False Discovery Control Research Articles

Taxanorm: a novel taxa-specific normalization approach for microbiome data

BackgroundIn high-throughput sequencing studies, sequencing depth, which quantifies the total number of reads, varies across samples. Unequal sequencing depth can obscure true biological signals of interest and prevent direct comparisons between samples. To remove variability due to differential sequencing depth, taxa counts are usually normalized before downstream analysis. However, most existing normalization methods scale counts using size factors that are sample specific but not taxa specific, which can result in over- or under-correction for some taxa.ResultsWe developed TaxaNorm, a novel normalization method based on a zero-inflated negative binomial model. This method assumes the effects of sequencing depth on mean and dispersion vary across taxa. Incorporating the zero-inflation part can better capture the nature of microbiome data. We also propose two corresponding diagnosis tests on the varying sequencing depth effect for validation. We find that TaxaNorm achieves comparable performance to existing methods in most simulation scenarios in downstream analysis and reaches a higher power for some cases. Specifically, it balances power and false discovery control well. When applying the method in a real dataset, TaxaNorm has improved performance when correcting technical bias.ConclusionTaxaNorm both sample- and taxon- specific bias by introducing an appropriate regression framework in the microbiome data, which aids in data interpretation and visualization. The ‘TaxaNorm’ R package is freely available through the CRAN repository https://CRAN.R-project.org/package=TaxaNorm and the source code can be downloaded at https://github.com/wangziyue57/TaxaNorm.

Reinvestigating the Correctness of Decoy-Based False Discovery Rate Control in Proteomics Tandem Mass Spectrometry.

Traditional database search methods for the analysis of bottom-up proteomics tandem mass spectrometry (MS/MS) data are limited in their ability to detect peptides with post-translational modifications (PTMs). Recently, "open modification" database search strategies, in which the requirement that the mass of the database peptide closely matches the observed precursor mass is relaxed, have become popular as ways to find a wider variety of types of PTMs. Indeed, in one study, Kong et al. reported that the open modification search tool MSFragger can achieve higher statistical power to detect peptides than a traditional "narrow window" database search. We investigated this claim empirically and, in the process, uncovered a potential general problem with false discovery rate (FDR) control in the machine learning postprocessors Percolator and PeptideProphet. This problem might have contributed to Kong et al.'s report that their empirical results suggest that false discovery (FDR) control in the narrow window setting might generally be compromised. Indeed, reanalyzing the same data while using a more standard form of target-decoy competition-based FDR control, we found that, after accounting for chimeric spectra as well as for the inherent difference in the number of candidates in open and narrow searches, the data does not provide sufficient evidence that FDR control in proteomics MS/MS database search is inherently problematic.

Control of false discoveries in grouped hypothesis testing for eQTL data

BackgroundExpression quantitative trait locus (eQTL) analysis aims to detect the genetic variants that influence the expression of one or more genes. Gene-level eQTL testing forms a natural grouped-hypothesis testing strategy with clear biological importance. Methods to control family-wise error rate or false discovery rate for group testing have been proposed earlier, but may not be powerful or easily apply to eQTL data, for which certain structured alternatives may be defensible and may enable the researcher to avoid overly conservative approaches.ResultsIn an empirical Bayesian setting, we propose a new method to control the false discovery rate (FDR) for grouped hypotheses. Here, each gene forms a group, with SNPs annotated to the gene corresponding to individual hypotheses. The heterogeneity of effect sizes in different groups is considered by the introduction of a random effects component. Our method, entitled Random Effects model and testing procedure for Group-level FDR control (REG-FDR), assumes a model for alternative hypotheses for the eQTL data and controls the FDR by adaptive thresholding. As a convenient alternate approach, we also propose Z-REG-FDR, an approximate version of REG-FDR, that uses only Z-statistics of association between genotype and expression for each gene-SNP pair. The performance of Z-REG-FDR is evaluated using both simulated and real data. Simulations demonstrate that Z-REG-FDR performs similarly to REG-FDR, but with much improved computational speed.ConclusionOur results demonstrate that the Z-REG-FDR method performs favorably compared to other methods in terms of statistical power and control of FDR. It can be of great practical use for grouped hypothesis testing for eQTL analysis or similar problems in statistical genomics due to its fast computation and ability to be fit using only summary data.

Diffusion MRI correlation with p16 status and prediction for tumor progression in locally advanced head and neck cancer.

