KINNTREX: A Neural Network Unveils Protein Mechanism from Time Resolved X-ray Crystallography

Abstract

Here, a machine learning method based on a kinetically informed neural network (NN) is introduced. The proposed method is designed to analyze a time series of difference electron density (DED) maps from a time-resolved X-ray crystallographic experiment. The method is named KINNTREX (Kinetics Inspired NN for Time-Resolved X-ray Crystallography). To validate KINNTREX, multiple realistic scenarios were simulated with increasing level of complexity. For the simulations, time-resolved X-ray data was generated that mimic data collected from the photocycle of the photoactive yellow protein (PYP). KINNTREX only requires the number of intermediates and approximate relaxation times (both obtained from a singular valued decomposition) and does not require an assumption of a candidate mechanism. It successfully predicts a consistent chemical kinetic mechanism, together with difference electron density maps of the intermediates that appear during the reaction. These features make KINNTREX attractive for tackling a wide range of biomolecular questions. In addition, the versatility of KINNTREX can inspire more NN-based applications to time-resolved data from biological macromolecules obtained by other methods.