Jun Liu

DeepUMQA3: a web server for model quality assessment of protein complexes

DeepUMQA3 evaluates protein complex structures using a deep neural network, achieving high accuracy in interface residue assessment and ranking first in CASP15 blind tests.

De novo protein structure prediction by incremental inter-residue geometries prediction and model quality assessment using deep learning

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

A de novo protein structure prediction by iterative partition sampling, topology adjustment, and residue-level distance deviation optimization

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

Distance-guided protein folding based on generalized descent direction

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