Qinghua Wang

OPUS-DSD2 disentangles structural heterogeneity in cryo-EM and cryo-ET data by separating rigid-body dynamics from other variations, improving analysis of macromolecular structures.

OPUS-BFactor predicts normalized protein B-factors using sequence or structural information, outperforming existing methods on benchmark datasets.

OPUS-TOMO improves resolution and resolves structural heterogeneity in cryo-ET data for biomolecules like ATP synthase and ribosomes.

OPUS-Rota5 improves protein side-chain modeling accuracy, enhancing molecular docking success rates for GPCR targets.

OPUS-Rota4 improves protein side-chain modeling by integrating deep learning predictors and constraints, achieving better accuracy than Alphafold2 on CASP14.