Zefeng Zhu

This study shows that AlphaFold2 distance maps can reveal multi-state protein structures, enabling prediction of alternative conformations with high accuracy.

PepMCP predicts membrane contact probability for short peptides using graph-based modeling, achieving high correlation with experimental data.

SteerAF improves AlphaFold2's ability to predict alternative protein conformations by using distogram information from MSAs, achieving better results than existing methods.

The paper determines the structure of the poxvirus portal complex and its pore, revealing their role in molecular transport and antiviral target potential.

PremPS predicts the effects of single mutations on protein stability and pathogenicity using a machine learning model trained on five thousand mutations.

PremPRI predicts the effects of single mutations on protein-RNA interactions using a regression model trained on experimental data, achieving high correlation with experimental binding affinity changes.