Graph Neural Networks in Modern AI-aided Drug Discovery

2025-06-07

AI Summary

This survey systematically examines the current applications and practical bottlenecks of Graph Neural Networks (GNNs) in AI-driven drug discovery (AIDD), covering core tasks including molecular property prediction, virtual screening, generative molecular design, biomedical knowledge graph construction, and retrosynthetic pathway planning. To address key limitations—namely insufficient interpretability, inadequate uncertainty modeling, weak geometric awareness, poor scalability, and limited generalization—we propose a novel paradigm integrating geometric GNNs, interpretability-enhancing modules, uncertainty quantification mechanisms, lightweight scalable graph architectures, and a unified graph generation framework, augmented by self-supervised learning, multi-task learning, meta-learning, and large-scale pretraining. The study identifies critical deployment barriers hindering GNN adoption in real-world drug development pipelines and establishes a comprehensive methodological landscape. It thereby provides both theoretical foundations and actionable technical pathways toward end-to-end AI-enabled drug discovery.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Graph neural networks (GNNs), as topology/structure-aware models within deep learning, have emerged as powerful tools for AI-aided drug discovery (AIDD). By directly operating on molecular graphs, GNNs offer an intuitive and expressive framework for learning the complex topological and geometric features of drug-like molecules, cementing their role in modern molecular modeling. This review provides a comprehensive overview of the methodological foundations and representative applications of GNNs in drug discovery, spanning tasks such as molecular property prediction, virtual screening, molecular generation, biomedical knowledge graph construction, and synthesis planning. Particular attention is given to recent methodological advances, including geometric GNNs, interpretable models, uncertainty quantification, scalable graph architectures, and graph generative frameworks. We also discuss how these models integrate with modern deep learning approaches, such as self-supervised learning, multi-task learning, meta-learning and pre-training. Throughout this review, we highlight the practical challenges and methodological bottlenecks encountered when applying GNNs to real-world drug discovery pipelines, and conclude with a discussion on future directions.

Problem

• GNNs model molecular graphs for drug discovery tasks
• Address challenges in molecular property prediction and generation
• Integrate GNNs with modern deep learning techniques

Innovation

• GNNs model molecular graphs for drug discovery
• Geometric GNNs enhance molecular feature learning
• Integrate self-supervised learning with GNNs