To investigate p16 effects on diffusion image metrics and associations with tumor progression in patients with locally advanced head and neck cancers. Diffusion images pretreatment and after 20 Gy (2wk) of RT were analyzed in patients with cT4/N3 p16+ oropharynx cancer (OPSCC) (N=51) and locoregionally advanced head and neck squamous cell carcinoma (LAHNSCC) (N=28), enrolled onto a prospective adaptive RT trial. Mean ADC values, subvolumes with ADC <1.2 um2/ms (TVLADC), and peak values of low (µL) and high (µH) components of ADC histograms in primary and total nodal gross tumor volumes were analyzed for prediction of freedom from local, distant, or any progression (FFLP, FFDP or FFLRDP) using multivariate Cox proportional-hazards model with clinical factors. P value with false discovery control <0.05 was considered as significant. With a mean follow up of 36 months, 18 of LAHNSCC patients and 16 of p16+ OPSCC patients had progression. After adjusting for p16, small µL and ADC values, and large TVLADC of primary tumors pre-RT were significantly associated with superior FFLRDP, FFLP and FFDP in the LAHNSCC (p<0.05), but no diffusion metrics were significant in p16+ oropharynx cancers. Post ad hoc analysis of the p16+ OPSCC only showed that large TVLADC of the total nodal burden pre-RT was significantly associated with inferior FFDP (p=0.05). ADC metrics were associated with different progression patterns in the LAHNSCC and p16+ OPSCC, possibly explained by differences in cancer biology and morphology. A deep understanding of ADC metrics is warranted to establish imaging biomarkers for adaptive RT in HNSCC.

BGWAS: Bayesian variable selection in linear mixed models with nonlocal priors for genome-wide association studies

BackgroundGenome-wide association studies (GWAS) seek to identify single nucleotide polymorphisms (SNPs) that cause observed phenotypes. However, with highly correlated SNPs, correlated observations, and the number of SNPs being two orders of magnitude larger than the number of observations, GWAS procedures often suffer from high false positive rates.ResultsWe propose BGWAS, a novel Bayesian variable selection method based on nonlocal priors for linear mixed models specifically tailored for genome-wide association studies. Our proposed method BGWAS uses a novel nonlocal prior for linear mixed models (LMMs). BGWAS has two steps: screening and model selection. The screening step scans through all the SNPs fitting one LMM for each SNP and then uses Bayesian false discovery control to select a set of candidate SNPs. After that, a model selection step searches through the space of LMMs that may have any number of SNPs from the candidate set. A simulation study shows that, when compared to popular GWAS procedures, BGWAS greatly reduces false positives while maintaining the same ability to detect true positive SNPs. We show the utility and flexibility of BGWAS with two case studies: a case study on salt stress in plants, and a case study on alcohol use disorder.ConclusionsBGWAS maintains and in some cases increases the recall of true SNPs while drastically lowering the number of false positives compared to popular SMA procedures.

MS Ana: Improving Sensitivity in Peptide Identification with Spectral Library Search

Spectral library search can enable more sensitive peptide identification in tandem mass spectrometry experiments. However, its drawbacks are the limited availability of high-quality libraries and the added difficulty of creating decoy spectra for result validation. We describe MS Ana, a new spectral library search engine that enables high sensitivity peptide identification using either curated or predicted spectral libraries as well as robust false discovery control through its own decoy library generation algorithm. MS Ana identifies on average 36% more spectrum matches and 4% more proteins than database search in a benchmark test on single-shot human cell-line data. Further, we demonstrate the quality of the result validation with tests on synthetic peptide pools and show the importance of library selection through a comparison of library search performance with different configurations of publicly available human spectral libraries.

Genome wide association study for growth in Pakistani dromedary camels using genotyping-by-sequencing.

Growth performance and growth-related traits have a crucial role in livestock due to their influence on productivity. This genome-wide association study (GWAS) in Pakistani dromedary camels was conducted to identify single nucleotide polymorphisms (SNPs) associated with growth at specific camel ages, and for selected SNPs, to investigate in detail how their effects change with increasing camel age. This is the first GWAS conducted on dromedary camels in this region. Two Pakistani breeds, Marecha and Lassi, were selected for this study. A genotypingby-sequencing method was used, and a total of 65,644 SNPs were identified. For GWAS, weight records data with several body weight traits, namely, birthweight, weaning weight, and weights of camels at 1, 2, 4, and 6 years of age were analysed by using model-based growth curve analysis. Age-specific weight data were analysed with a linear mixed model that included fixed effects of SNP genotype as well as sex. Based on the q-value method for false discovery control, for Marecha camels, five SNPs at q<0.01 and 96 at q<0.05 were significantly associated with the weight traits considered, while three (q<0.01) and seven (q<0.05) SNP associations were identified for Lassi camels. Several candidate genes harbouring these SNP were discovered. These results will help to better understand the genetic architecture of growth including how these genes are expressed at different phases of their life. This will serve to lay the foundations for applied breeding programs of camels by allowing the genetic selection of superior animals.

