SelfAlign: Achieving Subtomogram Alignment with Self-Supervised Deep Learning

Xuan Wang, Haofan Cao, Xinsheng Wang, Xiaohua Wan, Fa ZhangBIBM 2024 · OpenReview

Abstract

Cryo-Electron Tomography (Cryo-ET) and subtomogram averaging (STA) have been instrumental in advancing the analysis of high-resolution structural biology, enabling detailed insights into macromolecular complexes. However, due to limitations in sample thickness and electronic metrology, there are inherent issues with missing wedge artifacts and low signal-to-noise ratio in Cryo-ET. Researchers use STA to align and average subtomograms to address these two issues. Traditional STA methods, reliant on cross-correlation, are computationally expensive and not scalable for large datasets. The emerging method of using deep learning for STA has low accuracy and unstable performance at low signal-to-noise ratios. To address these issues, we proposed SelfAlign, a self-supervised deep learning approach for subtomogram alignment. To improve alignment accuracy, we introduce a rotation and translation method effectively reducing translation errors. Further, we present a self-labeling mechanism optimized for end-to-end processes,thereby abolishing the need for manual labeling. Additionally, we design a concise and efficient loss function to uphold stable training in scenarios with low signal-to-noise ratios. We demonstrate the efficacy of SelfAlign using four datasets, showcasing its superior performance in terms of alignment accuracy compared to existing methods. SelfAlign offers a robust and scalable solution for subtomogram analysis.
BibTeX
@inproceedings{wang2024selfalign,
  author = {Xuan Wang and Haofan Cao and Xinsheng Wang and Xiaohua Wan and Fa Zhang},
  title = {{SelfAlign: Achieving Subtomogram Alignment with Self-Supervised Deep Learning}},
  booktitle = {BIBM},
  year = {2024},
  url = {https://openreview.net/forum?id=pJdzZbW20A},
}

Loading related content...

Figure