Scalable Variational Quantum Circuits for Autoencoder-based Drug Discovery

TL;DR

This paper introduces scalable quantum autoencoders for drug molecule design, demonstrating potential advantages of quantum computing in generating and reconstructing molecules with improved properties in low to medium dimensions.

Contribution

The paper proposes a scalable quantum generative autoencoder architecture with novel strategies for high-dimensional molecule learning, outperforming classical methods in certain scenarios.

Findings

Quantum autoencoders perform well on low-dimensional molecules.

High-dimensional molecules generated show better drug properties.

Quantum advantages observed in normalized low-dimension molecule tasks.

Abstract

The de novo design of drug molecules is recognized as a time-consuming and costly process, and computational approaches have been applied in each stage of the drug discovery pipeline. Variational autoencoder is one of the computer-aided design methods which explores the chemical space based on existing molecular dataset. Quantum machine learning has emerged as an atypical learning method that may speed up some classical learning tasks because of its strong expressive power. However, near-term quantum computers suffer from limited number of qubits which hinders the representation learning in high dimensional spaces. We present a scalable quantum generative autoencoder (SQ-VAE) for simultaneously reconstructing and sampling drug molecules, and a corresponding vanilla variant (SQ-AE) for better reconstruction. The architectural strategies in hybrid quantum classical networks such as, adjustable quantum layer depth, heterogeneous learning rates, and patched quantum circuits are proposed to learn high dimensional dataset such as, ligand-targeted drugs. Extensive experimental results are reported for different dimensions including 8x8 and 32x32 after choosing suitable architectural strategies. The performance of quantum generative autoencoder is compared with the corresponding classical counterpart throughout all experiments. The results show that quantum computing advantages can be achieved for normalized low-dimension molecules, and that high-dimension molecules generated from quantum generative autoencoders have better drug properties within the same learning period.