CovaGEN introduced for de novo design of covalent inhibitors
CovaGEN is a conditional latent diffusion framework for de novo design of covalent inhibitors with enhanced drug-likeness and safety. In tests on EGFR T790M and Mpro, generated compounds showed higher probabilities of covalent binding.
CovaGEN is a conditional latent diffusion framework for the de novo design of covalent inhibitors with enhanced drug-likeness and safety. Computational design approaches for covalent drugs remain largely confined to virtual screening of existing libraries, and methods specifically tailored to de novo covalent drug generation are still lacking.
CovaGEN generates ligands from a drug-like latent space while conditioning on target sequences and employing a classifier to guide the formation of desirable covalent warheads. A reinforcement learning strategy further optimizes the safety profiles of generated molecules.
Experimental results demonstrate that CovaGEN effectively generates covalent drugs with the desired covalent warheads, exhibiting strong target protein affinity, favorable drug-likeness, and low toxicity. When applied to EGFR T790M and Mpro, the generated compounds exhibit higher probabilities of covalent binding.
The molecules used for the training of the molecular VAE and CovaGEN-cond are downloaded from the ZINC database. The raw data of the CrossDocked 2020 dataset were obtained from a public repository, and the small mouse intraperitoneal LD50 subdataset was obtained from TOXRIC. The source codes are available on GitHub and deposited on Zenodo.