Machine Learning for Structure Determination in Single-Particle Cryo-Electron Microscopy: A Systematic Review
Published in IEEE Transactions on Neural Networks and Learning Systems, 2021
Abstract
Single-particle cryo-electron microscopy has become a central technique for structural biology, but its computational workflow remains challenging because images are noisy, heterogeneous, and computationally demanding. This review surveys how machine-learning methods have been used across the structure-determination pipeline, including particle picking, two-dimensional classification, three-dimensional reconstruction, heterogeneity analysis, resolution estimation, and related image-processing tasks. It organizes representative algorithms, compares their roles in practical cryo-EM workflows, and discusses how deep learning and other learning-based methods can improve automation, robustness, and throughput while also introducing new needs for benchmark data, interpretability, and integration with established cryo-EM software.
Recommended citation: Jia-Geng Wu, Yang Yan, Dong-Xu Zhang, Bo-Wen Liu, Qing-Bing Zheng, Xiao-Liang Xie, Shi-Qi Liu, Sheng-Xiang Ge, Zeng-Guang Hou, Ning-Shao Xia. (2022). "Machine Learning for Structure Determination in Single-Particle Cryo-Electron Microscopy: A Systematic Review." IEEE Transactions on Neural Networks and Learning Systems, 33(2), 452-472. DOI: 10.1109/TNNLS.2021.3131325.
Publisher page