Sheng‐You Huang

EM3DFold: accurate de novo protein and nucleic acid model building for cryo-EM maps using language model-powered deep learning

EM3DFold improves cryo-EM model building for proteins, nucleic acids, and complexes using a language model-powered deep learning framework, achieving high accuracy on benchmark datasets.

HDOCK-Multimer: integrating docking and combinatorial assembly for structure prediction of large protein complexes

HDOCK-Multimer improves prediction of large protein complexes by combining docking and combinatorial assembly, outperforming existing methods on benchmark datasets.

EMAlign: accurate alignment of cryo-EM maps through main-chain probability using deep learning

EMAlign improves cryo-EM map alignment using deep learning to predict main-chain probability, achieving high accuracy and success rates across global and local alignments.

EMReady2: improvement of cryo-EM and cryo-ET maps by local quality-aware deep learning with Mamba

EMReady2 improves cryo-EM and cryo-ET maps using a Mamba-based deep learning model, enhancing quality and interpretability while reducing computational cost.

TRiC folds the giant ciliary protein IFT172 via a non-canonical open-state mechanism

This study reveals how TRiC folds the large ciliary protein IFT172 using a non-canonical open-state mechanism involving Z-shaped bending and fold-and-eject dynamics.

Accurate protein structure determination from cryo-EM maps using deep learning and structure prediction

EMProt improves protein structure determination from cryo-EM maps using a three-track attention network, outperforming existing methods in accuracy and completeness.

Mechanism-Aware Inductive Bias Enhances Generalization in Protein-Protein Interaction Prediction

PLMDA-PPI improves protein-protein interaction prediction by integrating biophysical inductive biases, outperforming existing models in efficiency and generalization.

Full-length de novo protein structure determination from cryo-EM maps using deep learning

This paper introduces DeepMM, a deep learning framework that automatically reconstructs full-atom protein structures from cryo-EM maps with high accuracy and coverage.

Accurate prediction of residue-residue contacts across homo-oligomeric protein interfaces through deep leaning

This paper introduces DeepHomo, a deep learning model for predicting residue-residue contacts in homo-oligomeric protein interfaces, achieving >60% accuracy and outperforming existing methods.