Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data

Abstract Background Multiple testing of composite null hypotheses is critical for identifying simultaneous signals across studies. While it is common to incorporate external information in simple null hypotheses, exploiting such auxiliary covariates to provide prior structural relationships among co...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Li, Yanmei Li, Han Ma, Zitong Yue, Xin Zhang
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-025-06163-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238397469589504
author Yan Li
Yanmei Li
Han Ma
Zitong Yue
Xin Zhang
author_facet Yan Li
Yanmei Li
Han Ma
Zitong Yue
Xin Zhang
author_sort Yan Li
collection DOAJ
description Abstract Background Multiple testing of composite null hypotheses is critical for identifying simultaneous signals across studies. While it is common to incorporate external information in simple null hypotheses, exploiting such auxiliary covariates to provide prior structural relationships among composite null hypotheses and boost the statistical power remains challenging. Results We propose a robust and powerful covariate-assisted composite null hypothesis testing (CoCoNuT) procedure based on a Bayesian framework to identify replicable signals in two studies while asymptotically controlling the false discovery rate. CoCoNuT innovatively adopts a three-dimensional mixture model to consider two primary studies and an integrative auxiliary covariate jointly. While accounting for heterogeneity across studies, the local false discovery rate optimally captures cross-study and cross-feature information, providing improved rankings of feature importance. Conclusions Theoretical and empirical evaluations confirm the validity and efficiency of CoCoNuT. Extensive simulations demonstrate that CoCoNuT outperforms conventional methods that do not exploit auxiliary covariates while controlling the FDR. We apply CoCoNuT to schizophrenia genome-wide association studies, illustrating its higher power in identifying replicable genetic variants with the assistance of relevant auxiliary studies.
format Article
id doaj-art-a95ca933628e44489cd99cf1766e9676
institution Kabale University
issn 1471-2105
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-a95ca933628e44489cd99cf1766e96762025-08-20T04:01:36ZengBMCBMC Bioinformatics1471-21052025-07-0126111810.1186/s12859-025-06163-8Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental dataYan Li0Yanmei Li1Han Ma2Zitong Yue3Xin Zhang4School of Computer Science and Technology, Changchun University of Science and TechnologySchool of Computer Science and Technology, Changchun University of Science and TechnologySchool of Computer Science and Technology, Changchun University of Science and TechnologySchool of Business, Hong Kong University of Science and TechnologySchool of Computer Science and Technology, Changchun University of Science and TechnologyAbstract Background Multiple testing of composite null hypotheses is critical for identifying simultaneous signals across studies. While it is common to incorporate external information in simple null hypotheses, exploiting such auxiliary covariates to provide prior structural relationships among composite null hypotheses and boost the statistical power remains challenging. Results We propose a robust and powerful covariate-assisted composite null hypothesis testing (CoCoNuT) procedure based on a Bayesian framework to identify replicable signals in two studies while asymptotically controlling the false discovery rate. CoCoNuT innovatively adopts a three-dimensional mixture model to consider two primary studies and an integrative auxiliary covariate jointly. While accounting for heterogeneity across studies, the local false discovery rate optimally captures cross-study and cross-feature information, providing improved rankings of feature importance. Conclusions Theoretical and empirical evaluations confirm the validity and efficiency of CoCoNuT. Extensive simulations demonstrate that CoCoNuT outperforms conventional methods that do not exploit auxiliary covariates while controlling the FDR. We apply CoCoNuT to schizophrenia genome-wide association studies, illustrating its higher power in identifying replicable genetic variants with the assistance of relevant auxiliary studies.https://doi.org/10.1186/s12859-025-06163-8Composite null hypothesisAuxiliary informationReplicabilityHigh-throughput experimentsCauchy combination
spellingShingle Yan Li
Yanmei Li
Han Ma
Zitong Yue
Xin Zhang
Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data
BMC Bioinformatics
Composite null hypothesis
Auxiliary information
Replicability
High-throughput experiments
Cauchy combination
title Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data
title_full Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data
title_fullStr Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data
title_full_unstemmed Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data
title_short Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data
title_sort coconut covariate assisted composite null hypothesis testing with applications to replicability analysis of high throughput experimental data
topic Composite null hypothesis
Auxiliary information
Replicability
High-throughput experiments
Cauchy combination
url https://doi.org/10.1186/s12859-025-06163-8
work_keys_str_mv AT yanli coconutcovariateassistedcompositenullhypothesistestingwithapplicationstoreplicabilityanalysisofhighthroughputexperimentaldata
AT yanmeili coconutcovariateassistedcompositenullhypothesistestingwithapplicationstoreplicabilityanalysisofhighthroughputexperimentaldata
AT hanma coconutcovariateassistedcompositenullhypothesistestingwithapplicationstoreplicabilityanalysisofhighthroughputexperimentaldata
AT zitongyue coconutcovariateassistedcompositenullhypothesistestingwithapplicationstoreplicabilityanalysisofhighthroughputexperimentaldata
AT xinzhang coconutcovariateassistedcompositenullhypothesistestingwithapplicationstoreplicabilityanalysisofhighthroughputexperimentaldata