GlyTrait: A Versatile Bioinformatics Tool for Glycomics Analysis

We
developed GlyTrait, a Python-based framework designed to enhance
Glycomics analysis through the innovative calculation and interpretation
of derived traits from N-glycome data. Glycomics
research often grapples with the interpretability and biological relevance
of Glycomics data. GlyTrait automates the derivation of biologically
significant traits, shifting focus from mere glycan abundances in
compositional or structural Glycomics studies to functional glycan
properties such as branching and fucosylation. Furthermore, with the
well-designed formula grammar, custom-derived traits can be materialized
without any knowledge of coding. Finally, subsequent statistical and
interpretable machine learning analyses provide robust insights into
the glycosylation patterns associated with disease states. GlyTrait’s
efficacy is demonstrated through the reanalysis of published glycoengineered
CHO cell lines and visceral leishmaniasis patient data, alongside
a newly conducted pilot study for hepatocellular carcinoma (HCC) N-glycan biomarker discovery. We are confident in GlyTrait’s
potential to become an indispensable tool for the Glycomics community.