Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning

Motivation: The Cox proportional hazard models are widely used in the study of cancer survival. However, these models often meet challenges such as the large number of features and small sample sizes of cancer data sets. While this issue can be partially solved by applying regularization techniques...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gabriela Malenová, Daniel Rowson, Valentina Boeva
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	survival analysis Cox model cancer lasso group lasso multi-task Genetics QH426-470
Acceso en línea:	https://doaj.org/article/b971f490aafb41a4b477f53f7a465abd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b971f490aafb41a4b477f53f7a465abd
record_format	dspace
spelling	oai:doaj.org-article:b971f490aafb41a4b477f53f7a465abd2021-12-01T13:44:47ZExploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning1664-802110.3389/fgene.2021.771301https://doaj.org/article/b971f490aafb41a4b477f53f7a465abd2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fgene.2021.771301/fullhttps://doaj.org/toc/1664-8021Motivation: The Cox proportional hazard models are widely used in the study of cancer survival. However, these models often meet challenges such as the large number of features and small sample sizes of cancer data sets. While this issue can be partially solved by applying regularization techniques such as lasso, the models still suffer from unsatisfactory predictive power and low stability.Methods: Here, we investigated two methods to improve survival models. Firstly, we leveraged the biological knowledge that groups of genes act together in pathways and regularized both at the group and gene level using latent group lasso penalty term. Secondly, we designed and applied a multi-task learning penalty that allowed us leveraging the relationship between survival models for different cancers.Results: We observed modest improvements over the simple lasso model with the inclusion of latent group lasso penalty for six of the 16 cancer types tested. The addition of a multi-task penalty, which penalized coefficients in pairs of cancers from diverging too greatly, significantly improved accuracy for a single cancer, lung squamous cell carcinoma, while having minimal effect on other cancer types.Conclusion: While the use of pathway information and multi-tasking shows some promise, these methods do not provide a substantial improvement when compared with standard methods.Gabriela MalenováDaniel RowsonValentina BoevaValentina BoevaValentina BoevaFrontiers Media S.A.articlesurvival analysisCox modelcancerlassogroup lassomulti-taskGeneticsQH426-470ENFrontiers in Genetics, Vol 12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	survival analysis Cox model cancer lasso group lasso multi-task Genetics QH426-470
spellingShingle	survival analysis Cox model cancer lasso group lasso multi-task Genetics QH426-470 Gabriela Malenová Daniel Rowson Valentina Boeva Valentina Boeva Valentina Boeva Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning
description	Motivation: The Cox proportional hazard models are widely used in the study of cancer survival. However, these models often meet challenges such as the large number of features and small sample sizes of cancer data sets. While this issue can be partially solved by applying regularization techniques such as lasso, the models still suffer from unsatisfactory predictive power and low stability.Methods: Here, we investigated two methods to improve survival models. Firstly, we leveraged the biological knowledge that groups of genes act together in pathways and regularized both at the group and gene level using latent group lasso penalty term. Secondly, we designed and applied a multi-task learning penalty that allowed us leveraging the relationship between survival models for different cancers.Results: We observed modest improvements over the simple lasso model with the inclusion of latent group lasso penalty for six of the 16 cancer types tested. The addition of a multi-task penalty, which penalized coefficients in pairs of cancers from diverging too greatly, significantly improved accuracy for a single cancer, lung squamous cell carcinoma, while having minimal effect on other cancer types.Conclusion: While the use of pathway information and multi-tasking shows some promise, these methods do not provide a substantial improvement when compared with standard methods.
format	article
author	Gabriela Malenová Daniel Rowson Valentina Boeva Valentina Boeva Valentina Boeva
author_facet	Gabriela Malenová Daniel Rowson Valentina Boeva Valentina Boeva Valentina Boeva
author_sort	Gabriela Malenová
title	Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning
title_short	Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning
title_full	Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning
title_fullStr	Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning
title_full_unstemmed	Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning
title_sort	exploring pathway-based group lasso for cancer survival analysis: a special case of multi-task learning
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/b971f490aafb41a4b477f53f7a465abd
work_keys_str_mv	AT gabrielamalenova exploringpathwaybasedgrouplassoforcancersurvivalanalysisaspecialcaseofmultitasklearning AT danielrowson exploringpathwaybasedgrouplassoforcancersurvivalanalysisaspecialcaseofmultitasklearning AT valentinaboeva exploringpathwaybasedgrouplassoforcancersurvivalanalysisaspecialcaseofmultitasklearning AT valentinaboeva exploringpathwaybasedgrouplassoforcancersurvivalanalysisaspecialcaseofmultitasklearning AT valentinaboeva exploringpathwaybasedgrouplassoforcancersurvivalanalysisaspecialcaseofmultitasklearning
_version_	1718405135957229568

Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning

Ejemplares similares