Deep learning model predicts water interaction sites on the surface of proteins using limited-resolution data.
Zaucha, J., Softley, C.A., Sattler, M., Frishman, D., Popowicz, G.M.(2020) Chem Commun (Camb) 56: 15454-15457
- PubMed: 33237041 
- DOI: https://doi.org/10.1039/d0cc04383d
- Primary Citation of Related Structures:  
6ZFW - PubMed Abstract: 
We develop a residual deep learning model, hotWater (https://pypi.org/project/hotWater/), to identify key water interaction sites on proteins for binding models and drug discovery. This is tested on new crystal structures, as well as cryo-EM and NMR structures from the PDB and in crystallographic refinement with promising results.
Organizational Affiliation: 
Department of Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universität München, Maximus-von-Imhof-Forum 3, 85354 Freising, Germany. d.frishman@wzw.tum.de.