Yanjun Li

SMARTFlexDB links ligand-bound and ligand-free RNA structures to study conformational flexibility and small-molecule recognition, providing a resource for RNA-targeted drug discovery.

Pep2Mol generates 3D molecules targeting protein-protein interfaces using diffusion models, achieving state-of-the-art binding affinities for small-molecule inhibitors.

SMARTPocket uses geometric deep learning to predict RNA-small molecule binding pockets from 3D structures, outperforming existing methods and identifying cryptic ligandable sites.

The paper develops a live-cell method to identify RNA-small molecule interactions and uses it to design selective RNA degraders.

GatorAffinity improves protein-ligand binding affinity prediction by combining synthetic structural data with experimental data, achieving better accuracy and generalizability.

SMARTBind uses deep learning and contrastive learning to identify small molecule binders to RNA without structural input, outperforming existing methods and reducing computational cost.

MGMG generates bioactivity-aware molecules using cell morphology and textual descriptions without target information, achieving comparable binding affinities to reference compounds.

AptaDiff generates and optimizes aptamers using diffusion models, outperforming existing methods and experimental candidates in binding affinity.

The paper introduces DeepDynaTree, a phylogenetic-informed graph deep learning model to classify dynamic transmission clusters in infectious disease epidemics, achieving higher accuracy than existing methods.

DyScore improves protein-ligand binding prediction by incorporating dynamic features into a boosting model, achieving better performance than existing methods.

The paper constructs a schizophrenia protein interaction network and shows it is sensitive to immune activation during fetal and adolescent development, with immune genes involved in synapse regulation.