LeGenD: determining N-glycoprofiles using an explainable AI-leveraged model with lectin profiling.

Autor:	Li H; Department of Bioengineering, University of California, San Diego, La Jolla, CA 92093, USA., Peralta AG; Department of Pediatrics, University of California, San Diego, La Jolla, CA 92093, USA., Schoffelen S; National Biologics Facility Department of Biotechnology and Biomedicine, Technical University of Denmark, Building 220, Kemitorvet, 2800 Kgs. Lyngby Denmark., Hansen AH; National Biologics Facility Department of Biotechnology and Biomedicine, Technical University of Denmark, Building 220, Kemitorvet, 2800 Kgs. Lyngby Denmark., Arnsdorf J; National Biologics Facility Department of Biotechnology and Biomedicine, Technical University of Denmark, Building 220, Kemitorvet, 2800 Kgs. Lyngby Denmark., Schinn SM; Department of Bioengineering, University of California, San Diego, La Jolla, CA 92093, USA., Skidmore J; Department of Bioengineering, University of California, San Diego, La Jolla, CA 92093, USA.; Department of Microbiology and Molecular Biology, Brigham Young University, Provo, UT 84602, USA., Choudhury B; Glycobiology Research and Training Center, University of California, San Diego, La Jolla, CA 92093, USA., Paulchakrabarti M; Glycobiology Research and Training Center, University of California, San Diego, La Jolla, CA 92093, USA., Voldborg BG; National Biologics Facility Department of Biotechnology and Biomedicine, Technical University of Denmark, Building 220, Kemitorvet, 2800 Kgs. Lyngby Denmark., Chiang AWT; Department of Pediatrics, University of California, San Diego, La Jolla, CA 92093, USA., Lewis NE; Department of Bioengineering, University of California, San Diego, La Jolla, CA 92093, USA.; Department of Pediatrics, University of California, San Diego, La Jolla, CA 92093, USA.
Jazyk:	angličtina
Zdroj:	BioRxiv : the preprint server for biology [bioRxiv] 2024 Mar 30. Date of Electronic Publication: 2024 Mar 30.
DOI:	10.1101/2024.03.27.587044
Abstrakt:	Glycosylation affects many vital functions of organisms. Therefore, its surveillance is critical from basic science to biotechnology, including biopharmaceutical development and clinical diagnostics. However, conventional glycan structure analysis faces challenges with throughput and cost. Lectins offer an alternative approach for analyzing glycans, but they only provide glycan epitopes and not full glycan structure information. To overcome these limitations, we developed LeGenD, a lectin and AI-based approach to predict N -glycan structures and determine their relative abundance in purified proteins based on lectin-binding patterns. We trained the LeGenD model using 309 glycoprofiles from 10 recombinant proteins, produced in 30 glycoengineered CHO cell lines. Our approach accurately reconstructed experimentally-measured N -glycoprofiles of bovine Fetuin B and IgG from human sera. Explanatory AI analysis with SHapley Additive exPlanations (SHAP) helped identify the critical lectins for glycoprofile predictions. Our LeGenD approach thus presents an alternative approach for N -glycan analysis. Competing Interests: Declaration of Interests AWTC and NEL are inventors on a patent associated with this study.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu