Powerful p-value combination methods to detect incomplete association
Abstract Meta-analyses increase statistical power by combining statistics from multiple studies. Meta-analysis methods have mostly been evaluated under the condition that all the data in each study have an association with the given phenotype. However, specific experimental conditions in each study...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/855cb6e277fa4760b73d3ae5f6fd7226 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:855cb6e277fa4760b73d3ae5f6fd7226 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:855cb6e277fa4760b73d3ae5f6fd72262021-12-02T17:04:36ZPowerful p-value combination methods to detect incomplete association10.1038/s41598-021-86465-y2045-2322https://doaj.org/article/855cb6e277fa4760b73d3ae5f6fd72262021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86465-yhttps://doaj.org/toc/2045-2322Abstract Meta-analyses increase statistical power by combining statistics from multiple studies. Meta-analysis methods have mostly been evaluated under the condition that all the data in each study have an association with the given phenotype. However, specific experimental conditions in each study or genetic heterogeneity can result in “unassociated statistics” that are derived from the null distribution. Here, we show that power of conventional meta-analysis methods rapidly decreases as an increasing number of unassociated statistics are included, whereas the classical Fisher’s method and its weighted variant (wFisher) exhibit relatively high power that is robust to addition of unassociated statistics. We also propose another robust method based on joint distribution of ordered p-values (ordmeta). Simulation analyses for t-test, RNA-seq, and microarray data demonstrated that wFisher and ordmeta, when only a small number of studies have an association, outperformed existing meta-analysis methods. We performed meta-analyses of nine microarray datasets (prostate cancer) and four association summary datasets (body mass index), where our methods exhibited high biological relevance and were able to detect genes that the-state-of-the-art methods missed. The metapro R package that implements the proposed methods is available from both CRAN and GitHub ( http://github.com/unistbig/metapro ).Sora YoonBukyung BaikTaesung ParkDougu NamNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Sora Yoon Bukyung Baik Taesung Park Dougu Nam Powerful p-value combination methods to detect incomplete association |
description |
Abstract Meta-analyses increase statistical power by combining statistics from multiple studies. Meta-analysis methods have mostly been evaluated under the condition that all the data in each study have an association with the given phenotype. However, specific experimental conditions in each study or genetic heterogeneity can result in “unassociated statistics” that are derived from the null distribution. Here, we show that power of conventional meta-analysis methods rapidly decreases as an increasing number of unassociated statistics are included, whereas the classical Fisher’s method and its weighted variant (wFisher) exhibit relatively high power that is robust to addition of unassociated statistics. We also propose another robust method based on joint distribution of ordered p-values (ordmeta). Simulation analyses for t-test, RNA-seq, and microarray data demonstrated that wFisher and ordmeta, when only a small number of studies have an association, outperformed existing meta-analysis methods. We performed meta-analyses of nine microarray datasets (prostate cancer) and four association summary datasets (body mass index), where our methods exhibited high biological relevance and were able to detect genes that the-state-of-the-art methods missed. The metapro R package that implements the proposed methods is available from both CRAN and GitHub ( http://github.com/unistbig/metapro ). |
format |
article |
author |
Sora Yoon Bukyung Baik Taesung Park Dougu Nam |
author_facet |
Sora Yoon Bukyung Baik Taesung Park Dougu Nam |
author_sort |
Sora Yoon |
title |
Powerful p-value combination methods to detect incomplete association |
title_short |
Powerful p-value combination methods to detect incomplete association |
title_full |
Powerful p-value combination methods to detect incomplete association |
title_fullStr |
Powerful p-value combination methods to detect incomplete association |
title_full_unstemmed |
Powerful p-value combination methods to detect incomplete association |
title_sort |
powerful p-value combination methods to detect incomplete association |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/855cb6e277fa4760b73d3ae5f6fd7226 |
work_keys_str_mv |
AT sorayoon powerfulpvaluecombinationmethodstodetectincompleteassociation AT bukyungbaik powerfulpvaluecombinationmethodstodetectincompleteassociation AT taesungpark powerfulpvaluecombinationmethodstodetectincompleteassociation AT dougunam powerfulpvaluecombinationmethodstodetectincompleteassociation |
_version_ |
1718381858728706048 |