Towards Efficient Generation, Correction and Properties Control of Unique Drug-like Structures

Efficient design and screening of the novel molecules is a major challenge in drug and material design. This report focuses on a multi-stage pipeline in which several deep neural network (DNN) models are combined to map discrete molecular representations into continuous vector space to later generate from it new molecular structures with desired properties. Here the Attention-based Sequence-to-Sequence model is added to “spellcheck” and correct generated structures while the oversampling in the continuous space allows generating candidate structures with desired distribution for properties and molecular descriptors even for small reference datasets. We further use computer simulation to validate the desired properties in the numerical experiment. With the focus on the drug design, such pipeline allows generating novel structures with control of SAS (Synthetic Accessibility Score) and a series of ADME metrics that assess the drug-likeliness.