Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Dynamic multivariate patterns of brain structure-neuropsychiatric symptom associations in long COVID.

Brain communications·2026

Same author

Glycoengineered Recombinant Alpha1-Antitrypsin Results in Comparable In Vitro and In Vivo Activities to Human Plasma-Derived Protein.

Biotechnology and bioengineering·2026

Same author

Human Genome-Scale Models of Metabolism and Gene Expression Reveal Resource Constraints of Cancer Cell Lines.

bioRxiv : the preprint server for biology·2026

Same author

High stability double Stokes-Mueller polarimetry under oblique incidence.

Optics express·2026

Same author

Systematic Mapping of Protein Interactions Underlying IL-2 Secretion in Human T Cells.

Analytical chemistry·2026

Same author

Cross-population validation of the TyG-ABSI index as a novel predictor for chronic obstructive pulmonary disease: an integrated analysis using logistic regression and explainable machine learning.

BMC pulmonary medicine·2026

Search research articles

Related Experiment Video

Updated: Jun 29, 2025

A Lectin HPLC Method to Enrich Selectively-glycosylated Peptides from Complex Biological Samples

A Lectin HPLC Method to Enrich Selectively-glycosylated Peptides from Complex Biological Samples

Published on: October 1, 2009

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

Haining Li¹, Angelo G Peralta², Sanne Schoffelen³

¹Department of Bioengineering, University of California, San Diego, La Jolla, CA 92093, USA.

Biorxiv : the Preprint Server for Biology

|April 8, 2024

Summary

Researchers developed LeGenD, an AI and lectin-based method for predicting N-glycan structures and abundance. This approach overcomes limitations of traditional glycan analysis, offering a cost-effective alternative.

More Related Videos

Author Spotlight: Advancing Protein Glycosylation Research Using a Fully Automated System

Author Spotlight: Advancing Protein Glycosylation Research Using a Fully Automated System

Published on: June 28, 2024

Bioinformatics Resources for the Study of Glycan-Mediated Protein Interactions

Bioinformatics Resources for the Study of Glycan-Mediated Protein Interactions

Published on: January 20, 2022

Related Experiment Videos

Last Updated: Jun 29, 2025

A Lectin HPLC Method to Enrich Selectively-glycosylated Peptides from Complex Biological Samples

A Lectin HPLC Method to Enrich Selectively-glycosylated Peptides from Complex Biological Samples

Published on: October 1, 2009

Author Spotlight: Advancing Protein Glycosylation Research Using a Fully Automated System

Author Spotlight: Advancing Protein Glycosylation Research Using a Fully Automated System

Published on: June 28, 2024

Bioinformatics Resources for the Study of Glycan-Mediated Protein Interactions

Bioinformatics Resources for the Study of Glycan-Mediated Protein Interactions

Published on: January 20, 2022

Area of Science:

Biochemistry and Biotechnology
Glycobiology
Artificial Intelligence in Life Sciences

Background:

Glycosylation is crucial for biological functions, impacting biopharmaceutical development and diagnostics.
Conventional glycan analysis methods are limited by throughput and cost.
Lectins provide glycan epitope information but not complete structures.

Approach:

Developed LeGenD, a novel approach combining lectin-binding patterns with artificial intelligence (AI) for N-glycan structure prediction.
Trained the LeGenD model on 309 glycoprofiles from recombinant proteins produced in glycoengineered Chinese hamster ovary (CHO) cell lines.
Utilized SHapley Additive exPlanations (SHAP) for AI-driven identification of key lectins in glycoprofile prediction.

Key Points:

LeGenD accurately reconstructs experimentally-measured N-glycoprofiles of proteins like bovine Fetuin B and human IgG.
The method determines the relative abundance of N-glycans based on lectin-binding data.
Identifies critical lectins influencing N-glycan structure prediction through explainable AI.

Conclusions:

LeGenD offers a powerful and alternative method for N-glycan analysis, addressing current limitations in throughput and cost.
This AI-powered lectin-based approach enhances glycan structure determination for biopharmaceutical and diagnostic applications.
Provides deeper insights into glycosylation patterns critical for understanding biological processes.