Xiaohua Wan

CryoMV generates and validates continuous protein conformations from cryo-EM data using structure priors and real-particle validation, achieving high resolution and robustness on benchmark datasets.

CryoFlex quantifies structural motion between cryo-EM conformational states directly from density maps, achieving high accuracy and outperforming registration baselines.

TD-COM detects personalized early-warning signals for critical transitions in complex diseases using single-sample community detection from transcriptomic data.

CryoDDM improves cryo-EM reconstruction by denoising images to capture conformational heterogeneity, validated on proteasome, membrane protein, and spike protein datasets.

MitoStructSeg accurately segments mitochondrial structures and quantifies morphological features in human and mouse tissues using a deep learning framework.

Noise-Transfer2Clean improves cryo-EM image denoising by modeling and transferring noise characteristics, achieving better signal restoration than existing methods.

VP-Detector uses a 3D convolutional neural network to automatically localize and classify macromolecules in cryo-electron tomograms, achieving competitive performance with efficient processing.