Publications by authors named "Yanbei Li"
Compound-protein interactions (CPIs) are critical in drug discovery for identifying therapeutic targets, drug side effects, and repurposing existing drugs. Machine learning (ML) algorithms have emerged as powerful tools for CPI prediction, offering notable advantages in cost-effectiveness and efficiency. This review provides an overview of recent advances in both structure-based and non-structure-based CPI prediction ML models, highlighting their performance and achievements.
View Article and Find Full Text PDFArticle Synopsis
- Structure-based lead optimization in drug discovery currently relies heavily on medicinal chemists' experience and hypotheses; a new method called PBCNet aims to improve this process.
- PBCNet uses a physics-informed graph attention mechanism to accurately rank binding affinities among similar ligands, outperforming traditional methods in both accuracy and efficiency during testing on over 460 ligands across 16 targets.
- Additionally, it includes a user-friendly web service, allowing researchers to easily predict binding affinities, potentially speeding up lead optimization campaigns by up to 473%.
When nanoparticles were introduced into the biological media, the protein corona would be formed, which endowed the nanoparticles with new bio-identities. Thus, controlling protein corona formation is critical to therapeutic effect. Controlling the particle size is the most feasible method during design, and the influence of media pH which varies with disease condition is quite important.
View Article and Find Full Text PDF