# ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model

DevFeed: [ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model](<https://devfeed.tech/articles/protglycandock-towards-accurate-protein-glycan-docking-with-tailored-dataset-benchmark-and-model-93588.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.26009>)

Author: Minghao Xu, Jiaze Song, Jinyu Wang, Wentao Zhang

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [alphafold-3](<https://devfeed.tech/tags/alphafold-3.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [case-studies](<https://devfeed.tech/tags/case-studies.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [molecular-structure-prediction](<https://devfeed.tech/tags/molecular-structure-prediction.md>), [techniques](<https://devfeed.tech/tags/techniques.md>)

## AI overview

ProtGlycanDock introduces a benchmark for protein-glycan docking that tests generalization to new proteins and glycans, and compares ten physics-based, machine-learning, and molecular-structure-prediction models. The abstract reports AlphaFold 3 as the strongest existing method evaluated. The authors also propose two complementary fine-tuning techniques for a general-purpose structure-prediction model: adding glycan topological features to its inputs and refining binding poses with a glycan energy loss. Combined, these techniques reportedly achieve state-of-the-art performance on the benchmark. Stratified analyses and case studies examine model strengths and weaknesses; the supplied text does not provide quantitative results or further detail.

## Source excerpt

arXiv:2610.26009v1 Announce Type: new Abstract: Performing accurate protein-glycan docking is critical to understanding protein-glycan interactions which govern many biological processes. However, this important task is hampered by the lack of tailored datasets, benchmarks and models for protein-glycan docking. To fill this blank, we first curate a standard benchmark ProtGlycanDock for training and evaluating protein-glycan docking models under both protein and glycan generalization settings. On this benchmark, we evaluate ten models in three categories, physics-based docking methods, machine-learning-based docking models and molecular structure prediction models. To obtain more precise binding poses, we further propose two finetuning techniques to inject the knowledge of glycan conformations into a general-purpose molecular structure prediction model. These two techniques respectively augment model inputs with glycan topological features and refine glycan binding pose with a glycan energy loss. Benchmark results show the superiority of AlphaFold 3 among existing methods, and the two proposed finetuning techniques can be well combined to achieve a state-of-the-art model for protein-glycan docking. Also, we perform stratified benchmark analysis and case studies to better understand the strengths and weaknesses of current models, providing insights for future model improvements. We maintain datasets at https://huggingface.co/datasets/ProtGlycanDock/ProtGlycanDock and source codes at https://github.com/kasawa1234/ProtGlycanDock