BICOSS: Bayesian iterative conditional stochastic search for GWAS

BackgroundSingle marker analysis (SMA) with linear mixed models for genome wide association studies has uncovered the contribution of genetic variants to many observed phenotypes. However, SMA has weak false discovery control. In addition, when a few variants have large effect sizes, SMA has low statistical power to detect small and medium effect sizes, leading to low recall of true causal single nucleotide polymorphisms (SNPs).ResultsWe present the Bayesian Iterative Conditional Stochastic Search (BICOSS) method that controls false discovery rate and increases recall of variants with small and medium effect sizes. BICOSS iterates between a screening step and a Bayesian model selection step. A simulation study shows that, when compared to SMA, BICOSS dramatically reduces false discovery rate and allows for smaller effect sizes to be discovered. Finally, two real world applications show the utility and flexibility of BICOSS.ConclusionsWhen compared to widely used SMA, BICOSS provides higher recall of true SNPs while dramatically reducing false discovery rate.

Powerful and interpretable control of false discoveries in two-group differential expression studies.

The standard approach for statistical inference in differential expression (DE) analyses is to control the false discovery rate (FDR). However, controlling the FDR does not in fact imply that the proportion of false discoveries is upper bounded. Moreover, no statistical guarantee can be given on subsets of genes selected by FDR thresholding. These known limitations are overcome by post hoc inference, which provides guarantees of the number of proportion of false discoveries among arbitrary gene selections. However, post hoc inference methods are not yet widely used for DE studies. In this article, we demonstrate the relevance and illustrate the performance of adaptive interpolation-based post hoc methods for two-group DE studies. First, we formalize the use of permutation-based methods to obtain sharp confidence bounds that are adaptive to the dependence between genes. Then, we introduce a generic linear time algorithm for computing post hoc bounds, making these bounds applicable to large-scale two-group DE studies. The use of the resulting Adaptive Simes bound is illustrated on a RNA sequencing study. Comprehensive numerical experiments based on real microarray and RNA sequencing data demonstrate the statistical performance of the method. A cross-platform open source implementation within the R package sanssouci is available at https://sanssouci-org.github.io/sanssouci/. Supplementary data are available at Bioinformatics online.

Notip: Non-parametric true discovery proportion control for brain imaging

Cluster-level inference procedures are widely used for brain mapping. These methods compare the size of clusters obtained by thresholding brain maps to an upper bound under the global null hypothesis, computed using Random Field Theory or permutations. However, the guarantees obtained by this type of inference - i.e. at least one voxel is truly activated in the cluster - are not informative with regards to the strength of the signal therein. There is thus a need for methods to assess the amount of signal within clusters; yet such methods have to take into account that clusters are defined based on the data, which creates circularity in the inference scheme. This has motivated the use of post hoc estimates that allow statistically valid estimation of the proportion of activated voxels in clusters. In the context of fMRI data, the All-Resolutions Inference framework introduced in Rosenblatt et al. (2018) provides post hoc estimates of the proportion of activated voxels. However, this method relies on parametric threshold families, which results in conservative inference. In this paper, we leverage randomization methods to adapt to data characteristics and obtain tighter false discovery control. We obtain Notip, for Non-parametric True Discovery Proportion control: a powerful, non-parametric method that yields statistically valid guarantees on the proportion of activated voxels in data-derived clusters. Numerical experiments demonstrate substantial gains in number of detections compared with state-of-the-art methods on 36 fMRI datasets. The conditions under which the proposed method brings benefits are also discussed.

Sequential Pathway Inference for Multimodal Neuroimaging Analysis.

Motivated by a multimodal neuroimaging study for Alzheimer's disease, in this article, we study the inference problem, i.e., hypothesis testing, of sequential mediation analysis. The existing sequential mediation solutions mostly focus on sparse estimation, while hypothesis testing is an utterly different and more challenging problem. Meanwhile, the few mediation testing solutions often ignore the potential dependency among the mediators, or cannot be applied to the sequential problem directly. We propose a statistical inference procedure to test mediation pathways when there are sequentially ordered multiple data modalities and each modality involves multiple mediators. We allow the mediators to be conditionally dependent, and the number of mediators within each modality to diverge with the sample size. We produce the explicit significance quantification and establish the theoretical guarantees in terms of asymptotic size, power, and false discovery control. We demonstrate the efficacy of the method through both simulations and an application to a multimodal neuroimaging pathway analysis of Alzheimer's disease.

