Understanding the data generation process could help to create artificial medical data sets without violating patient privacy, synthesizing different data modalities, or discovering data generating characteristics. Encouraging the latent representation of a generative model to be disentangled offers new perspectives of control and interpretability. Besides this, they are often criticized as black boxes as their decision process is often not human interpretable. These results show a broadly deployable machine intelligence framework can accelerate hit discovery across different emerging drug-targets.ĭiv>Deep neural networks are commonly used for medical purposes such as image generation, segmentation, or classification. The most potent spike RBD inhibitor also emerged as a rare non-covalent antiviral with broad-spectrum activity against several SARS-CoV-2 variants in live virus neutralization assays.
Micromolar-level in vitro inhibition was observed for two candidates (out of four synthesized) for each target. To perform target-aware design, the framework employs a target sequence-conditioned sampling of novel molecules from a generative model. We demonstrate the broad utility of a single deep generative framework toward discovering novel drug-like inhibitor molecules against two distinct SARS-CoV-2 targets - the main protease (Mpro) and the receptor binding domain (RBD) of the spike protein.
As exhaustive exploration of the vast chemical space is infeasible, discovering novel inhibitor molecules for emerging drug-target proteins is challenging, particularly for targets with unknown structure or ligands. The COVID-19 pandemic has highlighted the urgency for developing more efficient molecular discovery pathways.