https://3demmethods.i2pc.es/index.php?action=history&feed=atom&title=2023Zeng_AITOM 2026-05-24T21:06:57Z Revision history for this page on the wiki MediaWiki 1.44.2 https://3demmethods.i2pc.es/index.php?title=2023Zeng_AITOM&diff=4412&oldid=prev 2023-08-14T07:55:11Z

<p>Created page with &quot;== Citation == Zeng, Xiangrui / Kahng, Anson / Xue, Liang / Mahamid, Julia / Chang, Yi-Wei / Xu, Min. High-throughput cryo-ET structural pattern mining by unsupervised deep i...&quot;</p> <p><b>New page</b></p><div>== Citation ==<br /> <br /> Zeng, Xiangrui / Kahng, Anson / Xue, Liang / Mahamid, Julia / Chang, Yi-Wei / Xu, Min. High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering. 2023. Proc. Natl. Acad. Sci. USA, Vol. 120, p. e2213149120 <br /> <br /> == Abstract ==<br /> <br /> Cryoelectron tomography directly visualizes heterogeneous macromolecular structures<br /> in their native and complex cellular environments. However, existing computerassisted<br /> structure sorting approaches are low throughput or inherently limited due<br /> to their dependency on available templates and manual labels. Here, we introduce<br /> a high-throughput template-and-label-free deep learning approach, Deep Iterative<br /> Subtomogram Clustering Approach (DISCA), that automatically detects subsets<br /> of homogeneous structures by learning and modeling 3D structural features and<br /> their distributions. Evaluation on five experimental cryo-ET datasets shows that an<br /> unsupervised deep learning based method can detect diverse structures with a wide<br /> range of molecular sizes. This unsupervised detection paves the way for systematic<br /> unbiased recognition of macromolecular complexes in situ.<br /> <br /> == Keywords ==<br /> <br /> == Links ==<br /> <br /> https://www.pnas.org/doi/abs/10.1073/pnas.2213149120<br /> <br /> == Related software ==<br /> <br /> == Related methods ==<br /> <br /> == Comments ==</div>

WikiSysop