Accelerating Inhibitor Discovery With A Deep Generative Foundation Model: Validation for SARS-CoV-2 Drug Targets

TL;DR

This paper demonstrates that a deep generative model trained on protein and molecule data can effectively design inhibitors for SARS-CoV-2 targets without target-specific training, showing promising in vitro activity and broad applicability.

Contribution

It introduces a target-agnostic, deep generative framework for inhibitor discovery that works solely on protein sequences, validated on SARS-CoV-2 targets with successful experimental results.

Findings

Achieved micromolar inhibition in vitro for two SARS-CoV-2 targets.

The most potent inhibitor showed activity against virus variants.

A single generative model can be broadly effective without target-specific adaptation.

Abstract

The discovery of novel inhibitor molecules for emerging drug-target proteins is widely acknowledged as a challenging inverse design problem: Exhaustive exploration of the vast chemical search space is impractical, especially when the target structure or active molecules are unknown. Here we validate experimentally the broad utility of a deep generative framework trained at-scale on protein sequences, small molecules, and their mutual interactions -- that is unbiased toward any specific target. As demonstrators, we consider two dissimilar and relevant SARS-CoV-2 targets: the main protease and the spike protein (receptor binding domain, RBD). To perform target-aware design of novel inhibitor molecules, a protein sequence-conditioned sampling on the generative foundation model is performed. Despite using only the target sequence information, and without performing any target-specific adaptation of the generative model, micromolar-level inhibition was observed in in vitro experiments for two candidates out of only four synthesized for each target. The most potent spike RBD inhibitor also exhibited activity against several variants in live virus neutralization assays. These results therefore establish that a single, broadly deployable generative foundation model for accelerated hit discovery is effective and efficient, even in the most general case where neither target structure nor binder information is available.