Actively Searching: Inverse Design of Novel Molecules with Simultaneously Optimized Properties

Abstract

Combining quantum chemistry characterizations with generative machine learning models has the potential to accelerate molecular discovery. In this paradigm, quantum chemistry acts as a relatively cost-effective oracle for evaluating the properties of particular molecules, while generative models provide a means of sampling chemical space based on learned structure–function relationships. For practical applications, multiple potentially orthogonal properties must be optimized in tandem during a discovery workflow. This carries additional difficulties associated with the specificity of the targets and the ability for the model to reconcile all properties simultaneously. Here, we demonstrate an active learning approach to improve the performance of multi-target generative chemical models. We first demonstrate the effectiveness of a set of baseline models trained on single property prediction tasks in generating novel compounds (i.e., not present in the training data) with various property targets, including both interpolative and extrapolative generation scenarios. For property ranges where accurate targeting proves difficult, the novel compounds suggested by the model are characterized using quantum chemistry and the new molecules closest to expressing the desired properties are fed back into the generative model for additional training. This gradually improves the generative models’ understanding of targeted areas of chemical space and shifts the distribution of the generated compounds toward the targeted values. We then demonstrate the effectiveness of this active learning approach in generating compounds with multiple chemical constraints, including vertical ionization potential, electron affinity, and dipole moment targets, and validate the results at the ωB97X-D3/def2-TZVP level. This method requires no modifications to extant generative approaches, but rather utilizes their inherent generative and predictive aspects for self-refinement, and can be applied to situations where any number of properties with varying degrees of correlation must be optimized simultaneously.

Understanding predictions of drug effectiveness using explainable Machine Learning models

“…The expert can combine the insights of feature contributions for a single molecule with the feature's marginal impact at the global level to optimize the search for drug leads, for example in the molecule's neighbor space. The engineering of molecules from properties is an active field of research [35,36], where issues such as the optimization of multiple properties are challenging [37]. The information about the contribution of a certain feature can help in the engineering of models for inverse molecular design or help to optimize the search for improved drug leads.…”

De novo molecule design towards biased properties via a deep generative framework and iterative transfer learning

“…2 For instance, grammar variational autoencoders (GVAEs) 22 which represent molecules as parse trees from a context-free grammar, have been applied for multi-properties optimization. 23,24 However, VAEs lack a mechanism for de novo generating molecules conditioned on targeted, continuous property values. If a value of interest was changed, they should be retrained.…”

Generative organic electronic molecular design informed by quantum chemistry

“…Usually, a few hundred iterations (64 or 128 molecules sampled per iteration) were involved in applications of REINVENT for drug discovery. [26][27][28] We note that autoencoders have been employed for active search in model studies for searching for specied electronic properties (through iterative retraining of the autoencoder), 29 but these methods, if applied with DFT methods as a property predictor, would require hundreds of thousands DFT calculations, or an appropriate surrogate method to estimate their properties. Surrogate models have been employed as electronic property predictors for organic electronic materials discovery tasks using the REINVENT workow.…”