A Useful Guide to Lectin Binding: Machine-Learning Directed Annotation of 57 Unique Lectin Specificities

Abstract

Glycans are critical to every facet of biology and medicine, from viral infections to embryogenesis. Tools to study glycans are rapidly evolving, however the majority of our knowledge is deeply dependent on binding by glycan binding proteins (e.g., lectins). The specificities of lectins, which are often naturally isolated proteins, have not been welldefined, making it difficult to leverage their full potential for glycan analysis. Herein, we use glycan microarray analysis of 116 commercially available lectins, including different preparations of the same lectin, to extract the specific glycan features required for lectin binding. Data was obtained using the Consortium for Functional Glycomics microarray (CFG v5.0) containing 611 glycans. We use a combination of machine learning algorithms to define lectin specificity, mapping inputs (glycan sequences) to outputs (lectin-glycan binding) for a large-scale evaluation of lectin-glycan binding behaviours. Our motif analysis was performed by integrating 68 manually defined glycan features with systematic probing of computational rules for significant binding motifs using mono-and disaccharides-and linkages. Using a combination of machine learning and manual annotation of the data, we created a detailed interpretation of glycan-binding specificity for 57 unique lectins, categorized by their major binding motifs: mannose, complex-type N-glycan, O-glycan, fucose, sialic acid and sulfate, GlcNAc and chitin, Gal and LacNAc, and GalNAc. Our work provides fresh insights into the complex binding features of commercially available lectins in current use, providing a critical guide to these important reagents.

GlyNet: a multi-task neural network for predicting protein–glycan interactions

“…The glycans predicted to have the strongest binding match both the experimentally observed results. Further we see these glycans possess binding motifs previously reported by Mahal and coworkers 54 suggesting that GlyNet recognizes the same features that have been previously identified as binding motifs for these proteins. The result is that GlyNet makes it possible to compare data from arrays that have mismatched composition by extrapolating the binding for glycans that are not included in all of the arrays.…”

CarboGrove: a resource of glycan-binding specificities through analyzed glycan-array datasets from all platforms

“…2019 ) and other databases. A resource that appeared after submission of this work is a machine learning annotation of lectin specificities, which could provide additional, complementary information ( Bojar et al. 2022 ).…”

Glycomic Analysis Reveals a Conserved Response to Bacterial Sepsis Induced by Different Bacterial Pathogens

“…Both AIA and MPA recognize these core 1/3 O -glycans with many terminal extensions, implying that expression of this epitope is likely due to an increase in levels of this O- glycan rather than trimming of existing unrecognized epitopes. 31 This effect on core 1/3 O -glycans is seen in both Gram-positive and Gram-negative infections. The increase of core 1/3 O -glycans can be observed in early sepsis in three out of the four organisms studied.…”