Jiqing Zheng

NeoPep designs functional peptides de novo using a deep-learning framework that models biophysical principles, achieving high hit rates and structural accuracy across diverse targets.

This paper introduces AnewOmni, a generative model that designs biomolecules across scales by learning interaction patterns and physical constraints from 5 million complexes.

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.

MFPLI evaluates protein-ligand binding authenticity using deep learning with physicochemical and structural features, achieving high accuracy in distinguishing native conformations from docking poses.

The paper determines cryo-EM structures of IMiDs in full CRL4CRBN complexes, revealing a cryptic interfacial pocket that enhances IMiD efficacy and neosubstrate specificity.

The paper identifies a unique mechanism by which ASXL1 K351 monoubiquitination enhances PR-DUB activity through structural stabilization, enabling efficient H2AK119Ub deubiquitination.