We thank all the reviewers for their careful reviews. None of these follow trivially from Xu et al. In molecule generation, validity is encouraged using the reward-based approach of MolGANs, not the SL. We will clarify this in the discussion. Thank you, we were not aware of this link.

Hybrid quantum-classical machine learning offers a path to leverage noisy intermediate-scale quantum (NISQ) devices for drug discovery, but optimal model architectures remain unclear. We systematically optimize the quantum-classical bridge architecture of generative adversarial networks (GANs) for molecule discovery using multi-objective Bayesian optimization. Our optimized model (BO-QGAN) significantly improves performance, achieving a 2.27-fold higher Drug Candidate Score (DCS) than prior quantum-hybrid benchmarks and 2.21-fold higher than the classical baseline, while reducing parameter count by more than 60%. Key findings favor layering multiple (3-4) shallow (4-8 qubit) quantum circuits sequentially, while classical architecture shows less sensitivity above a minimum capacity. This work provides the first empirically-grounded architectural guidelines for hybrid models, enabling more effective integration of current quantum computers into pharmaceutical research pipelines.

The discovery of new molecules and materials is crucial for addressing challenges in chemistry, such as treating diseases and tackling climate change [Liu et al., 2023, Sanchez and Aspuru-Guzik, 2018]. Traditional methods rely on human expertise and are time-consuming and costly, limiting the exploration of the vast chemical space [Polishchuk et al., 2013]. Generative models offer a promising solution using deep learning to design molecules based on desired properties, rapidly identifying diverse and optimized molecules for specific applications. These models vary in their approaches and have seen rapid development, with benchmarks now in place to evaluate their performance in terms of distribution learning and chemical diversity. Although these models are publicly available, practitioners require extensive Python and machine learning knowledge to reap their benefits. Thus, we introduce open-source molecular generative model infrastructure into DeepChem Ramsundar et al. [2019], a widely used open-source library for molecular machine learning.

The contemporary drug design process demands considerable time and resources to develop each new compound entering the market. Generating small molecules is a pivotal aspect of drug discovery, essential for developing innovative pharmaceuticals. Uniqueness, validity, diversity, druglikeliness, synthesizability, and solubility molecular pharmacokinetic properties, however, are yet to be maximized. This work introduces several new generative adversarial network models based on engineering integration of parametrized quantum circuits into known molecular generative adversarial networks. The introduced machine learning models incorporate a new multi-parameter reward function grounded in reinforcement learning principles. Through extensive experimentation on benchmark drug design datasets, QM9 and PC9, the introduced models are shown to outperform scores achieved previously. Most prominently, the new scores indicate an increase of up to 30% in the druglikeness quantitative estimation. The new hybrid quantum machine learning algorithms, as well as the achieved scores of pharmacokinetic properties, contribute to the development of fast and accurate drug discovery processes.

Fuels with high-knock resistance enable modern spark-ignition engines to achieve high efficiency and thus low CO2 emissions. Identification of molecules with desired autoignition properties indicated by a high research octane number and a high octane sensitivity is therefore of great practical relevance and can be supported by computer-aided molecular design (CAMD). Recent developments in the field of graph machine learning (graph-ML) provide novel, promising tools for CAMD. We propose a modular graph-ML CAMD framework that integrates generative graph-ML models with graph neural networks and optimization, enabling the design of molecules with desired ignition properties in a continuous molecular space. In particular, we explore the potential of Bayesian optimization and genetic algorithms in combination with generative graph-ML models. The graph-ML CAMD framework successfully identifies well-established high-octane components. It also suggests new candidates, one of which we experimentally investigate and use to illustrate the need for further auto-ignition training data.

Deep generative models for graph-structured data offer a new angle on the problem of chemical synthesis: by optimizing differentiable models that directly generate molecular graphs, it is possible to side-step expensive search procedures in the discrete and vast space of chemical structures. We introduce MolGAN, an implicit, likelihood-free generative model for small molecular graphs that circumvents the need for expensive graph matching procedures or node ordering heuristics of previous likelihood-based methods. Our method adapts generative adversarial networks (GANs) to operate directly on graph-structured data. We combine our approach with a reinforcement learning objective to encourage the generation of molecules with specific desired chemical properties. In experiments on the QM9 chemical database, we demonstrate that our model is capable of generating close to 100% valid compounds. MolGAN compares favorably both to recent proposals that use string-based (SMILES) representations of molecules and to a likelihood-based method that directly generates graphs, albeit being susceptible to mode collapse. Code at https://github.com/nicola-decao/MolGAN