Identifying glycan motifs using a novel subtree mining approach

Abstract

Background Glycans are complex sugar chains, crucial to many biological processes. By participating in binding interactions with proteins, glycans often play key roles in host–pathogen interactions. The specificities of glycan-binding proteins, such as lectins and antibodies, are governed by motifs within larger glycan structures, and improved characterisations of these determinants would aid research into human diseases. Identification of motifs has previously been approached as a frequent subtree mining problem, and we extend these approaches with a glycan notation that allows recognition of terminal motifs. Results In this work, we customised a frequent subtree mining approach by altering the glycan notation to include information on terminal connections. This allows specific identification of terminal residues as potential motifs, better capturing the complexity of glycan-binding interactions. We achieved this by including additional nodes in a graph representation of the glycan structure to indicate the presence or absence of a linkage at particular backbone carbon positions. Combining this frequent subtree mining approach with a state-of-the-art feature selection algorithm termed minimum-redundancy, maximum-relevance (mRMR), we have generated a classification pipeline that is trained on data from a glycan microarray. When applied to a set of commonly used lectins, the identified motifs were consistent with known binding determinants. Furthermore, logistic regression classifiers trained using these motifs performed well across most lectins examined, with a median AUC value of 0.89. Conclusions We present here a new subtree mining approach for the classification of glycan binding and identification of potential binding motifs. The Carbohydrate Classification Accounting for Restricted Linkages (CCARL) method will assist in the interpretation of glycan microarray experiments and will aid in the discovery of novel binding motifs for further experimental characterisation.

Using Graph Convolutional Neural Networks to Learn a Representation for Glycans

“…We then identified glycan motifs that are important for the binding of hemagglutinin. Most approaches apply some form of subtree frequency mining to the glycan array data (Coff et al, 2020), identifying preferentially bound glycan fragments (Cholleti et al, 2012). However, we wanted to capitalize on the predictive nature of our trained model and used all our 19,775 available glycan sequences, which are to the most part not covered by existing glycan arrays, as inputs to the trained model for each host species.…”

Big-Data Glycomics: Tools to Connect Glycan Biosynthesis to Extracellular Communication

“…Extracting Important Glycan Substructures Glycan substructures can be analyzed to highlight functional elements of a glycoprofile, epitopes (see Glossary). Phenotype-associated motifs can be extracted from lectin or lectin arrays [82][83][84][85][86]149,150], and glycomes [79,[82][83][84][85][86]93,140,149]. Selected substructures can be interpreted for meaning and potential impact using databases of glycan interactions and subsequent experiments.…”

Tools for generating and analyzing glycan microarray data

“…Address: https://github.com/andrewguy/CCARL. Description: CCARL is a very new method of identifying motifs from glycan microarray experiments [ 50 ]. Previous subtree mining approaches would not account for terminal motifs.…”