期刊
JOURNAL OF APPLIED CRYSTALLOGRAPHY
卷 55, 期 -, 页码 751-757出版社
INT UNION CRYSTALLOGRAPHY
DOI: 10.1107/S1600576722004435
关键词
protein dynamics; X-ray photon correlation spectroscopy; XPCS; Cahn-Hilliard; auto-encoders; machine learning
资金
- BMBF [05K19PS1, 05K20PSA, 05K20VTA]
- Studienstiftung des deutschen Volkes for a personal fellowship
- Alexander von Humbold Foundation for a postdoctoral research fellowship
Machine learning methods are used to automatically classify X-ray photon correlation maps from protein solution experiments. The correlation maps are matched with simulated maps of liquid-liquid phase separations and interpreted in the simulation framework. This method facilitates the handling of large amounts of dynamic data.
Machine learning methods are used for an automated classification of experimental two-time X-ray photon correlation maps from an arrested liquid-liquid phase separation of a protein solution. The correlation maps are matched with correlation maps generated with Cahn-Hilliard-type simulations of liquid-liquid phase separations according to two simulation parameters and in the last step interpreted in the framework of the simulation. The matching routine employs an auto-encoder network and a differential evolution based algorithm. The method presented here is a first step towards handling large amounts of dynamic data measured at high-brilliance synchrotron and X-ray free-electron laser sources, facilitating fast comparison with phase field models of phase separation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据