EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ProtT5 and random forests-based viscosity prediction method for therapeutic mAbs

Xiaohu Hao, Long Fan

European Journal of Pharmaceutical Sciences · 2024-03 · 194 · 106705

DOI: 10.1016/j.ejps.2024.106705 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Pharmaceutical Sciences, 2024-03. Verfasst von Xiaohu Hao und 1 weiteren Autor:innen. Beteiligte Einrichtung: Production and R&D Center I of LSS (Life Science Service), GenScript Biotech Corporation, No. 28, Yongxi Rd., Nanjing, 211110, Jiangsu, China. Hauptthemen laut MEDLINE: Random Forest, Antibodies, Monoclonal. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Viscosity is a key characteristic of therapeutic antibodies for subcutaneous administration which requires low volume and high concentration formulations. It would be highly beneficial to accurately predict the viscosity of newly developed therapeutic antibodies in the early stages of development. In this work, a ProtT5-XL-UniRef50 (ProtT5) and Random Forests (RF)-based prediction method was proposed for accurately predicting the viscosity of monoclonal antibodies, with only corresponding sequences needed. Starting from the given heavy and light chain V-region sequences, corresponding features were first extracted from the ProtT5 pretrained model. Kernel principal analysis (Kernel-PCA) was then used for reducing the extracted 2048-D (1024-D for each sequence) feature vector to a reasonable level for efficient training of the RF-regressor. Then, the RF model was constructed on 40 commercially available therapeutic antibodies and tested with 3-folds cross-validation. Test results show that the model could reproduce the viscosity value at a high level (Pearson correlation coefficient (PCC) = 0.928). Performance on classifying high (>30 cP) and low (

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Random ForestAntibodies, MonoclonalViscosityDrug Compounding

Stichwörter der Autor:innen

Monoclonal antibodyProtT5Random forestsViscosity

Substanzen

Antibodies, Monoclonal

Autor:innen und Institutionen

  • Production and R&D Center I of LSS (Life Science Service), GenScript Biotech Corporation, No. 28, Yongxi Rd., Nanjing, 211110, Jiangsu, China.
  • Production and R&D Center I of LSS (Life Science Service), GenScript Biotech Corporation, No. 28, Yongxi Rd., Nanjing, 211110, Jiangsu, China; Production and R&D Center I of LSS (Life Science Service), GenScript (Shangh…

Förderung

  • China Postdoctoral Science Foundation

Zitieren

APA

Hao, X., & Fan, L. (2024). ProtT5 and random forests-based viscosity prediction method for therapeutic mAbs. European Journal of Pharmaceutical Sciences, 194, 106705. https://doi.org/10.1016/j.ejps.2024.106705

Vancouver

Hao X, Fan L. ProtT5 and random forests-based viscosity prediction method for therapeutic mAbs. European Journal of Pharmaceutical Sciences. 2024;194:106705. doi:10.1016/j.ejps.2024.106705

BibTeX
@article{Hao2024,
  author = {Hao, Xiaohu and Fan, Long},
  title = {ProtT5 and random forests-based viscosity prediction method for therapeutic mAbs},
  journal = {European Journal of Pharmaceutical Sciences},
  year = {2024},
  volume = {194},
  pages = {106705},
  doi = {10.1016/j.ejps.2024.106705}
}
Kostenlos starten →