Automated matching of two‐time X‐ray photon correlation maps from phase‐separating proteins with Cahn–Hilliard‐type simulations using auto‐encoder networks. Issue 4 (15th June 2022)

• Record Type: Journal Article
• Authors: Timmermann, Sonja; Starostin, Vladimir; Girelli, Anita; Ragulskaya, Anastasia; Rahmann, Hendrik; Reiser, Mario; Begam, Nafisa; Randolph, Lisa; Sprung, Michael; Westermeier, Fabian; Zhang, Fajun; Schreiber, Frank; Gutt, Christian
• Is Part Of: Journal of applied crystallography. Volume 55:Issue 4(2022)
• Page Start: 751
• Page End: 757
• Publication Date: 2022-06-15
• Subjects: protein dynamics -- X‐ray photon correlation spectroscopy -- XPCS -- Cahn–Hilliard -- auto‐encoders -- machine learning; Crystallography -- Periodicals; 548.05
• DOI: 10.1107/S1600576722004435
• Languages: English
• ISSNs: 0021-8898

Abstract

Abstract : Two‐time correlation maps are classified in a simulation framework using an auto‐encoder network. Abstract : 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.