logo
ResearchBunny Logo
TomoTwin: generalized 3D localization of macromolecules in cryo-electron tomograms with structural data mining

Biology

TomoTwin: generalized 3D localization of macromolecules in cryo-electron tomograms with structural data mining

G. Rice, T. Wagner, et al.

Discover how Gavin Rice and colleagues have revolutionized cryogenic-electron tomography with TomoTwin, a cutting-edge deep metric learning model that accurately localizes macromolecules in complex cellular environments without the need for manual data training. This breakthrough enables de novo protein identification, making analysis of densely packed tomograms more efficient and reliable.

00:00
00:00
Playback language: English
Abstract
Cryogenic-electron tomography (cryo-ET) offers detailed visualization of cellular environments, but analyzing the vast information within densely packed volumes remains challenging. Accurate macromolecule localization for subtomogram averaging (STA) is crucial but hindered by low signal-to-noise ratios and crowding. Existing methods are either error-prone or require manual training data annotation. TomoTwin, an open-source deep metric learning model, addresses this by embedding tomograms in a high-dimensional space that separates macromolecules based on their 3D structure. This allows de novo protein identification without manual training data or retraining for new proteins.
Publisher
Nature Methods
Published On
May 15, 2023
Authors
Gavin Rice, Thorsten Wagner, Markus Stabrin, Oleg Sitsel, Daniel Prumbaum, Stefan Raunser
Tags
Cryogenic-electron tomography
Deep metric learning
TomoTwin
Subtomogram averaging
Protein identification
Macromolecule localization
3D structure

Related Publications

Explore these studies to deepen your understanding of the subject.

Application of deep learning algorithm on whole genome sequencing data uncovers structural variants associated with multiple mental disorders in African American patients
Medicine and Health

Application of deep learning algorithm on whole genome sequencing data uncovers structural variants associated with multiple mental disorders in African American patients

Y. Liu, H. Qu, et al.

Validity of Scottish predictors of child obesity (age 12) for risk screening in mid-childhood: a secondary analysis of prospective cohort study data—with sensitivity analyses for settings without various routinely collected predictor variables
Medicine and Health

Validity of Scottish predictors of child obesity (age 12) for risk screening in mid-childhood: a secondary analysis of prospective cohort study data—with sensitivity analyses for settings without various routinely collected predictor variables

G. Carrillo-balam, L. Doi, et al.

How the crisis of trust in experts occurs on social media in China? Multiple-case analysis based on data mining
Social Work

How the crisis of trust in experts occurs on social media in China? Multiple-case analysis based on data mining

Y. Wen, X. Zhao, et al.

Measuring the impact of enterprise risk management on performance, value, and risk indicators of Borsa Istanbul XBANK companies with data mining prediction models
Business

Measuring the impact of enterprise risk management on performance, value, and risk indicators of Borsa Istanbul XBANK companies with data mining prediction models

M. Ç. Akbaş

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny