Deep generative chemistry models emerge as powerful tools to expedite drug discovery. How- ever, the immense size and complexity of the structural space of all possible drug-like molecules pose significant obstacles, which could be overcome with hybrid architectures combining quantum computers with deep classical networks. As the first step toward this goal, we built a compact discrete variational autoencoder (DVAE) with a Restricted Boltzmann Machine (RBM) of reduced size in its latent layer. The size of the proposed model was small enough to fit on a state-of-the-art D-Wave quantum annealer and allowed training on a subset of the ChEMBL dataset of biologically active compounds. Finally, we generated 2331 novel chemical structures with medicinal chemistry and synthetic accessibility properties in the ranges typical for molecules from ChEMBL. The pre- sented results demonstrate the feasibility of using already existing or soon-to-be-available quantum computing devices as testbeds for future drug discovery applications.

Molecule datasets for paper "Hybrid quantum-classical machine learning for generative chemistry and drug design", A.I. Gircha, A.S. Boev, K. Avchaciov, P. O. Fedichev, and A.K. Fedorov. 1. Training dataset: train_set.txt 2. Molecules generated using the model with Gibbs sampling after 300 epochs of training: gibbs300.txt 3. Molecules generated using the model with Gibbs sampling after 75 epochs of training: gibbs75.txt gibbs75-1.txt 4. Molecules generated using the model with D-Wave sampling after 75 epochs of training: dw75-1.txt dw75-2.txt dw75-3.txt dw75-4.txt dw75-5.txt dw75-6.txt

{"references": ["arXiv:2108.11644"]}