Guijun Zhang

RocketX improves de novo protein structure prediction using a closed-loop feedback mechanism combining geometric constraint prediction and model quality assessment.

DomBpred predicts protein domain boundaries using sequence-based methods, outperforming existing approaches in accuracy and multi-domain protein handling.

The paper introduces MPDB, a multi-domain protein structure database, and a server with modules for filtering and detecting structural analogues to aid in multi-domain protein modeling.

IPTDFold improves protein structure prediction by combining iterative sampling, topology adjustment, and distance deviation optimization, outperforming existing methods on benchmark datasets.

This paper introduces GDDfold, a distance-guided protein folding algorithm that outperforms existing methods on benchmark datasets.

This paper introduces SNfold, a sequential niche multimodal conformation sampling algorithm for protein structure prediction, which improves sampling efficiency and accuracy compared to existing methods.

MMpred improves de novo protein structure prediction by using a multimodal optimization protocol that enhances conformation sampling and model accuracy.

scTPA provides a web tool for analyzing single-cell RNA-seq data using pathway activation signatures to annotate cell types and identify functional patterns.