Accelerating drug target inhibitor discovery with a deep generative foundation model

Inhibitor discovery for emerging drug-target proteins is challenging, especially when target structure or active molecules are unknown. Here, we experimentally validate the broad utility of a deep generative framework trained at-scale on protein sequences, small molecules, and their mutual interactions-unbiased toward any specific target. We performed a protein sequence-conditioned sampling on the generative foundation model to design small-molecule inhibitors for two dissimilar targets: the spike protein receptor-binding domain (RBD) and the main protease from SARS-CoV-2. Despite using only the target sequence information during the model inference, micromolar-level inhibition was observed in vitro for two candidates out of four synthesized for each target. The most potent spike RBD inhibitor exhibited activity against several variants in live virus neutralization assays. These results establish that a single, broadly deployable generative foundation model for accelerated inhibitor discovery is effective and efficient, even in the absence of target structure or binder information.

Automated summary

We validate the broad utility of a deep generative framework trained on protein sequences, small molecules, and their interactions to discover inhibitors for emerging drug-target proteins. By using protein sequence-conditioned sampling, we successfully designed small-molecule inhibitors for two dissimilar targets without knowing their structures or active molecules. In vitro experiments showed micromolar-level inhibition for two out of four synthesized candidates for each target. The most potent inhibitor also exhibited activity against several variants in live virus neutralization assays, demonstrating the effectiveness and efficiency of the generative foundation model in accelerated inhibitor discovery without target structure or binder information.