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.

Keywords: X-ray diffraction; dynamic sampling; nonlinear optical microscopy; second-harmonic generation; supervised learning approach; two-photon-excited fluorescence.

Figure 1

Illustration of the SLADS algorithm. The inputs to the function are initial measurements and the parameters from training. SLADS runs until a predefined stopping condition is met.

Figure 2

(a, c) TPEF of mCherry crystal acquired at 1 µm resolution. (b, d) Synthetic binary XRD image created by thresholding, filtering the TPEF image using a Gaussian kernel and downsampling the image five times. A training database for the algorithm was created with (b), whereas (d) was used to determine a threshold to stop SLADS.

Figure 3

(a) XRD image of mCherry crystals with accompanying diffraction pattern. (b) Binary-image ground-truth imageconstructed by setting a threshold of 5 × 10⁵. (c) Location and measurements that were acquired; green = background; yellow = crystal; 30.8% of the image was sampled and 9.03% of the interior of the crystal was measured. (d) Image reconstructed from SLADS measurements in (c). The ND between the ground truth in (b) and reconstructed image in (d) was 4 × 10⁻³.

Figure 4

(a) TPEF image of mCherry crystals, (b) thresholded image for use as training set, (c) TPEF of mCherry crystals and (d) thresholded image to find stopping condition.

Figure 5

(a) TPEF image of mCherry crystals. (b) Synthetic image created by thresholding the image in (a) and used as ground truth for reconstruction. (c) Location and measurements that were acquired; green = background; yellow = crystal; 6.7% of the image was sampled and 11.5% of the interior of crystal was measured. (d) Image reconstructed from SLADS measurements in (c). The ND between the ground truth in (b) and reconstructed image in (d) was 1.7 × 10⁻³.

Figure 6

SLADS implementation at Argonne National Laboratory with lysozyme. (a) Measured locations for the 0° rotation acquired; green = background; yellow = crystal; 3% of the image was sampled and approximately 5% of the interior of crystal was measured. (b) Generated reconstruction from (a). (c) Measured locations for the 90° rotation acquired; green = background; yellow = crystal; 3% of the image was sampled and approximately 5% of the interior of crystal was measured. (d) Generated reconstruction from (c).