Accelerating drug target inhibitor discovery with a deep generative foundation model

Abstract

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.

Targeting the Main Protease (Mpro, nsp5) by Growth of Fragment Scaffolds Exploiting Structure-Based Methodologies

“…Also AI methodolgy has very recently been proposed to expedite the process. 24 Crystallography (X-ray) and nuclear magnetic resonance spectroscopy (NMR) 25−29 have been used as primary structural screens for M pro . In addition, activity-based readouts have been performed.…”

“…A different approach is to start with fragment molecules that serve as molecular scaffolds and to grow or link one or several fragments to improve binding affinity and specificity. , In both cases, experimental structural data and/or modeling are used to prioritize initial screening hits for subsequent medicinal chemistry optimization cycles. Also AI methodolgy has very recently been proposed to expedite the process …”

Target-aware Molecule Generation for Drug Design Using a Chemical Language Model*

“…Generative modeling techniques greatly empowers drug design. In recent years, a growing number of approaches have been proposed to guide the generation of drug-like compounds given the information of target proteins [12][13][14][15][16][17], stemming from creative artificial intelligence techniques such as autoregressive models [18], generative adversarial networks (GAN) [19], variational autoencoders (VAE) [20], and diffusion models [12]. These approaches, by exploring the chemical space conditioned on the target of interest, have demonstrated the feasibility of target-based generative drug design with deep learning.…”

Identification of SARS-CoV-2 Mpro inhibitors through deep reinforcement learning for de novo drug design and computational chemistry approaches

“…14 Another similar approach employing reinforcement learning has been applied retrospectively to demonstrate that a DGM could generate active molecules where these molecules were not included in the training dataset. 15 Finally, de novo design approaches, without reinforcement learning, were applied to discover new SARS-COV-2 Mpro inhibitors for which two approaches were experimentally validated 16,17 while two others were not. 18,19…”