Scalable 3D Reconstruction for X-Ray Single Particle Imaging Based on Online Machine Learning
X-ray free-electron lasers (XFELs) offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate XFELs enable single particle imaging (X-ray SPI) where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray SPI reconstruction algorithms, which estimate the unknown orientation of a particle in each captured image as well as its shared 3D structure, are inadequate in handling the massive datasets generated by these emerging XFELs.
Illustration of XFEL SPI image acquisition process and subsequent online processing by our algorithm. A femtosecond-resolution X-ray pulse intersects a single, hydrated molecule, creating a diffraction image. This process is repeated at high rates to collect millions of diffraction images, each observing the molecule with an unknown orientation, or pose. Our algorithm, X-RAI, employs a CNN-based encoder fψ to efficiently estimate the pose Rφ of the molecule in each image. A physically accurate decoder Γ (in Fourier space, shown here in real space) produces a noise-free estimate of the diffraction pattern using the molecule’s 3D structure, represented as a neural field Vθ. The symmetric loss Lsym is applied to optimize the parameters ψ and θ in an online fashion using self-supervision. At any point during the experiment, the volume Vθ can be phased to obtain an estimate of the electron density.
Here, we introduce X-RAI, an online reconstruction framework that estimates the structure of a 3D macromolecule from large X-ray SPI datasets (Shenoy et al., 2023; Shenoy et al., 2023). X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner.
Reconstruction of a cubic gold nanoparticle from experimental data collected at an XFEL facility. To enforce the known cubic symmetry of the nanoparticle, we augment the encoder’s orientation estimates with the symmetry rotations of the cube (equivalent to the octahedral symmetry group), effectively spreading out the pose estimates over SO(3). The re- sulting density reconstruction is of resolution 5.74 nanometers. Only the low-resolution panels of the diffraction content are used for reconstruction and shown in this figure as they contain the majority of the diffraction signal. The patterns are displayed with reduced image contrast. 16
We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray SPI towards real-time capture and reconstruction.
References
2023
SPI
Amortized pose estimation for x-ray single particle imaging
Jay Shenoy, Axel Levy, Frédéric Poitevin, and 1 more author
In Machine learning for structural biology Workshop, 2023
X-ray single particle imaging (SPI) is a nascent technique that can capture the dynamics of biomolecules at room temperature. SPI experiments will one day collect tens of millions of images of the same molecule in order to overcome the weak scattering of individual proteins. Existing reconstruction algorithms will be unable to scale to datasets of this size because they perform computationally expensive search steps to estimate the orientation of the molecule in each image. In this work, we propose a reconstruction algorithm that amortizes the estimation of pose via an autoencoder framework. Our approach consists of a convolutional encoder that maps X-ray images to predicted poses and a physics-based decoder that implicitly fuses all the 2D scattering images into a volumetric representation of the molecule. We validate our method on 6 synthetic datasets of 2 distinct proteins, showing that for the largest datasets containing 5 million images, our technique can reconstruct the electron density in a single pass.
SPI
Scalable 3D Reconstruction From Single Particle X-Ray Diffraction Images Based on Online Machine Learning
Jay Shenoy, Axel Levy, Frédéric Poitevin, and 1 more author
X-ray free-electron lasers (XFELs) offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate XFELs enable single particle imaging (X-ray SPI) where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray SPI reconstruction algorithms, which estimate the unknown orientation of a particle in each captured image as well as its shared 3D structure, are inadequate in handling the massive datasets generated by these emerging XFELs. Here, we introduce X-RAI, an online reconstruction framework that estimates the structure of a 3D macromolecule from large X-ray SPI datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray SPI towards real-time capture and reconstruction.
