CryoGS: High-Quality Cryo-EM Homogeneous Reconstruction by Gaussian Splatting

High-resolution Cryo-EM structure reconstruction of complex macromolecules is a vital step in the field of structural biology. Although many attempts have been made towards this goal to consider quality-degrading factors such as imaging noise and non-uniform distribution of particle orientations, there is still a substantial gap between the best resolution achieved by the existing methods, measured in the Gold Standard Fourier Shell Correlation (GSFSC), and the hard resolution provided by the imaging device. Here, we introduce CryoGS, a novel 3-D reconstruction method for Cryo-EM structures using Gaussian splatting. Through the integration of 3-D Gaussian representations into neural network learning, CryoGS employs a spatial domain approach to optimize learnable 3-D Gaussians and project them into 2-D images using the splatting technique. Compared with existing methods, CryoGS achieves significant improvements in resolution, isotropy, and computational efficiency. For example, CryoGS achieves a GSFSC resolution of 2.217Å on the EMPIAR-10492 dataset, approaching its Nyquist limit of 2.2Å, while the best resolution achieved by the existing methods is 3.805Å. Furthermore, CryoGS exhibits remarkable robustness in reconstructing high-resolution models under challenging conditions such as data heterogeneity, pose inaccuracy, limited particle data, and high noise. Based on these results, we believe that CryoGS has great potential to be a powerful tool for Cryo-EM applications to ensure enhanced resolution, robustness, and efficiency.