TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms

Cryo-electron tomography is a rapidly developing field for studying macromolecular complexes in their native environments and has the potential to revolutionize our understanding of protein function. However, fast and accurate identification of particles in cryo-tomograms is challenging and represen...

ver descrição completa

Detalhes bibliográficos
Autores: Shah, Pranav, Sánchez García, Ruben, Stuart, David
Tipo de documento: artigo
Data de publicação:2025
País:España
Recursos:IE
Repositório:Repositorio IE
OAI Identifier:oai:repositorio.ie.edu:20.500.14417/4224
Acesso em linha:https://doi.org/10.1107/S2059798325000865
https://hdl.handle.net/20.500.14417/4224
https://journals.iucr.org/d/issues/2025/02/00/sor5001/index.html
Access Level:Acceso aberto
Palavra-chave:24 Ciencias de la Vida::2406 Biofísica
ODS 3 - Salud y bienestar
ODS 9 - Industria, innovación e infraestructura
cryo-ET
particle picking
subtomogram averaging.
id ES_e075da6156eeb16e9caf9ecd2eabcae1
oai_identifier_str oai:repositorio.ie.edu:20.500.14417/4224
network_acronym_str ES
network_name_str España
repository_id_str
spelling TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomogramsShah, PranavSánchez García, RubenStuart, David24 Ciencias de la Vida::2406 BiofísicaODS 3 - Salud y bienestarODS 9 - Industria, innovación e infraestructuracryo-ETparticle pickingsubtomogram averaging.Cryo-electron tomography is a rapidly developing field for studying macromolecular complexes in their native environments and has the potential to revolutionize our understanding of protein function. However, fast and accurate identification of particles in cryo-tomograms is challenging and represents a significant bottleneck in downstream processes such as subtomogram averaging. Here, we present tomoCPT (Tomogram Centroid Prediction Tool), a transformer-based solution that reformulates particle detection as a centroid-prediction task using Gaussian labels. Our approach, which is built upon the SwinUNETR architecture, demonstrates superior performance compared with both conventional binary labelling strategies and template matching. We show that tomoCPT effectively generalizes to novel particle types through zero-shot inference and can be significantly enhanced through fine-tuning with limited data. The efficacy of tomoCPT is validated using three case studies: apoferritin, achieving a resolution of 3.0 Å compared with 3.3 Å using template matching, SARS-CoV-2 spike proteins on cell surfaces, yielding an 18.3 Å resolution map where template matching proved unsuccessful, and rubisco molecules within carboxysomes, reaching 8.0 Å resolution. These results demonstrate the ability of tomoCPT to handle varied scenarios, including densely packed environments and membrane-bound proteins. The implementation of the tool as a command-line program, coupled with its minimal data requirements for fine-tuning, makes it a practical solution for high-throughput cryo-ET data-processing workflows.Computation used the Oxford Biomedical Research Computing (BMRC) facility, a joint development between the Centre for Human Genetics and the Big Data Institute supported by Health Data Research UK and the National Institute for Health (NIHR) Oxford Biomedical Research Centre. Financial support was provided by the Wellcome Trust Core Award Grant No. 03141/Z/16/Z. The OPIC electron microscopy facility was founded by a Wellcome Trust JIF award (060208/Z/00/Z). This work was supported by the UK Medical Research Council grant to DIS (MR/N00065X/1).YesPublishedInternational Union of CrystallographyUK Medical Research CouncilWellcome Trusthttps://ror.org/02jjdwm7520262025info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://doi.org/10.1107/S2059798325000865https://hdl.handle.net/20.500.14417/4224https://journals.iucr.org/d/issues/2025/02/00/sor5001/index.htmlreponame:Repositorio IEinstname:IEInglésIE School of Science & TechnologyMR/N00065X/103141/Z/16/Z060208/Z/00/ZIE UniversitySci Tech (Data Science)Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositorio.ie.edu:20.500.14417/42242026-06-15T12:40:57Z
dc.title.none.fl_str_mv TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
title TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
spellingShingle TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
Shah, Pranav
24 Ciencias de la Vida::2406 Biofísica
ODS 3 - Salud y bienestar
ODS 9 - Industria, innovación e infraestructura
cryo-ET
particle picking
subtomogram averaging.
title_short TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
title_full TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
title_fullStr TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
title_full_unstemmed TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
title_sort TomoCPT: a generalizable model for 3D particle detection and localization in cryo-electron tomograms
dc.creator.none.fl_str_mv Shah, Pranav
Sánchez García, Ruben
Stuart, David
author Shah, Pranav
author_facet Shah, Pranav
Sánchez García, Ruben
Stuart, David
author_role author
author2 Sánchez García, Ruben
Stuart, David
author2_role author
author
dc.contributor.none.fl_str_mv UK Medical Research Council
Wellcome Trust
https://ror.org/02jjdwm75
dc.subject.none.fl_str_mv 24 Ciencias de la Vida::2406 Biofísica
ODS 3 - Salud y bienestar
ODS 9 - Industria, innovación e infraestructura
cryo-ET
particle picking
subtomogram averaging.
topic 24 Ciencias de la Vida::2406 Biofísica
ODS 3 - Salud y bienestar
ODS 9 - Industria, innovación e infraestructura
cryo-ET
particle picking
subtomogram averaging.
description Cryo-electron tomography is a rapidly developing field for studying macromolecular complexes in their native environments and has the potential to revolutionize our understanding of protein function. However, fast and accurate identification of particles in cryo-tomograms is challenging and represents a significant bottleneck in downstream processes such as subtomogram averaging. Here, we present tomoCPT (Tomogram Centroid Prediction Tool), a transformer-based solution that reformulates particle detection as a centroid-prediction task using Gaussian labels. Our approach, which is built upon the SwinUNETR architecture, demonstrates superior performance compared with both conventional binary labelling strategies and template matching. We show that tomoCPT effectively generalizes to novel particle types through zero-shot inference and can be significantly enhanced through fine-tuning with limited data. The efficacy of tomoCPT is validated using three case studies: apoferritin, achieving a resolution of 3.0 Å compared with 3.3 Å using template matching, SARS-CoV-2 spike proteins on cell surfaces, yielding an 18.3 Å resolution map where template matching proved unsuccessful, and rubisco molecules within carboxysomes, reaching 8.0 Å resolution. These results demonstrate the ability of tomoCPT to handle varied scenarios, including densely packed environments and membrane-bound proteins. The implementation of the tool as a command-line program, coupled with its minimal data requirements for fine-tuning, makes it a practical solution for high-throughput cryo-ET data-processing workflows.
publishDate 2025
dc.date.none.fl_str_mv 2025
2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://doi.org/10.1107/S2059798325000865
https://hdl.handle.net/20.500.14417/4224
https://journals.iucr.org/d/issues/2025/02/00/sor5001/index.html
url https://doi.org/10.1107/S2059798325000865
https://hdl.handle.net/20.500.14417/4224
https://journals.iucr.org/d/issues/2025/02/00/sor5001/index.html
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv IE School of Science & Technology
MR/N00065X/1
03141/Z/16/Z
060208/Z/00/Z
IE University
Sci Tech (Data Science)
dc.rights.none.fl_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv International Union of Crystallography
publisher.none.fl_str_mv International Union of Crystallography
dc.source.none.fl_str_mv reponame:Repositorio IE
instname:IE
instname_str IE
reponame_str Repositorio IE
collection Repositorio IE
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422204438970368
score 15,81155

Registros relacionados