Skilled Mutual Fund Selection: False Discovery Control Under Dependence

Selecting skilled mutual funds through the multiple testing framework has received increasing attention from finance researchers and statisticians. The intercept α of Carhart four-factor model is commonly used to measure the true performance of mutual funds, and positive α’s are considered as skilled. We observe that the standardized ordinary least-square estimates of α’s across the funds possess strong dependence and nonnormality structures, indicating that the conventional multiple testing methods are inadequate for selecting the skilled funds. We start from a decision theoretical perspective, and propose an optimal multiple testing procedure to minimize a combination of false discovery rate and false nondiscovery rate. Our proposed testing procedure is constructed based on the probability of each fund not being skilled conditional on the information across all of the funds in our study. To model the distribution of the information used for the testing procedure, we consider a mixture model under dependence and propose a new method called “approximate empirical Bayes” to fit the parameters. Empirical studies show that our selected skilled funds have superior long-term and short-term performance, for example, our selection strongly outperforms the S&P 500 index during the same period.

Estimation and false discovery control for the analysis of environmental mixtures.

The analysis of environmental mixtures is of growing importance in environmental epidemiology, and one of the key goals in such analyses is to identify exposures and their interactions that are associated with adverse health outcomes. Typical approaches utilize flexible regression models combined with variable selection to identify important exposures and estimate a potentially nonlinear relationship with the outcome of interest. Despite this surge in interest, no approaches to date can identify exposures and interactions while controlling any form of error rates with respect to exposure selection. We propose two novel approaches to estimating the health effects of environmental mixtures that simultaneously (i) estimate and provide valid inference for the overall mixture effect and (ii) identify important exposures and interactions while controlling the false discovery rate (FDR). We show that this can lead to substantial power gains to detect weak effects of environmental exposures. We apply our approaches to a study of persistent organic pollutants and find that controlling the FDR leads to substantially different conclusions.

11C]PiB and [18F]AV45 PET radiotracers show different rates of amyloid‐β clearance

AbstractBackgroundResults from the first Dominantly Inherited Alzheimer Network Trials Unit (DIAN‐TU) clinical trial showed Gantenerumab reduces amyloid‐β deposition in autosomal dominant Alzheimer disease individuals. However, it is uncertain whether these initial findings from [11C]PiB PET generalize to other amyloid‐β PET radiotracers.MethodWe acquired [11C]PiB and [18F]AV45 PET in mutation positive DIAN‐TU participants in the gantenerumab (n=30) and placebo drug arms (n=19). Participants were assessed at baseline and Year 4; at each visit, [11C]PiB and [18F]AV45 PET were acquired, with at most 28 days between imaging sessions. Regional standardized uptake value ratios (SUVRs) were quantified using the PET Unified Pipeline. Annualized SUVR percent change between baseline and Year 4 for both radiotracers in both drug arms were calculated. Differences in SUVR change between radiotracers/drug arms were assessed using the Wilcoxon signed‐rank/rank‐sum test. Each test statistic is reported as a rank‐biserial correlation r accompanied by p‐values adjusted for false discovery control by the Benjamini‐Hochberg procedure at level q=0.20.ResultWe observed a decrease from baseline to Year 4 SUVR in the gantenerumab arm, which was larger when studied with [11C]PiB than with [18F]AV45 PET in several regions, including the striatum and cingulate gyrus (r=[‐0.79,‐0.31], FDR‐adjusted p‐values=[0.00086,0.19], Figure 1). In contrast, we observed an increase in SUVR in the placebo arm, comparable in magnitude between [11C]PiB and [18F]AV45 PET (r=[‐0.15,0.68], FDR‐adjusted p‐values=[0.29,0.86]).ConclusionDifferences seen between the effects of gantenerumab in [11C]PiB versus [18F]AV45 PET suggest several regions, such as the striatum and cingulate gyrus, may be inappropriate for radiotracer harmonization in studies involving gantenerumab. More practically, the finding that anti‐amyloid‐β therapies may have different effects on signal across radiotracers suggests multi‐site studies of anti‐amyloid‐β treatments should agree on a single radiotracer for best results. Follow‐up postmortem studies will be conducted to determine the binding affinity of various amyloid‐β radiotracers to amyloid‐β plaques in this cohort.

