深度学习模型使用低分辨率数据预测蛋白质表面的水相互作用位点。
Deep learning model predicts water interaction sites on the surface of proteins using limited-resolution data.
机构信息
Department of Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universität München, Maximus-von-Imhof-Forum 3, 85354 Freising, Germany.
出版信息
Chem Commun (Camb). 2020 Dec 21;56(98):15454-15457. doi: 10.1039/d0cc04383d. Epub 2020 Nov 25.
PMID:33237041
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.
摘要
我们开发了一个残差深度学习模型，hotWater（https://pypi.org/project/hotWater/），用于识别蛋白质结合模型和药物发现中的关键水相互作用位点。该模型在新的晶体结构、PDB 中的冷冻电镜和 NMR 结构以及晶体学精修中进行了测试，结果令人满意。
Zotero 插件