What question did this study set out to answer?

To develop and evaluate Quantum Long Short-Term Memory (QLSTM) in enhancing the drug discovery process.

January 14, 2026EPJ Quantum Technology0 citationsOpen Access

Quantum long short-term memory for drug discovery

LZLiang ZhangQuantumCTek (China)YXYin XuTianjin University of Science and Technology MWMohan WuTianjin University of Science and Technology

Key Points

To develop and evaluate Quantum Long Short-Term Memory (QLSTM) in enhancing the drug discovery process.
Evaluation on five benchmark datasets: BBBP, BACE, SIDER, BCAP37, T-47D.
Performance measured against classical LSTM using ROC-AUC metrics.
Assessment of how predictive accuracy scales with increased qubit counts.
QLSTM outperformed classical LSTM, achieving ROC-AUC improvements between 3% and over 6%.
Exhibited faster convergence compared to classical LSTM under identical training conditions.
Showed strong robustness against quantum computer noise, surpassing classical LSTM performance in some scenarios.

Abstract

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.

Ask AI

Helpful

Bookmark

View Full Paper