National Institutes of Health/National Institute of General Medical Sciences (NIH/NIGMS)
R01GM134020
米国
National Institutes of Health/National Institute of General Medical Sciences (NIH/NIGMS)
P41GM103712
米国
National Science Foundation (NSF, United States)
DBI-1949629
米国
National Science Foundation (NSF, United States)
IIS-2007595
米国
National Science Foundation (NSF, United States)
IIS-2211597
米国
National Science Foundation (NSF, United States)
MCB-2205148
米国
The Mark Foundation
19-044-ASP
米国
David and Lucile Packard Foundation
2019-69645
米国
引用
ジャーナル: Proc Natl Acad Sci U S A / 年: 2023 タイトル: High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering. 著者: Xiangrui Zeng / Anson Kahng / Liang Xue / Julia Mahamid / Yi-Wei Chang / Min Xu / 要旨: Cryoelectron tomography directly visualizes heterogeneous macromolecular structures in their native and complex cellular environments. However, existing computer-assisted structure sorting approaches ...Cryoelectron tomography directly visualizes heterogeneous macromolecular structures in their native and complex cellular environments. However, existing computer-assisted structure sorting approaches are low throughput or inherently limited due to their dependency on available templates and manual labels. Here, we introduce a high-throughput template-and-label-free deep learning approach, Deep Iterative Subtomogram Clustering Approach (DISCA), that automatically detects subsets of homogeneous structures by learning and modeling 3D structural features and their distributions. Evaluation on five experimental cryo-ET datasets shows that an unsupervised deep learning based method can detect diverse structures with a wide range of molecular sizes. This unsupervised detection paves the way for systematic unbiased recognition of macromolecular complexes in situ.