Rxivist logo

DISCA: high-throughput cryo-ET structural pattern mining by deep unsupervised clustering

By Xiangrui Zeng, Anson Kahng, Liang Xue, Julia Mahamid, Yi-Wei Chang, Min Xu

Posted 17 May 2021
bioRxiv DOI: 10.1101/2021.05.16.444381

Cryo-electron tomography directly visualizes heterogeneous macromolecular structures in complex cellular environments, but existing computer-assisted sorting approaches are low-throughput or inherently limited due to their dependency on available templates and manual labels. We introduce a high-throughput template-and-label-free deep learning approach that automatically discovers subsets of homogeneous structures by learning and modeling 3D structural features and their distributions. Diverse structures emerging from sorted subsets enable systematic unbiased recognition of macromolecular complexes in situ.

Download data

  • Downloaded 595 times
  • Download rankings, all-time:
    • Site-wide: 48,234
    • In bioinformatics: 4,987
  • Year to date:
    • Site-wide: 5,816
  • Since beginning of last month:
    • Site-wide: 4,961

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide