Quantifying the nativeness of antibody sequences using long short-term memory networks
Protein Engineering, Design and Selection · 31.12.2019 · 32 (7) · 347-354
DOI: 10.1093/protein/gzz031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Protein Engineering, Design and Selection, online erschienen am 28.08.2019. Verfasst von Andrew M Wollacott und 6 weiteren Autor:innen. Beteiligte Einrichtung: Visterra Inc., Waltham, MA 02451, USA. Hauptthemen laut MEDLINE: Computational Biology. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NCATS NIH HHS, NIAMS NIH HHS, NIA NIH HHS.
Abstract (Originalsprache)
Antibodies often undergo substantial engineering en route to the generation of a therapeutic candidate with good developability properties. Characterization of antibody libraries has shown that retaining native-like sequence improves the overall quality of the library. Motivated by recent advances in deep learning, we developed a bi-directional long short-term memory (LSTM) network model to make use of the large amount of available antibody sequence information, and use this model to quantify the nativeness of antibody sequences. The model scores sequences for their similarity to naturally occurring antibodies, which can be used as a consideration during design and engineering of libraries. We demonstrate the performance of this approach by training a model on human antibody sequences and show that our method outperforms other approaches at distinguishing human antibodies from those of other species. We show the applicability of this method for the evaluation of synthesized antibody libraries and humanization of mouse antibodies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Visterra Inc., Waltham, MA 02451, USA.
- Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA 02118, USA.
- Hariri Institute of Computing and Computational Science & Engineering, Boston University, Boston, MA 02115, USA.
- Whitaker Cardiovascular Institute, Boston University School of Medicine, Boston, MA 02118, USA.
- Boston University Alzheimer's Disease Center, Boston, MA 02118, USA.
Förderung
- NCATS NIH HHS
- NIAMS NIH HHS
- NIA NIH HHS
- National Institutes of Health
- American Heart Association
Zitieren
APA
Wollacott, A. M., Xue, C., Qin, Q., Hua, J., Bohnuud, T., Viswanathan, K., & Kolachalama, V. B. (2019). Quantifying the nativeness of antibody sequences using long short-term memory networks. Protein Engineering, Design and Selection, 32(7), 347-354. https://doi.org/10.1093/protein/gzz031
Vancouver
Wollacott AM, Xue C, Qin Q, Hua J, Bohnuud T, Viswanathan K, et al. Quantifying the nativeness of antibody sequences using long short-term memory networks. Protein Engineering, Design and Selection. 2019;32(7):347-354. doi:10.1093/protein/gzz031
BibTeX
@article{Wollacott2019,
author = {Wollacott, Andrew M and Xue, Chonghua and Qin, Qiuyuan and Hua, June and Bohnuud, Tanggis and Viswanathan, Karthik and Kolachalama, Vijaya B},
title = {Quantifying the nativeness of antibody sequences using long short-term memory networks},
journal = {Protein Engineering, Design and Selection},
year = {2019},
volume = {32},
number = {7},
pages = {347--354},
doi = {10.1093/protein/gzz031}
}
EUVIMED