A Geometric Graph-Based Deep Learning Model for Drug-Target Affinity Prediction

2025-09-15

AI Summary

Accurately predicting protein–ligand binding affinity remains challenging in structure-based drug design. To address this, we propose DeepGGL—a novel deep learning model that represents protein–ligand complexes as geometric graphs via a multi-scale weighted colored bipartite graph construction. DeepGGL integrates geometric graph convolutional layers, residual connections, and self-attention mechanisms, while explicitly modeling multi-scale subgraph structures to enhance atomic-level interaction representation and improve identification of critical binding motifs. The architecture ensures strong interpretability through attention-guided feature attribution. Evaluated on the CASF-2013 and CASF-2016 benchmarks, DeepGGL achieves state-of-the-art performance. Furthermore, it demonstrates superior robustness and generalization on the CSAR-NRC-HiQ and PDBbind v2019 datasets, confirming its effectiveness across diverse binding scenarios and experimental conditions.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Knowledge Representation and Reasoning: Description Logics

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
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

In structure-based drug design, accurately estimating the binding affinity between a candidate ligand and its protein receptor is a central challenge. Recent advances in artificial intelligence, particularly deep learning, have demonstrated superior performance over traditional empirical and physics-based methods for this task, enabled by the growing availability of structural and experimental affinity data. In this work, we introduce DeepGGL, a deep convolutional neural network that integrates residual connections and an attention mechanism within a geometric graph learning framework. By leveraging multiscale weighted colored bipartite subgraphs, DeepGGL effectively captures fine-grained atom-level interactions in protein-ligand complexes across multiple scales. We benchmarked DeepGGL against established models on CASF-2013 and CASF-2016, where it achieved state-of-the-art performance with significant improvements across diverse evaluation metrics. To further assess robustness and generalization, we tested the model on the CSAR-NRC-HiQ dataset and the PDBbind v2019 holdout set. DeepGGL consistently maintained high predictive accuracy, highlighting its adaptability and reliability for binding affinity prediction in structure-based drug discovery.

Problem

• Predicting drug-target binding affinity accurately
• Capturing atom-level interactions in protein-ligand complexes
• Improving computational methods for structure-based drug design

Innovation

• Geometric graph-based deep learning framework
• Multiscale weighted colored bipartite subgraphs
• Residual connections with attention mechanism