Quantized Neural Representation for Lossy Cryo-EM Compression

Clicks: 4
ID: 322590
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #222 of 818 articles by views in BMC Bioinformatics

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 818 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
SUMMARY: Cryo-electron microscopy (cryo-EM) visualization transforms high-resolution 3D density volumes into intuitive representations, playing a vital role in structural biology. However, the increasing scale of cryo-EM data poses challenges for interactive visualization, including storage, transmission, and exploration. To address this, we propose a hybrid quantized implicit neural representation (INR) method that compresses cryo-EM volumes while supporting efficient on-demand access. To evaluate its effectiveness, we benchmark our approach against traditional compression techniques and one classic INR compressor, assessing both compression efficiency and visual quality. Beyond standard metrics, we examine performance on key cryo-EM tasks, including overall structure identification, secondary structure recognition, and fine-chain inspection. Our results demonstrate that the quantized INR achieves superior storage efficiency and task-relevant fidelity, and we provide an interactive tool and guidelines to assist users in selecting optimal compression strategies. AVAILABILITY: To facilitate future research, we provide our quantized neural representation approach and interactive tool available at Zenodo (https://doi.org/10.5281/zenodo.19688284) and GitHub (https://github.com/ChiefMoo/Lossy-Cryo-EM-Compression).
Reference Key
openalex_W7170143265 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Xi Duan, Yiming Shao, ZhiYuan Meng, Zijian Xu, Jun Han, Changhe Tu, Yue Wang, Renmin Han, Qiong Zeng
Journal BMC Bioinformatics
Year 2026
DOI
10.1093/bioinformatics/btag547
URL
https://doi.org/10.1093/bioinformatics/btag547
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.