A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy

Abstract

Background: Single-particle cryo-electron microscopy (cryo-EM) has become a popular tool for structural determination of biological macromolecular complexes. High-resolution cryo-EM reconstruction often requires hundreds of thousands of single-particle images. Particle extraction from experimental micrographs thus can be laborious and presents a major practical bottleneck in cryo-EM structural determination. Existing computational methods of particle picking often use low-resolution templates as inputs for particle matching, making it possible to cause reference-dependent bias. It is critical to develop a highly efficient template-free method to automatically recognize particle images from cryo-EM micrographs. Results: We developed a deep learning-based algorithmic framework, DeepEM, for single-particle recognition from noisy cryo-EM micrographs, enabling automated particle picking, selection and verification in an integrated fashion. The kernel of DeepEM is built upon a convolutional neural network (CNN) of eight layers, which can be recursively trained to be highly "knowledgeable". Our approach exhibits improved performance and high precision when tested on the standard KLH dataset. Application of DeepEM to several challenging experimental cryo-EM datasets demonstrates its capability in avoiding selection of un-wanted particles and non-particles even when true particles contain fewer features. Conclusions: The DeepEM method derived from a deep CNN allows automated particle extraction from raw cryo-EM micrographs in the absence of templates, which demonstrated improved performance, objectivity and accuracy. Application of this novel approach is expected to free the labor involved in single-particle verification, thus promoting the efficiency of cryo-EM data processing.

arXiv comment26 pages, 6 figures, 1 table

References in corpus (1)

• Understanding Deep Convolutional Networks

Cited by in corpus (12)

• Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs
• A deep learning approach to identify local structures in atomic-resolution transmission electron microscopy images
• Classification of diffusion modes in single-particle tracking data: Feature-based versus deep-learning approach
• Single-particle cryo-electron microscopy: Mathematical theory, computational challenges, and opportunities
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• Deep neural networks for classifying complex features in diffraction images
• Exploring particle dynamics during self-organization processes via rotationally invariant latent representations
• Artificial Intelligence Advances for De Novo Molecular Structure Modeling in Cryo-EM
• Microparticle cloud imaging and tracking for data-driven plasma science
• Simulation Study of Energy Resolution with Changing Pixel Size for Radon Monitor Based on \textit{Topmetal-${II}^{-}$} TPC
• On the parameters affecting dual-target-function evaluation of single-particle selection from cryo-electron micrographs
• Dual-target function validation of single-particle selection from low-contrast cryo-electron micrographs