Generative Adversarial Networks for Robust Cryo-EM Image Denoising

The cryo-electron microscopy (cryo-EM) becomes popular for macromolecular structure determination. However, the 2D images captured by cryo-EM are of high noise and often mixed with multiple heterogeneous conformations and contamination, imposing a challenge for denoising. Traditional image denoising methods and simple denoising autoencoder cannot work well when the signal-to-noise ratio (SNR) of images is meager and contamination distribution is complex. Thus it is desired to develop new effective denoising techniques to facilitate further research such as 3D reconstruction, 2D conformation classification, and so on. In this chapter, we approach the robust denoising problem for cryo-EM images by introducing a family of generative adversarial networks (GANs), called β-GAN, which is able to achieve robust estimation of certain distributional parameters under Huber contamination model with statistical optimality. To address the denoising challenges, for example, the traditional image generative model might be contaminated by a small portion of unknown outliers, β-GANs are exploited to enhance the robustness of denoising autoencoder. Our proposed method is evaluated by both a simulated dataset on the Thermus aquaticus RNA polymerase (RNAP) and a real-world dataset on the Plasmodium falciparum 80S ribosome dataset (EMPIAR-10028), in terms of mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and 3D reconstruction as well. Quantitative comparisons show that equipped with some designs of β-GANs and the robust ℓ1-autoencoder, one can stabilize the training of GANs and achieve the state-of-the-art performance of robust denoising with low SNR data and against possible information contamination. Our proposed methodology thus provides an effective tool for robust denoising of cryo-EM 2D images and helpful for 3D structure reconstruction.