A powerful FDR control procedure for multiple hypotheses

Zhao, Haibing; Fung, Wing K.

doi:10.1016/j.csda.2015.12.013

Cited by 5 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CHiCAGO’s multiple testing procedure is based on the p value weighting approach by Genovese et al [ 15 ], which is a generalisation of a segment-wise weighting procedure by Sun et al [ 32 ]. These approaches have been used successfully to incorporate prior knowledge in GWAS [ 33 – 35 ] and are emerging in functional genomics analyses [ 36 , 37 ]. In using the reproducibility of significant calls across replicates as an estimate of the relative true positive rate, we have taken inspiration from the irreproducible discovery rate (IDR) approach [ 38 ] used to determine peak signal thresholds in other types of genomics data, such as ChIP-seq.…”

Section: Discussionmentioning

confidence: 99%

CHiCAGO: robust detection of DNA looping interactions in Capture Hi-C data

et al. 2016

View full text Add to dashboard Cite

Capture Hi-C (CHi-C) is a method for profiling chromosomal interactions involving targeted regions of interest, such as gene promoters, globally and at high resolution. Signal detection in CHi-C data involves a number of statistical challenges that are not observed when using other Hi-C-like techniques. We present a background model and algorithms for normalisation and multiple testing that are specifically adapted to CHi-C experiments. We implement these procedures in CHiCAGO (http://regulatorygenomicsgroup.org/chicago), an open-source package for robust interaction detection in CHi-C. We validate CHiCAGO by showing that promoter-interacting regions detected with this method are enriched for regulatory features and disease-associated SNPs.Electronic supplementary materialThe online version of this article (doi:10.1186/s13059-016-0992-2) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

CHiCAGO: robust detection of DNA looping interactions in Capture Hi-C data

et al. 2016

View full text Add to dashboard Cite

show abstract

“…CHiCAGO's multiple testing procedure is based on the p-value weighting approach by Genovese et al [15], which is a generalisation of a segment-wise weighting procedure by Sun et al [37]. These approaches have been used successfully to incorporate prior knowledge in genome-wide association studies [38][39][40] and are emerging in functional genomics analyses [41,42]. In using the reproducibility of significant calls across replicates as an estimate of the relative true positive rate, we have taken inspiration from the irreproducible discovery rate (IDR) approach [43] used to determine peak signal thresholds in other types of genomics data, such as ChIPseq.…”

Section: Discussionmentioning

confidence: 99%

CHiCAGO: Robust Detection of DNA Looping Interactions in Capture Hi-C data

Cairns

Freire-Pritchett

Wingett

et al. 2015

Preprint

128

View full text Add to dashboard Cite

show abstract

“…a z ‐score), and the non‐nulls are more likely to have positive means than negative (or vice versa), then taking this into account in the adaptive procedure will increase power. Zhao and Fung () allowed for this asymmetry by giving distinct weights to p ‐values that are associated with positive versus negative statistics, specifically, by estimating

{\overset{false^}{π}}_{0}^{+}

and

{\overset{false^}{π}}_{0}^{-}

, the proportion of nulls among hypotheses with positive or negative z ‐scores respectively. More generally, Sun and Cai () studied oracle decision rules for discovering signals, and found that using z ‐scores (i.e.…”

Section: Background: Multiple Testing and False Discovery Rate Controlmentioning

confidence: 99%

Multiple Testing with the Structure-Adaptive Benjamini–Hochberg Algorithm

Barber

2018

Journal of the Royal Statistical Society Series B: Statistical Methodology

122

156

View full text Add to dashboard Cite

Summary In multiple‐testing problems, where a large number of hypotheses are tested simultaneously, false discovery rate (FDR) control can be achieved with the well‐known Benjamini–Hochberg procedure, which a(0,1]dapts to the amount of signal in the data, under certain distributional assumptions. Many modifications of this procedure have been proposed to improve power in scenarios where the hypotheses are organized into groups or into a hierarchy, as well as other structured settings. Here we introduce the ‘structure‐adaptive Benjamini–Hochberg algorithm’ (SABHA) as a generalization of these adaptive testing methods. The SABHA method incorporates prior information about any predetermined type of structure in the pattern of locations of the signals and nulls within the list of hypotheses, to reweight the p‐values in a data‐adaptive way. This raises the power by making more discoveries in regions where signals appear to be more common. Our main theoretical result proves that the SABHA method controls the FDR at a level that is at most slightly higher than the target FDR level, as long as the adaptive weights are constrained sufficiently so as not to overfit too much to the data—interestingly, the excess FDR can be related to the Rademacher complexity or Gaussian width of the class from which we choose our data‐adaptive weights. We apply this general framework to various structured settings, including ordered, grouped and low total variation structures, and obtain the bounds on the FDR for each specific setting. We also examine the empirical performance of the SABHA method on functional magnetic resonance imaging activity data and on gene–drug response data, as well as on simulated data.

show abstract

A powerful FDR control procedure for multiple hypotheses

Cited by 5 publications

References 26 publications

CHiCAGO: robust detection of DNA looping interactions in Capture Hi-C data

CHiCAGO: robust detection of DNA looping interactions in Capture Hi-C data

CHiCAGO: Robust Detection of DNA Looping Interactions in Capture Hi-C data

Multiple Testing with the Structure-Adaptive Benjamini–Hochberg Algorithm

Contact Info

Product

Resources

About