Fa Zhang

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.

CryoForge is an evidence-gated agent that improves cryo-EM model building by selectively accepting or rejecting edits based on structural evidence, achieving validated improvements in most test cases.

CryoDiff enhances cryo-EM maps using a diffusion model with uncertainty estimation, improving resolution and model completeness.

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.

PGAR-Zernike provides a fast and accurate open-source toolkit for computing Zernike descriptors of protein structures, enabling efficient structural database construction and retrieval.

This paper introduces trRosettaRNA, a deep learning method for RNA 3D structure prediction, showing improved accuracy over existing methods on benchmark datasets.

This paper introduces a hybrid unsupervised method for accurate short read clustering and barcoded sample demultiplexing in nanopore sequencing, outperforming traditional tools in clustering and matching learning-based methods in demultiplexing.

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.