QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning

2025-09-05

AI Summary

Drug molecule design faces the challenge of efficiently generating novel candidates within vast chemical space while simultaneously satisfying drug-likeness, lipophilicity (LogP), and synthetic accessibility (SA). This paper proposes a quantum-classical hybrid generative framework: a quantum Born machine models the molecular latent-space prior, coupled with a generative adversarial network for structural generation, and augmented by multi-agent reinforcement learning to jointly optimize QED, LogP, and SA. Its key innovation lies in the first integration of quantum state representations into molecular generation, enabling dynamic trade-offs and alignment among competing objectives via decentralized agent policies. Experiments demonstrate significant improvements over baseline methods: +12.3% in QED score, 37.6% higher compliance rate for LogP within ±0.5, and 91.2% of generated molecules achieving SA < 4. These results validate the effectiveness of quantum-enhanced representation learning and multi-objective collaborative optimization in de novo molecular design.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Multiagent Systems: Mechanism Design

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Navigating the vast chemical space of molecular structures to design novel drug molecules with desired target properties remains a central challenge in drug discovery. Recent advances in generative models offer promising solutions. This work presents a novel quantum circuit Born machine (QCBM)-enabled Generative Adversarial Network (GAN), called QCA-MolGAN, for generating drug-like molecules. The QCBM serves as a learnable prior distribution, which is associatively trained to define a latent space aligning with high-level features captured by the GANs discriminator. Additionally, we integrate a novel multi-agent reinforcement learning network to guide molecular generation with desired targeted properties, optimising key metrics such as quantitative estimate of drug-likeness (QED), octanol-water partition coefficient (LogP) and synthetic accessibility (SA) scores in conjunction with one another. Experimental results demonstrate that our approach enhances the property alignment of generated molecules with the multi-agent reinforcement learning agents effectively balancing chemical properties.

Problem

• Designing novel drug molecules with desired target properties
• Navigating vast chemical space for molecular structure generation
• Optimizing drug-likeness, partition coefficient and synthetic accessibility

Innovation

• Quantum circuit Born machine as learnable prior
• Multi-agent reinforcement learning for property optimization
• Associative training aligning latent space with features