Conformal inference for reliable single cell RNA-seq annotation

Motivation Despite the inherent complexity associated to automatic cell type assignments, most supervised learning models overlook rigorous uncertainty quantification on the annotations. Although some existing pipelines incorporate rejection options under predefined circumstances, they usually rely...

Descripción completa

Detalles Bibliográficos
Autores: López-De-Castro, M. (Marcos)|||/items/090a2188-2fba-4e3a-9a46-3ba5359be938, García-Galindo, A. (Alberto)|||/items/2e1d5e43-0be6-46e5-9b39-5d52d228eac2, González-Gomariz, J. (José)|||/items/99ec6fe7-0d9d-4d48-938e-6bec841670af, Armañanzas-Arnedillo, R. (Ruben)|||/items/67ce955e-8d9a-44a9-b83a-5b8b81dcbfd6
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Navarra
Repositorio:Dadun. Depósito Académico Digital de la Universidad de Navarra
Idioma:inglés
OAI Identifier:oai:dadun.unav.edu:10171/119757
Acceso en línea:https://hdl.handle.net/10171/119757
Access Level:acceso abierto
Palabra clave:RNA-seq
id ES_ed0cb8232d84beca59d461bbe3b724e7
oai_identifier_str oai:dadun.unav.edu:10171/119757
network_acronym_str ES
network_name_str España
repository_id_str
spelling Conformal inference for reliable single cell RNA-seq annotationLópez-De-Castro, M. (Marcos)|||/items/090a2188-2fba-4e3a-9a46-3ba5359be938García-Galindo, A. (Alberto)|||/items/2e1d5e43-0be6-46e5-9b39-5d52d228eac2González-Gomariz, J. (José)|||/items/99ec6fe7-0d9d-4d48-938e-6bec841670afArmañanzas-Arnedillo, R. (Ruben)|||/items/67ce955e-8d9a-44a9-b83a-5b8b81dcbfd6RNA-seqMotivation Despite the inherent complexity associated to automatic cell type assignments, most supervised learning models overlook rigorous uncertainty quantification on the annotations. Although some existing pipelines incorporate rejection options under predefined circumstances, they usually rely on arbitrary assumptions and do not provide statistical guarantees. In this work, we propose a methodology based on the conformal prediction framework to provide reliable single-cell annotations. Conformal prediction provides statistical guarantees on the outcome predictions without making any assumption about the underlying distribution of the data. Our methodological proposal leverages conformal inference to address two critical challenges in single-cell RNA sequencing annotations: (i) detect out-of-distribution cell types in the query data; and, (ii) perform reliable uncertainty quantification of the cell annotations through well-calibrated prediction sets.Results We evaluated the anomaly detector and the uncertainty-aware annotator in 10 batched experiments derived from various tissues. Specifically, we studied three different annotation taxonomies (standard, classwise, and cluster) alongside three different non-conformity measures. The results showed that our anomaly detector effectively identified previously unseen cell types, producing well-calibrated prediction sets. This rigorous annotation helped maintain coverage probabilities at the expected significance level. Finally, we illustrate how the integration of conformal prediction outputs enhanced further downstream analyses.Availability and implementation The automatic scRNA-seq annotator is available at https://github.com/digital-medicine-research-group-UNAV/conformalized_single_cell_annotator and https://doi.org/10.5281/zenodo.15870599.Dadun. Depósito Académico Digital Universidad de Navarra20252025-01-0120252025-01-01journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10171/119757reponame:Dadun. Depósito Académico Digital de la Universidad de Navarrainstname:Universidad de NavarraInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:dadun.unav.edu:10171/1197572026-06-21T12:47:57Z
dc.title.none.fl_str_mv Conformal inference for reliable single cell RNA-seq annotation
title Conformal inference for reliable single cell RNA-seq annotation
spellingShingle Conformal inference for reliable single cell RNA-seq annotation
López-De-Castro, M. (Marcos)|||/items/090a2188-2fba-4e3a-9a46-3ba5359be938
