Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training
Keywords: Glycan Machine Learning, Heterogeneous Graph Modeling, Self-Supervised Pre-training
TL;DR: This work proposes an all-atom-wise glycan encoder GlycanAA and a pre-trained version of it PreGlycanAA.
Abstract: Understanding the various properties of glycans with machine learning has shown some preliminary promise. However, previous methods mainly focused on modeling the backbone structure of glycans as graphs of monosaccharides (i.e., sugar units), while they neglected the atomic structures underlying each monosaccharide, which are actually important indicators of glycan properties. In this work, we fill this blank by introducing the GlycanAA model for All-Atom-wise Glycan modeling. GlycanAA models a glycan as a heterogeneous graph with monosaccharide nodes representing its global backbone structure and atom nodes representing its local atomic-level structures. Based on such a graph, GlycanAA performs hierarchical message passing to capture from local atomic-level interactions to global monosaccharide-level interactions hierarchically. To further enhance the model capability, we pre-train GlycanAA on a high-quality unlabeled glycan dataset in a self-supervised way, deriving the PreGlycanAA model. Specifically, we design a multi-scale mask prediction algorithm to endow the model with knowledge about different levels of dependencies in a glycan. Extensive benchmark results show the superiority of GlycanAA over existing glycan encoders and verify the further improvements achieved by PreGlycanAA.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1249
Loading