Screening articles from across Nature Portfolio

Chemical variational autoencoder (VAE) is a deep learning method for constructing chemical latent spaces, however, the current chemical VAE variants are limited in their ability to handle complex compound structures like natural products. Here, the authors develop a variational autoencoder that can handle natural products and demonstrate its utility as an in silico drug discovery tool.

A chemical screen identified a small molecule inhibitor of CHEK2 that boosts insulin secretion in human β cells, including those from both healthy and type 2 diabetic human islets, as well as in diabetic mouse models and cynomolgus macaques.

A high-throughput DNA-encoded library (DEL)-based screening approach was developed for the discovery of proximity-inducing small molecules.

Tricyclic peptides have reduced conformational flexibility, making them well suited for ligand development. Researchers have now generated large combinatorial libraries of tricyclic peptides using a disulfide-directing motif. Screening these libraries discovered binders to challenging protein targets.

Elucidating the interactions between serum protein-bound nanoparticles and cell-surface receptors typically operates on a per protein–receptor interaction basis. Integration of omic approaches for testing thousands of interactions unbiasedly reveals important interactions that drive cellular uptake of nanoparticles.

In early 2020, scientists and medics started rummaging around the pharmacy shelves hunting for treatments that might curtail the spiralling pandemic death rates. This is the story of how they are searching and what they have found so far.