RNA-seq
title_short Conformal inference for reliable single cell RNA-seq annotation
title_full Conformal inference for reliable single cell RNA-seq annotation
title_fullStr Conformal inference for reliable single cell RNA-seq annotation
title_full_unstemmed Conformal inference for reliable single cell RNA-seq annotation
title_sort Conformal inference for reliable single cell RNA-seq annotation
dc.creator.none.fl_str_mv López-De-Castro, M. (Marcos)|||/items/090a2188-2fba-4e3a-9a46-3ba5359be938
García-Galindo, A. (Alberto)|||/items/2e1d5e43-0be6-46e5-9b39-5d52d228eac2
González-Gomariz, J. (José)|||/items/99ec6fe7-0d9d-4d48-938e-6bec841670af
Armañanzas-Arnedillo, R. (Ruben)|||/items/67ce955e-8d9a-44a9-b83a-5b8b81dcbfd6
author López-De-Castro, M. (Marcos)|||/items/090a2188-2fba-4e3a-9a46-3ba5359be938
author_facet López-De-Castro, M. (Marcos)|||/items/090a2188-2fba-4e3a-9a46-3ba5359be938
García-Galindo, A. (Alberto)|||/items/2e1d5e43-0be6-46e5-9b39-5d52d228eac2
González-Gomariz, J. (José)|||/items/99ec6fe7-0d9d-4d48-938e-6bec841670af
Armañanzas-Arnedillo, R. (Ruben)|||/items/67ce955e-8d9a-44a9-b83a-5b8b81dcbfd6
author_role author
author2 García-Galindo, A. (Alberto)|||/items/2e1d5e43-0be6-46e5-9b39-5d52d228eac2
González-Gomariz, J. (José)|||/items/99ec6fe7-0d9d-4d48-938e-6bec841670af
Armañanzas-Arnedillo, R. (Ruben)|||/items/67ce955e-8d9a-44a9-b83a-5b8b81dcbfd6
author2_role author
author
author
dc.contributor.none.fl_str_mv Dadun. Depósito Académico Digital Universidad de Navarra
dc.subject.none.fl_str_mv RNA-seq
topic RNA-seq
description Motivation Despite the inherent complexity associated to automatic cell type assignments, most supervised learning models overlook rigorous uncertainty quantification on the annotations. Although some existing pipelines incorporate rejection options under predefined circumstances, they usually rely on arbitrary assumptions and do not provide statistical guarantees. In this work, we propose a methodology based on the conformal prediction framework to provide reliable single-cell annotations. Conformal prediction provides statistical guarantees on the outcome predictions without making any assumption about the underlying distribution of the data. Our methodological proposal leverages conformal inference to address two critical challenges in single-cell RNA sequencing annotations: (i) detect out-of-distribution cell types in the query data; and, (ii) perform reliable uncertainty quantification of the cell annotations through well-calibrated prediction sets.Results We evaluated the anomaly detector and the uncertainty-aware annotator in 10 batched experiments derived from various tissues. Specifically, we studied three different annotation taxonomies (standard, classwise, and cluster) alongside three different non-conformity measures. The results showed that our anomaly detector effectively identified previously unseen cell types, producing well-calibrated prediction sets. This rigorous annotation helped maintain coverage probabilities at the expected significance level. Finally, we illustrate how the integration of conformal prediction outputs enhanced further downstream analyses.Availability and implementation The automatic scRNA-seq annotator is available at https://github.com/digital-medicine-research-group-UNAV/conformalized_single_cell_annotator and https://doi.org/10.5281/zenodo.15870599.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-01-01
2025
2025-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10171/119757
url https://hdl.handle.net/10171/119757
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Dadun. Depósito Académico Digital de la Universidad de Navarra
instname:Universidad de Navarra
instname_str Universidad de Navarra
reponame_str Dadun. Depósito Académico Digital de la Universidad de Navarra
collection Dadun. Depósito Académico Digital de la Universidad de Navarra
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423394244526080
score 15,812429

Similares en LA Referencia