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

Tags

Fields of Study

  • Computer science

Readers

  • Electrochemical Surface Science
  • Nanoscale Plasmonic Nanotechnology
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Microelectronics