Supervised Classification Methods for Flash X-ray single particle diffraction Imaging

Current Flash X-ray single-particle diffraction Imaging (FXI) experiments, which operate on modern X-ray Free Electron Lasers (XFELs), can record millions of interpretable diffraction patterns from individual biomolecules per day. Due to the practical limitations with the FXI technology, those patterns will to a varying degree include scatterings from contaminated samples. Also, the heterogeneity of the sample biomolecules is unavoidable and complicates data processing. Reducing the data volumes and selecting high-quality single-molecule patterns are therefore critical steps in the experimental setup. In this paper, we present two supervised template-based learning methods for classifying FXI patterns. Our Eigen-Image and LogLikelihood classifier can find the best-matched template for a single-molecule pattern within a few milliseconds. It is also straightforward to parallelize them so as to match the XFEL repetition rate fully, thereby enabling processing at site. The methods perform in a stable way on various kinds of synthetic data. As a practical example we tested our methods on a real mimivirus dataset, obtaining a convincing classification accuracy of 0.9. © 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

[1]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[2]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  A. Polydoros,et al.  Further results in likelihood classification of QAM signals , 1994, Proceedings of MILCOM '94.

[4]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Alex Pentland,et al.  Beyond eigenfaces: probabilistic matching for face recognition , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[6]  Gérard Govaert,et al.  Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  J. Hajdu,et al.  Potential for biomolecular imaging with femtosecond X-ray pulses , 2000, Nature.

[8]  David R Nelson,et al.  Virus shapes and buckling transitions in spherical shells. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  Bruce A. Draper,et al.  Analyzing PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Measures , 2003 .

[10]  S. Marchesini,et al.  High-resolution ab initio three-dimensional x-ray diffraction microscopy. , 2005, Journal of the Optical Society of America. A, Optics, image science, and vision.

[11]  Monica Olvera de la Cruz,et al.  Faceting ionic shells into icosahedra via electrostatics , 2007, Proceedings of the National Academy of Sciences.

[12]  D. Powers.  Evaluation: From Precision, Recall and F-Factor to ROC, Informedness, Markedness & Correlation , 2008 .

[13]  Veit Elser,et al.  Reconstruction algorithm for single-particle diffraction imaging experiments. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  J. Bozek.  AMO instrumentation for the LCLS X-ray FEL , 2009 .

[15]  Claudio R. C. M. da Silva,et al.  Maximum-Likelihood Classification of Digital Amplitude-Phase Modulated Signals in Flat Fading Non-Gaussian Channels , 2011, IEEE Transactions on Communications.

[16]  Andrew V. Martin,et al.  Unsupervised classification of single-particle X-ray diffraction snapshots by spectral clustering. , 2011, Optics express.

[17]  Garth J. Williams,et al.  Single mimivirus particles intercepted and imaged with an X-ray laser , 2011, Nature.

[18]  Hujun Yin,et al.  Eigenlights: Recovering Illumination from Face Images , 2011, IDEAL.

[19]  Chunhong Yoon,et al.  Novel algorithms in coherent diffraction imaging using x-ray free-electron lasers , 2012, Other Conferences.

[20]  Roberto Dinapoli,et al.  High speed cameras for X-rays: AGIPD and others , 2013 .

[21]  Anton Barty,et al.  High-throughput imaging of heterogeneous cell organelles with an X-ray laser , 2014, Nature Photonics.

[22]  Anton Barty,et al.  Automated identification and classification of single particle serial femtosecond X-ray diffraction data. , 2014, Optics express.

[23]  Anton Barty,et al.  Cheetah: software for high-throughput reduction and analysis of serial femtosecond X-ray diffraction data , 2014, Journal of applied crystallography.

[24]  Jing Liu,et al.  Machine learning for ultrafast X-ray diffraction patterns on large-scale GPU clusters , 2014, Int. J. High Perform. Comput. Appl..

[25]  Anton Barty,et al.  Imaging single cells in a beam of live cyanobacteria with an X-ray laser , 2015, Nature Communications.

[26]  Jean-Michel Claverie,et al.  Three-dimensional reconstruction of the giant mimivirus particle with an x-ray free-electron laser. , 2015, Physical review letters.

[27]  Georg Weidenspointner,et al.  Single-shot diffraction data from the Mimivirus particle using an X-ray free-electron laser , 2016, Scientific Data.

[28]  Tomas Ekeberg,et al.  Condor: a simulation tool for flash X-ray imaging , 2016, Journal of applied crystallography.

[29]  Correlations in Scattered X-Ray Laser Pulses Reveal Nanoscale Structural Features of Viruses. , 2017, Physical review letters.

[30]  Anton Barty,et al.  Experimental strategies for imaging bioparticles with femtosecond hard X-ray pulses , 2017, IUCrJ.

[31]  Anton Barty,et al.  Coherent soft X-ray diffraction imaging of coliphage PR772 at the Linac coherent light source , 2017, Scientific Data.

[32]  Anton Barty,et al.  Single-particle imaging without symmetry constraints at an X-ray free-electron laser , 2018, IUCrJ.