Yanyan Lan

GalaxyVS rapidly screens 100 billion compounds against protein structures, achieving high throughput and releasing a cross-species interaction database.

This paper introduces AlphaRank, a deep learning model that ranks protein-ligand binding affinity using hyperbolic geometry to overcome limitations of Euclidean space models.

DrugCLIP, a contrastive dense-retrieval model for pockets and molecules, beats docking on DUD-E and LIT-PCBA and screened about 10,000 human AlphaFold2 proteins in 24 hours.

This study evaluates AlphaFold3-derived models for drug binding affinity ranking, showing they outperform existing methods and require fewer resources.

GET is a foundation model that accurately predicts gene expression and regulatory interactions across 213 human cell types using chromatin accessibility and sequence data.