the binding affinity between nanobody and its target, further validating the potential of this workflow for designing and optimizing nanobody mutations. Additionally, sequence-based predictions are generally less dependent on structural absence, allowing them to be more easily integrated with tools for structural predictions, such as AlphaFold 3. Through mutation prediction and systematic analysis of key sites, we can quickly predict the most promising variants for experimental validation without relying on traditional evolutionary or selection processes. The EvoNB workflow provides an effective tool for the rapid optimization of nanobodies and facilitates the application of PLMs in the biomedical field.http://www.sciencedirect.com/science/article/pii/S2095177925000772NanobodyProtein language models (PLMs)ESM2 modelEvolutionary-nanobody (EvoNB)MD simulationsAlphaFold 3
spellingShingle Danyang Xiong
Yongfan Ming
Yuting Li
Shuhan Li
Kexin Chen
Jinfeng Liu
Lili Duan
Honglin Li
Min Li
Xiao He
EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimization
Journal of Pharmaceutical Analysis
Nanobody
Protein language models (PLMs)
ESM2 model
Evolutionary-nanobody (EvoNB)
MD simulations
AlphaFold 3
title EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimization
title_full EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimization
title_fullStr EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimization
title_full_unstemmed EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimization
title_short EvoNB: A protein language model-based workflow for nanobody mutation prediction and optimization
title_sort evonb a protein language model based workflow for nanobody mutation prediction and optimization
topic Nanobody
Protein language models (PLMs)
ESM2 model
Evolutionary-nanobody (EvoNB)
MD simulations
AlphaFold 3
url http://www.sciencedirect.com/science/article/pii/S2095177925000772
work_keys_str_mv AT danyangxiong evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT yongfanming evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT yutingli evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT shuhanli evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT kexinchen evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT jinfengliu evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT liliduan evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT honglinli evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT minli evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization
AT xiaohe evonbaproteinlanguagemodelbasedworkflowfornanobodymutationpredictionandoptimization