Deep learning model predicts water interaction sites on the surface of proteins using limited-resolution data. Issue 98 (25th November 2020)

• Record Type: Journal Article
• Authors: Zaucha, Jan; Softley, Charlotte A.; Sattler, Michael; Frishman, Dmitrij; Popowicz, Grzegorz M.
• Is Part Of: Chemical communications. Volume 56:Issue 98(2020)
• Page Start: 15454
• Page End: 15457
• Publication Date: 2020-11-25
• Subjects: Chemistry -- Periodicals; 540
• DOI: 10.1039/d0cc04383d
• Languages: English
• ISSNs: 1359-7345

Abstract

Abstract : Deep learning model 'hotWater' scans the surface of proteins to identify the most likely water binding sites. 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.