Few shot domain adaptation for in situ macromolecule structural classification in cryo-electron tomograms

TL;DR

This paper introduces a few-shot domain adaptation approach to improve cross-domain subtomogram classification in cryo-electron tomography, addressing data scarcity and domain discrepancy issues.

Contribution

It proposes a novel method leveraging unlabeled target data and source-target correlation to enhance classification accuracy across domains.

Findings

Significant improvement over baseline methods in simulated datasets.

Effective utilization of unlabeled target data boosts classification performance.

Method demonstrates robustness in real cryo-ET datasets.

Abstract

Motivation: Cryo-Electron Tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at sub-molecular resolution. Such information is critical for the accurate understanding of cellular processes. However, subtomogram classification remains one of the major challenges for the systematic recognition and recovery of the macromolecule structures in cryo-ET because of imaging limits and data quantity. Recently, deep learning has significantly improved the throughput and accuracy of large-scale subtomogram classification. However often it is difficult to get enough high-quality annotated subtomogram data for supervised training due to the enormous expense of labeling. To tackle this problem, it is beneficial to utilize another already annotated dataset to assist the training process. However, due to the discrepancy of image intensity distribution between source domain and target domain, the model trained on subtomograms in source domainmay perform poorly in predicting subtomogram classes in the target domain. Results: In this paper, we adapt a few shot domain adaptation method for deep learning based cross-domain subtomogram classification. The essential idea of our method consists of two parts: 1) take full advantage of the distribution of plentiful unlabeled target domain data, and 2) exploit the correlation between the whole source domain dataset and few labeled target domain data. Experiments conducted on simulated and real datasets show that our method achieves significant improvement on cross domain subtomogram classification compared with baseline methods.