Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.

<h4>Introduction</h4>Despite continuous efforts, not a single predictor of breast cancer chemotherapy resistance has made it into the clinic yet. However, it has become clear in recent years that breast cancer is a collection of molecularly distinct diseases. With ever increasing amounts...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jorma J de Ronde, Marc Jan Bonder, Esther H Lips, Sjoerd Rodenhuis, Lodewyk F A Wessels
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2014
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d694dcb5c88a486ab2f015e14107d826
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d694dcb5c88a486ab2f015e14107d826
record_format	dspace
spelling	oai:doaj.org-article:d694dcb5c88a486ab2f015e14107d8262021-11-18T08:32:18ZBreast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.1932-620310.1371/journal.pone.0088551https://doaj.org/article/d694dcb5c88a486ab2f015e14107d8262014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24558399/?tool=EBIhttps://doaj.org/toc/1932-6203<h4>Introduction</h4>Despite continuous efforts, not a single predictor of breast cancer chemotherapy resistance has made it into the clinic yet. However, it has become clear in recent years that breast cancer is a collection of molecularly distinct diseases. With ever increasing amounts of breast cancer data becoming available, we set out to study if gene expression based predictors of chemotherapy resistance that are specific for breast cancer subtypes can improve upon the performance of generic predictors.<h4>Methods</h4>We trained predictors of resistance that were specific for a subtype and generic predictors that were not specific for a particular subtype, i.e. trained on all subtypes simultaneously. Through a rigorous double-loop cross-validation we compared the performance of these two types of predictors on the different subtypes on a large set of tumors all profiled on the same expression platform (n = 394). We evaluated predictors based on either mRNA gene expression or clinical features.<h4>Results</h4>For HER2+, ER- breast cancer, subtype specific predictor based on clinical features outperformed the generic, non-specific predictor. This can be explained by the fact that the generic predictor included HER2 and ER status, features that are predictive over the whole set, but not within this subtype. In all other scenarios the generic predictors outperformed the subtype specific predictors or showed equal performance.<h4>Conclusions</h4>Since it depends on the specific context which type of predictor - subtype specific or generic- performed better, it is highly recommended to evaluate both specific and generic predictors when attempting to predict treatment response in breast cancer.Jorma J de RondeMarc Jan BonderEsther H LipsSjoerd RodenhuisLodewyk F A WesselsPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 2, p e88551 (2014)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jorma J de Ronde Marc Jan Bonder Esther H Lips Sjoerd Rodenhuis Lodewyk F A Wessels Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.
description	<h4>Introduction</h4>Despite continuous efforts, not a single predictor of breast cancer chemotherapy resistance has made it into the clinic yet. However, it has become clear in recent years that breast cancer is a collection of molecularly distinct diseases. With ever increasing amounts of breast cancer data becoming available, we set out to study if gene expression based predictors of chemotherapy resistance that are specific for breast cancer subtypes can improve upon the performance of generic predictors.<h4>Methods</h4>We trained predictors of resistance that were specific for a subtype and generic predictors that were not specific for a particular subtype, i.e. trained on all subtypes simultaneously. Through a rigorous double-loop cross-validation we compared the performance of these two types of predictors on the different subtypes on a large set of tumors all profiled on the same expression platform (n = 394). We evaluated predictors based on either mRNA gene expression or clinical features.<h4>Results</h4>For HER2+, ER- breast cancer, subtype specific predictor based on clinical features outperformed the generic, non-specific predictor. This can be explained by the fact that the generic predictor included HER2 and ER status, features that are predictive over the whole set, but not within this subtype. In all other scenarios the generic predictors outperformed the subtype specific predictors or showed equal performance.<h4>Conclusions</h4>Since it depends on the specific context which type of predictor - subtype specific or generic- performed better, it is highly recommended to evaluate both specific and generic predictors when attempting to predict treatment response in breast cancer.
format	article
author	Jorma J de Ronde Marc Jan Bonder Esther H Lips Sjoerd Rodenhuis Lodewyk F A Wessels
author_facet	Jorma J de Ronde Marc Jan Bonder Esther H Lips Sjoerd Rodenhuis Lodewyk F A Wessels
author_sort	Jorma J de Ronde
title	Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.
title_short	Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.
title_full	Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.
title_fullStr	Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.
title_full_unstemmed	Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.
title_sort	breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.
publisher	Public Library of Science (PLoS)
publishDate	2014
url	https://doaj.org/article/d694dcb5c88a486ab2f015e14107d826
work_keys_str_mv	AT jormajderonde breastcancersubtypespecificclassifiersofresponsetoneoadjuvantchemotherapydonotoutperformclassifierstrainedonallsubtypes AT marcjanbonder breastcancersubtypespecificclassifiersofresponsetoneoadjuvantchemotherapydonotoutperformclassifierstrainedonallsubtypes AT estherhlips breastcancersubtypespecificclassifiersofresponsetoneoadjuvantchemotherapydonotoutperformclassifierstrainedonallsubtypes AT sjoerdrodenhuis breastcancersubtypespecificclassifiersofresponsetoneoadjuvantchemotherapydonotoutperformclassifierstrainedonallsubtypes AT lodewykfawessels breastcancersubtypespecificclassifiersofresponsetoneoadjuvantchemotherapydonotoutperformclassifierstrainedonallsubtypes
_version_	1718421711637970944

Breast cancer subtype specific classifiers of response to neoadjuvant chemotherapy do not outperform classifiers trained on all subtypes.

Ejemplares similares