analiza aiqbench
The paper proposes a hybrid quantum Wasserstein GAN for molecule generation, paired with a variational autoencoder, and reports comparable or better drug-relevant metrics than a classical latent GAN on the MOSES benchmark while using about 110 generator parameters versus roughly 700,000. Most validation runs on noiseless simulators, with only a 5-qubit inference demonstration on IBM Heron hardware, so the practical case for quantum advantage remains unproven. Readers should weigh the parameter-efficiency result against those simulation-heavy conditions and the limited hardware evidence.
Latent Style-based Quantum Wasserstein GAN for Drug Design
arXiv:2603.22399v2 Announce Type: replace-cross Abstract: The development of new drugs is a time-consuming and expensive process, with average costs estimated to be up to around $2.5 billion. The first step in this process is the design of the new drug, for which de novo drug design, assisted by artificial intelligence, has blossomed in recent years and has revolutionized the field. In particular, generative artificial intelligence has delivered promising results in drug discovery and development, reducing costs and time to solution. However, classical generative models, such as generative adversarial networks (GANs), can be difficult to train and are prone to mode collapse. Quantum computing may be an avenue to overcome some of these issues, providing compact models with far fewer trainable parameters, thereby enhancing the generalizability of GANs. We propose a new latent style-based quantum Wasserstein GAN (QGAN) for drug design, combining a variational autoencoder that maps molecular structures into a latent space with a hybrid quantum GAN. Our pipeline is benchmarked against classical models of the industry-relevant MOSES suite. Style-based noise reuploading at every rotational gate and a Wasserstein gradient penalty are used to improve trainability and to mitigate mode collapse. Training and large-scale sampling with circuits of up to 15 qubits are performed on noiseless quantum simulators to validate our architecture. We present an inference-only demonstration on an IBM Heron quantum computer using 5 qubits, sampling 2,500 new molecules, to investigate quantum noise effects. Our default QGAN, using 110 trainable generator parameters, reaches statistically comparable overall performance and statistically significant gains on selected drug-relevant metrics relative to both the MOSES classical latent GAN baseline, which contains about 700,000 trainable parameters for the generator, and a classical latent GAN with matched generator capacity.
Abstract:The development of new drugs is a time-consuming and expensive process, with average costs estimated to be up to around $2.5 billion. The first step in this process is the design of the new drug, for which de novo drug design, assisted by artificial intelligence, has blossomed in recent years and has revolutionized the field. In particular, generative artificial intelligence has delivered promising results in drug discovery and development, reducing costs and time to solution. However, classical generative models, such as generative adversarial networks (GANs), can be difficult to train and are prone to mode collapse. Quantum computing may be an avenue to overcome some of these issues, providing compact models with far fewer trainable parameters, thereby enhancing the generalizability of GANs. We propose a new latent style-based quantum Wasserstein GAN (QGAN) for drug design, combining a variational autoencoder that maps molecular structures into a latent space with a hybrid quantum GAN. Our pipeline is benchmarked against classical models of the industry-relevant MOSES suite. Style-based noise reuploading at every rotational gate and a Wasserstein gradient penalty are used to improve trainability and to mitigate mode collapse. Training and large-scale sampling with circuits of up to 15 qubits are performed on noiseless quantum simulators to validate our architecture. We present an inference-only demonstration on an IBM Heron quantum computer using 5 qubits, sampling 2,500 new molecules, to investigate quantum noise effects. Our default QGAN, using 110 trainable generator parameters, reaches statistically comparable overall performance and statistically significant gains on selected drug-relevant metrics relative to both the MOSES classical latent GAN baseline, which contains about 700,000 trainable parameters for the generator, and a classical latent GAN with matched generator capacity.
Main part: 26 pages, 11 figures, 6 tables. Supplementary material: 24 pages, 20 figures, 21 tables. v2: revision containing matched-capacity analysis of the classical GAN and extensive details on the hardware inference run, plus bootstrap error analysis of the hardware results. Matches published version
Quantum Physics (quant-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Biomolecules (q-bio.BM)
arXiv:2603.22399 [quant-ph]
(or arXiv:2603.22399v2 [quant-ph] for this version)
J. Chem. Inf. Model. (2026) 66 (20): 13136-13154
https://doi.org/10.1021/acs.jcim.6c01249 DOI(s) linking to related resources
Text integral sub licența deschisă a publicației · 355 cuvinte