Dynamic X-ray diffraction sampling for protein crystal positioning

Abstract

A sparse supervised learning approach for dynamic sampling (SLADS) is described for dose reduction in diffraction-based protein crystal positioning. Crystal centering is typically a prerequisite for macromolecular diffraction at synchrotron facilities, with X-ray diffraction mapping growing in popularity as a mechanism for localization. In X-ray raster scanning, diffraction is used to identify the crystal positions based on the detection of Bragg-like peaks in the scattering patterns; however, this additional X-ray exposure may result in detectable damage to the crystal prior to data collection. Dynamic sampling, in which preceding measurements inform the next most information-rich location to probe for image reconstruction, significantly reduced the X-ray dose experienced by protein crystals during positioning by diffraction raster scanning. The SLADS algorithm implemented herein is designed for single-pixel measurements and can select a new location to measure. In each step of SLADS, the algorithm selects the pixel, which, when measured, maximizes the expected reduction in distortion given previous measurements. Ground-truth diffraction data were obtained for a 5 µm-diameter beam and SLADS reconstructed the image sampling 31% of the total volume and only 9% of the interior of the crystal greatly reducing the X-ray dosage on the crystal. Using in situ two-photon-excited fluorescence microscopy measurements as a surrogate for diffraction imaging with a 1 µm-diameter beam, the SLADS algorithm enabled image reconstruction from a 7% sampling of the total volume and 12% sampling of the interior of the crystal. When implemented into the beamline at Argonne National Laboratory, without ground-truth images, an acceptable reconstruction was obtained with 3% of the image sampled and approximately 5% of the crystal. The incorporation of SLADS into X-ray diffraction acquisitions has the potential to significantly minimize the impact of X-ray exposure on the crystal by limiting the dose and area exposed for image reconstruction and crystal positioning using data collection hardware present in most macromolecular crystallography end-stations.

Synchrotron Big Data Science

“…One example is the application of the deep CNN methods to X‐ray tomography which can improve the quality of the projections collected, thus increasing by at least tenfold, the final low‐dose fast acquisition X‐ray tomographic signal . Further examples include the application of machine learning approaches to image classification and pattern recognition in image analysis of protein crystals, X‐ray diffraction, X‐ray scattering, X‐ray spectroscopy, parameter‐space exploration, as well as X‐ray microtomography . At ALS this approach has been incorporated in a whole framework to address Images across Domains, Experiments, Algorithms and Learning (IDEAL), which is aimed at addressing a full set of pattern recognition and analysis problems …”

Reduced electron exposure for energy-dispersive spectroscopy using dynamic sampling

“…Supervised learning approach for Dynamic Sampling (SLADS) was developed by Godaliyadda et al [15,27,28]. The goal of dynamic sampling, in general, is to find the measurement which, when added to the existing dataset, has the greatest effect on the expected reduction in distortion (ERD).…”

Deep Learning Approach for Dynamic Sparse Sampling for High-Throughput Mass Spectrometry Imaging

“…SLADS achieved below 10 −5 Normalized Distortion (ND) levels with only 6.9% of scanned locations in Electron Back Scatter Diffraction (EBSD) microscopy [8,9]. In X-Ray crystallography of proteins, only 5% of a sample was required for a ND level of ~ 10 −3 % (a ~ 20-fold reduction in X-ray exposure) [10]. In confocal Raman microscopy, SLADS yielded a 6-fold reduction in the number of measurements needed for a 0.1% image difference [11].…”