Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs

2026-01-31

AI Summary

Existing graph neural networks struggle to efficiently capture multiscale features and long-range dependencies in protein structure modeling. To address this limitation, this work proposes a hierarchical graph modeling framework grounded in geometric secondary structure motifs. The approach constructs both fine-grained subgraphs of individual motifs and a coarse-grained inter-motif graph, employing a two-stage GNN architecture to separately learn local conformations and global topology while integrating spatial arrangement and relative orientation information. This design enables modular selection of GNN backbones, achieving substantial gains in both computational efficiency and predictive accuracy without compromising expressiveness. Extensive experiments across multiple benchmark tasks demonstrate superior performance and reduced computational overhead, confirming the method’s effectiveness and generalizability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Graph neural networks (GNNs) have emerged as powerful tools for learning protein structures by capturing spatial relationships at the residue level. However, existing GNN-based methods often face challenges in learning multiscale representations and modeling long-range dependencies efficiently. In this work, we propose an efficient multiscale graph-based learning framework tailored to proteins. Our proposed framework contains two crucial components: (1) It constructs a hierarchical graph representation comprising a collection of fine-grained subgraphs, each corresponding to a secondary structure motif (e.g., $\alpha$-helices, $\beta$-strands, loops), and a single coarse-grained graph that connects these motifs based on their spatial arrangement and relative orientation. (2) It employs two GNNs for feature learning: the first operates within individual secondary motifs to capture local interactions, and the second models higher-level structural relationships across motifs. Our modular framework allows a flexible choice of GNN in each stage. Theoretically, we show that our hierarchical framework preserves the desired maximal expressiveness, ensuring no loss of critical structural information. Empirically, we demonstrate that integrating baseline GNNs into our multiscale framework remarkably improves prediction accuracy and reduces computational cost across various benchmarks.

Problem

• multiscale representation
• long-range dependencies
• graph neural networks
• protein structure learning
• secondary structural motifs

Innovation

• multiscale graph learning
• geometric secondary structural motifs
• hierarchical graph representation
• protein structure modeling
• graph neural networks