Molecular De Novo Design through Deep Reinforcement Learning
This addresses the problem of efficient drug discovery for chemists and pharmaceutical researchers, offering a method for scaffold hopping and library expansion, though it appears incremental as it builds on existing generative models.
The paper tackles molecular de novo design by tuning a generative model to produce molecules with specific properties, achieving over 95% predicted active compounds for a dopamine receptor target, including novel actives not in the training data.
This work introduces a method to tune a sequence-based generative model for molecular de novo design that through augmented episodic likelihood can learn to generate structures with certain specified desirable properties. We demonstrate how this model can execute a range of tasks such as generating analogues to a query structure and generating compounds predicted to be active against a biological target. As a proof of principle, the model is first trained to generate molecules that do not contain sulphur. As a second example, the model is trained to generate analogues to the drug Celecoxib, a technique that could be used for scaffold hopping or library expansion starting from a single molecule. Finally, when tuning the model towards generating compounds predicted to be active against the dopamine receptor type 2, the model generates structures of which more than 95% are predicted to be active, including experimentally confirmed actives that have not been included in either the generative model nor the activity prediction model.