InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization

2025-03-03

AI Summary

In multi-objective drug discovery, simultaneous optimization of conflicting molecular properties faces challenges including difficulty in balancing trade-offs and low efficiency in exploring the Pareto frontier. To address these, we propose a dual-path graph neural network (GNN) framework: a forward path employs a multi-task GNN to learn mappings between functional group combinations and molecular properties; a backward path integrates gradient-driven discrete Pareto search to enable efficient, constraint-aware molecular generation. Our key contributions are (i) the first dual-path cooperative architecture for multi-objective molecular design, and (ii) a novel gradient-guided algorithm for approximating the Pareto frontier in discrete molecular space. Evaluated on multiple multi-objective drug design benchmarks, our method achieves superior sample efficiency and generates higher-quality Pareto-optimal molecules, outperforming state-of-the-art approaches across comprehensive metrics.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization
• Machine Learning: Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Exploring chemical space to find novel molecules that simultaneously satisfy multiple properties is crucial in drug discovery. However, existing methods often struggle with trading off multiple properties due to the conflicting or correlated nature of chemical properties. To tackle this issue, we introduce InversionGNN framework, an effective yet sample-efficient dual-path graph neural network (GNN) for multi-objective drug discovery. In the direct prediction path of InversionGNN, we train the model for multi-property prediction to acquire knowledge of the optimal combination of functional groups. Then the learned chemical knowledge helps the inversion generation path to generate molecules with required properties. In order to decode the complex knowledge of multiple properties in the inversion path, we propose a gradient-based Pareto search method to balance conflicting properties and generate Pareto optimal molecules. Additionally, InversionGNN is able to search the full Pareto front approximately in discrete chemical space. Comprehensive experimental evaluations show that InversionGNN is both effective and sample-efficient in various discrete multi-objective settings including drug discovery.

Problem

• Optimizing molecules for multiple conflicting chemical properties
• Developing a dual-path GNN for multi-objective drug discovery
• Balancing and generating Pareto optimal molecules efficiently

Innovation

• Dual-path GNN for multi-property molecular optimization
• Gradient-based Pareto search for property balancing
• Approximate full Pareto front search in chemical space