Latent Style-based Quantum Wasserstein GAN for Drug Design

TL;DR

This paper introduces a novel quantum GAN architecture with style-based encoding for drug design, aiming to improve generative modeling by leveraging quantum computing to address training challenges in classical GANs.

Contribution

It presents a new style-based quantum GAN architecture with noise encoding and gradient penalty, validated on quantum simulators and real hardware for drug molecule generation.

Findings

Successfully implemented on up to 15 qubits in simulation

Demonstrated feasibility on a 156-qubit IBM quantum computer

Benchmarked against classical models with promising results

Abstract

The development of new drugs is a tedious, time-consuming, and expensive process, for which the average costs are estimated to be up to around $2.5 billion. The first step in this long process is the design of the new drug, for which de novo drug design, assisted by artificial intelligence, has blossomed in recent years and revolutionized the field. In particular, generative artificial intelligence has delivered promising results in drug discovery and development, reducing costs and the time to solution. However, classical generative models, such as generative adversarial networks (GANs), are difficult to train due to barren plateaus and prone to mode collapse. Quantum computing may be an avenue to overcome these issues and provide models with fewer parameters, thereby enhancing the generalizability of GANs. We propose a new style-based quantum GAN (QGAN) architecture for drug design that implements noise encoding at every rotational gate of the circuit and a gradient penalty in the loss function to mitigate mode collapse. Our pipeline employs a variational autoencoder to represent the molecular structure in a latent space, which is then used as input to our QGAN. Our baseline model runs on up to 15 qubits to validate our architecture on quantum simulators, and a 156-qubit IBM Heron quantum computer in the five-qubit setup is used for inference to investigate the effects of using real quantum hardware on the analysis. We benchmark our results against classical models as provided by the MOSES benchmark suite.