Self-supervised learning for macromolecular structure classification based on cryo-electron tomograms
Abstract
Macromolecular structure classification from cryo-electron tomography (cryo-ET) data is important for understanding macro-molecular dynamics. It has a wide range of applications and is essential in enhancing our knowledge of the sub-cellular environment. However, a major limitation has been insufficient labelled cryo-ET data. In this work, we use Contrastive Self-supervised Learning (CSSL) to improve the previous approaches for macromolecular structure classification from cryo-ET data with limited labels. We first pretrain an encoder with unlabelled data using CSSL and then fine-tune the pretrained weights on the downstream classification task. To this end, we design a cryo-ET domain-specific data-augmentation pipeline. The benefit of augmenting cryo-ET datasets is most prominent when the original dataset is limited in size. Overall, extensive experiments performed on real and simulated cryo-ET data in the semi-supervised learning setting demonstrate the effectiveness of our approach in macromolecular labeling and classification.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Aug 30, 2022
- Source ID
- 10.3389/fphys.2022.957484
Entities
People
- Andrew Zhou
- Jing Zhang
- Min Xu
- Mostofa Rafid Uddin
- Tarun Gupta
- Xiangrui Zeng
- Xuehai He
- Zachary Freyberg
Organizations
- National Institutes of Health
- National Science Foundation
- The Mark Foundation for Cancer Research
- United States Department of Defense