Quantum Long Short-Term Memory for Drug Discovery

TL;DR

This paper introduces Quantum Long Short-Term Memory (QLSTM), a quantum machine learning model that outperforms classical LSTM in drug discovery tasks, showing improved accuracy, convergence, and noise robustness on benchmark datasets.

Contribution

The paper presents the novel QLSTM architecture and demonstrates its superior performance and robustness over classical LSTM in drug discovery applications.

Findings

QLSTM achieves 3-6% ROC-AUC improvements over classical LSTM.

QLSTM's accuracy improves with more qubits.

QLSTM shows robustness against quantum noise.

Abstract

Quantum computing combined with machine learning (ML) is a highly promising research area, with numerous studies demonstrating that quantum machine learning (QML) is expected to solve scientific problems more effectively than classical ML. In this work, we present Quantum Long Short-Term Memory (QLSTM), a QML architecture, and demonstrate its effectiveness in drug discovery. We evaluate QLSTM on five benchmark datasets (BBBP, BACE, SIDER, BCAP37, T-47D), and observe consistent performance gains over classical LSTM, with ROC-AUC improvements ranging from 3% to over 6%. Furthermore, QLSTM exhibits improved predictive accuracy as the number of qubits increases, and faster convergence than classical LSTM under the same training conditions. Notably, QLSTM maintains strong robustness against quantum computer noise, outperforming noise-free classical LSTM in certain settings. These findings highlight the potential of QLSTM as a scalable and noise-resilient model for scientific applications, particularly as quantum hardware continues to advance in qubit capacity and fidelity.