Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
Abstract
Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuring the biophysical signals that underlie function. Here we introduce ProtDiS, a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded and task-relevant dimensions. Inspired by the information bottleneck principle, ProtDiS learns representations that balance informativeness and compression, yielding structural features that are more specific, independent, and information-efficient, and achieving consistent improvements across twelve downstream tasks, with the largest gains under structure-based splits. Protein- and residue-level analyses further show that ProtDiS differentiates proteins with similar folds but divergent functions and captures fine-grained biophysical signals critical. These findings suggest that knowledge-guided decomposition provides a general and interpretable approach for structuring latent spaces in protein structural modeling. The source code and implementation details are publicly available at https://github.com/AI-HPC-Research-Team/ProtDiS.
Cite
@article{arxiv.2605.23960,
title = {Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition},
author = {Mingqing Wang and Zhiwei Nie and Athanasios V. Vasilakos and Yonghong He and Zhixiang Ren},
journal= {arXiv preprint arXiv:2605.23960},
year = {2026}
}
Comments
28 pages, 17 figures, icml 2026 regular