| The design and development of novel molecules and compounds through automated computer-aided techniques is a challenging task that can be addressed with quantum computing (QC) owing to its notable advances in domains like optimization and machine learning. Here, we present the results for molecular property prediction and generation tasks using QC-assisted learning and optimization techniques which can be successfully implemented with near-term QC devices. The proposed probabilistic energy-based deep learning model trained in a generative manner facilitated by QC yields robust latent representations of molecules, while the proposed data-driven QC-based optimization framework performs guided navigation of the target chemical space by exploiting the structure-property relationships captured by the energy-based model. We demonstrate the viability of the proposed molecular design approach by generating 4,457 molecular candidates that satisfy specific property target requirements. The proposed QC-based methods exhibit an improvement in predictive performance over conventional property estimation methods while efficiently generating novel molecules that accurately fulfill target conditions over other molecular design frameworks and exemplify the potential of QC for automated molecular design, thus accentuating its utility. |
