Virtual drug screening articles from across Nature Portfolio

The pore-forming toxin pneumolysin is responsible for the high mortality seen in pneumococcal infections unresponsive to antibiotics. In this work, authors report a small molecule inhibitor targeting pneumolysin and related ones as an anti-virulence strategy protecting human cells during infection.

Deep learning generative approaches have been used in recent years to discover new molecules with drug-like properties. To improve the performance of such approaches, Yang et al. add chemical binding knowledge to a deep generative framework and demonstrate, including by wet-lab verification, that the method can find valid molecules that successfully bind to target proteins.

Modern drug discovery relies upon intelligent exploration of ‘in stock’ and ‘on demand’ virtual libraries of compounds. A comparative analysis highlights the explosive expansion of accessible chemical space and also reveals challenges and opportunities arising for computational drug discovery.

We developed a computational method to reveal the drug-induced single-cell transcriptomic landscape. This algorithm enabled us to impute unknown drug-induced single-cell gene expression profiles using tensor imputation, predict cell type-specific drug efficacy, detect cell-type-specific marker genes, and identify the trajectories of regulated biological pathways while considering intercellular heterogeneity.

After a difficult start, medicinal chemists are now ready to embrace AI-based methods and concepts in drug discovery, explains Gisbert Schneider.