Eric J Carpenter

The paper evaluates how glycan-binding proteins and immune cells recognize mirror-image glycans, finding widespread binding and donor-specific recognition of L-glycans.

The paper develops deep-learning models to predict glycan-protein binding strengths using hybrid datasets and tail-aware losses, finding that glycan interactions are harder than small-molecule interactions due to chiral feature limitations.

The paper introduces two methods to profile functional glycan-lectin interactions in tissues using single-cell and spatial multiomic approaches, revealing stimulus-specific glycan remodeling and spatial glycan programs in immune cells and follicular lymphoma.

This paper develops MCNet, a machine learning model that predicts protein-glycan binding strength using atom-level representations, enabling cross-chiral recognition and unifying diverse glycobiology datasets.