Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction

Abstract Breast cancer is a heterogeneous disease. To guide proper treatment decisions for each patient, robust prognostic biomarkers, which allow reliable prognosis prediction, are necessary. Gene feature selection based on microarray data is an approach to discover potential biomarkers systematica...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Li-Hsin Cheng, Te-Cheng Hsu, Che Lin
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c621b24dda584dbca72cb509d4970b73
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c621b24dda584dbca72cb509d4970b73
record_format	dspace
spelling	oai:doaj.org-article:c621b24dda584dbca72cb509d4970b732021-12-02T16:50:23ZIntegrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction10.1038/s41598-021-92864-y2045-2322https://doaj.org/article/c621b24dda584dbca72cb509d4970b732021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-92864-yhttps://doaj.org/toc/2045-2322Abstract Breast cancer is a heterogeneous disease. To guide proper treatment decisions for each patient, robust prognostic biomarkers, which allow reliable prognosis prediction, are necessary. Gene feature selection based on microarray data is an approach to discover potential biomarkers systematically. However, standard pure-statistical feature selection approaches often fail to incorporate prior biological knowledge and select genes that lack biological insights. Besides, due to the high dimensionality and low sample size properties of microarray data, selecting robust gene features is an intrinsically challenging problem. We hence combined systems biology feature selection with ensemble learning in this study, aiming to select genes with biological insights and robust prognostic predictive power. Moreover, to capture breast cancer's complex molecular processes, we adopted a multi-gene approach to predict the prognosis status using deep learning classifiers. We found that all ensemble approaches could improve feature selection robustness, wherein the hybrid ensemble approach led to the most robust result. Among all prognosis prediction models, the bimodal deep neural network (DNN) achieved the highest test performance, further verified by survival analysis. In summary, this study demonstrated the potential of combining ensemble learning and bimodal DNN in guiding precision medicine.Li-Hsin ChengTe-Cheng HsuChe LinNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Li-Hsin Cheng Te-Cheng Hsu Che Lin Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
description	Abstract Breast cancer is a heterogeneous disease. To guide proper treatment decisions for each patient, robust prognostic biomarkers, which allow reliable prognosis prediction, are necessary. Gene feature selection based on microarray data is an approach to discover potential biomarkers systematically. However, standard pure-statistical feature selection approaches often fail to incorporate prior biological knowledge and select genes that lack biological insights. Besides, due to the high dimensionality and low sample size properties of microarray data, selecting robust gene features is an intrinsically challenging problem. We hence combined systems biology feature selection with ensemble learning in this study, aiming to select genes with biological insights and robust prognostic predictive power. Moreover, to capture breast cancer's complex molecular processes, we adopted a multi-gene approach to predict the prognosis status using deep learning classifiers. We found that all ensemble approaches could improve feature selection robustness, wherein the hybrid ensemble approach led to the most robust result. Among all prognosis prediction models, the bimodal deep neural network (DNN) achieved the highest test performance, further verified by survival analysis. In summary, this study demonstrated the potential of combining ensemble learning and bimodal DNN in guiding precision medicine.
format	article
author	Li-Hsin Cheng Te-Cheng Hsu Che Lin
author_facet	Li-Hsin Cheng Te-Cheng Hsu Che Lin
author_sort	Li-Hsin Cheng
title	Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
title_short	Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
title_full	Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
title_fullStr	Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
title_full_unstemmed	Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
title_sort	integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/c621b24dda584dbca72cb509d4970b73
work_keys_str_mv	AT lihsincheng integratingensemblesystemsbiologyfeatureselectionandbimodaldeepneuralnetworkforbreastcancerprognosisprediction AT techenghsu integratingensemblesystemsbiologyfeatureselectionandbimodaldeepneuralnetworkforbreastcancerprognosisprediction AT chelin integratingensemblesystemsbiologyfeatureselectionandbimodaldeepneuralnetworkforbreastcancerprognosisprediction
_version_	1718383065055625216

Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction

Ejemplares similares