EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AbImmPred: An immunogenicity prediction method for therapeutic antibodies using AntiBERTy-based sequence features

Hong Wang iD, Xiaohu Hao, Yuzhuo He, Long Fan iD

PLOS ONE · 23.02.2024 · 19 (2) · e0296737

DOI: 10.1371/journal.pone.0296737 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 23.02.2024. Verfasst von Hong Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Production and R&D Center I of Life Science Services, GenScript Biotech Corporation, Nanjing, China. Hauptthemen laut MEDLINE: Machine Learning, Antibodies. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the unnecessary immune responses induced by therapeutic antibodies in clinical applications, immunogenicity is an important factor to be considered in the development of antibody therapeutics. To a certain extent, there is a lag in using wet-lab experiments to test the immunogenicity in the development process of antibody therapeutics. Developing a computational method to predict the immunogenicity at once the antibody sequence is designed, is of great significance for the screening in the early stage and reducing the risk of antibody therapeutics development. In this study, a computational immunogenicity prediction method was proposed on the basis of AntiBERTy-based features of amino sequences in the antibody variable region. The AntiBERTy-based sequence features were first calculated using the AntiBERTy pre-trained model. Principal component analysis (PCA) was then applied to reduce the extracted feature to two dimensions to obtain the final features. AutoGluon was then used to train multiple machine learning models and the best one, the weighted ensemble model, was obtained through 5-fold cross-validation on the collected data. The data contains 199 commercial therapeutic antibodies, of which 177 samples were used for model training and 5-fold cross-validation, and the remaining 22 samples were used as an independent test dataset to evaluate the performance of the constructed model and compare it with other prediction methods. Test results show that the proposed method outperforms the comparison method with 0.7273 accuracy on the independent test dataset, which is 9.09% higher than the comparison method. The corresponding web server is available through the official website of GenScript Co., Ltd., https://www.genscript.com/tools/antibody-immunogenicity .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAntibodies

Substanzen

Antibodies

Autor:innen und Institutionen

  • Production and R&D Center I of Life Science Services, GenScript Biotech Corporation, Nanjing, China.
  • Production and R&D Center I of Life Science Services, GenScript (Shanghai) Biotech Co., Ltd., Shanghai, China.

ORCID-Profile: Hong Wang, Long Fan

Förderung

  • China Postdoctoral Science Foundation

Zitieren

APA

Wang, H., Hao, X., He, Y., & Fan, L. (2024). AbImmPred: An immunogenicity prediction method for therapeutic antibodies using AntiBERTy-based sequence features. PLOS ONE, 19(2), e0296737. https://doi.org/10.1371/journal.pone.0296737

Vancouver

Wang H, Hao X, He Y, Fan L. AbImmPred: An immunogenicity prediction method for therapeutic antibodies using AntiBERTy-based sequence features. PLOS ONE. 2024;19(2):e0296737. doi:10.1371/journal.pone.0296737

BibTeX
@article{Wang2024,
  author = {Wang, Hong and Hao, Xiaohu and He, Yuzhuo and Fan, Long},
  title = {AbImmPred: An immunogenicity prediction method for therapeutic antibodies using AntiBERTy-based sequence features},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {2},
  pages = {e0296737},
  doi = {10.1371/journal.pone.0296737}
}
Kostenlos starten →