FUNCTION-ON-FUNCTION REGRESSION FOR THE IDENTIFICATION OF EPIGENETIC REGIONS EXHIBITING WINDOWS OF SUSCEPTIBILITY TO ENVIRONMENTAL EXPOSURES.

The ability to identify time periods when individuals are most susceptible to exposures as well as the biological mechanisms through which these exposures act is of great public health interest. Growing evidence supports an association between prenatal exposure to air pollution and epigenetic marks, such as DNA methylation, but the timing and gene-specific effects of these epigenetic changes are not well understood. Here, we present the first study that aims to identify prenatal windows of susceptibility to air pollution exposures in cord blood DNA methylation. In particular, we propose a function-on-function regression model that leverages data from nearby DNA methylation probes to identify epigenetic regions that exhibit windows of susceptibility to ambient particulate matter less than 2.5 microns (PM2.5). By incorporating the covariance structure among both the multivariate DNA methylation outcome and the time-varying exposure under study, this framework yields greater power to detect windows of susceptibility and greater control of false discoveries than methods that model probes independently. We compare our method to a distributed lag model approach that models DNA methylation in a probe-by-probe manner, both in simulation and by application to motivating data from the Project Viva birth cohort. We identify a window of susceptibility to PM2.5 exposure in the middle of the third trimester of pregnancy in an epigenetic region selected based on prior studies of air pollution effects on epigenome-wide methylation.

Hypothesis testing for high-dimensional multivariate regression with false discovery rate control

Motivated by applications in microarray data analysis, we consider the problem of estimating the row sparsity of the coefficient matrix in multivariate regression. The problem is formulated as a row-wise multiple testing problem. A new test statistic is constructed for each row of the coefficient matrix, and a row-wise multiple testing procedure is proposed. Our approach takes advantage of the row sparsity of the coefficient matrix to gain high power and handles the correlation structure of the error vector. Asymptotic distribution of the test statistic and asymptotic false discovery control of the row-wise multiple testing procedure are provided. Numerical results are also presented to evaluate the performance of the proposed method in both simulation studies and real data analysis.

Defining the Inflammatory Plasma Proteome in Pediatric Hodgkin Lymphoma.

Simple SummaryHodgkin lymphoma (HL) is a common type of cancer that is characterized by rare, malignant cells among an inflammatory microenvironment. Specific systemic, inflammatory plasma proteins have demonstrated prognostic significance in adult HL; however, systemic inflammation has not been well-characterized in childhood HL. The aim of our study was to better define the inflammatory pre-therapy plasma proteome and identify plasma proteins associated with clinical features of childhood HL. We measured plasma concentrations of 135 proteins in 56 pediatric subjects with newly diagnosed HL and 47 healthy pediatric controls. We found that the plasma protein profile was distinct from controls, and unique proteins were associated with high-risk disease (IL-10, TNF-α, IFN-γ, IL-8), slow early therapy response (CCL13, IFN-λ1, IL-8), and relapse (TNFSF10). These proteins could be used to improve risk stratification, and thus optimize outcomes and minimize unnecessary toxic exposures for those with childhood HL.Hodgkin lymphoma (HL) histopathology is characterized by rare malignant Reed–Sternberg cells among an inflammatory infiltrate. We hypothesized that characteristics of inflammation in pediatric HL lesions would be reflected by the levels of inflammatory cytokines or chemokines in pre-therapy plasma of children with HL. The study objectives were to better define the inflammatory pre-therapy plasma proteome and identify plasma biomarkers associated with extent of disease and clinical outcomes in pediatric HL. Pre-therapy plasma samples were obtained from pediatric subjects with newly diagnosed HL and healthy pediatric controls. Plasma concentrations of 135 cytokines/chemokines were measured with the Luminex platform. Associations between protein concentration and disease characteristics were determined using multivariate permutation tests with false discovery control. Fifty-six subjects with HL (mean age: 13 years, range 3–18) and 47 controls were analyzed. The cytokine/chemokine profiles of subjects with HL were distinct from controls, and unique cytokines/chemokines were associated with high-risk disease (IL-10, TNF-α, IFN-γ, IL-8) and slow early response (CCL13, IFN-λ1, IL-8). TNFSF10 was significantly elevated among those who ultimately relapsed and was significantly associated with worse event-free survival. These biomarkers could be incorporated into biologically based risk stratification to optimize outcomes and minimize toxicities in pediatric HL.

Compositional knockoff filter for high-dimensional regression analysis of microbiome data.

A critical task in microbiome data analysis is to explore the association between a scalar response of interest and a large number of microbial taxa that are summarized as compositional data at different taxonomic levels. Motivated by fine-mapping of the microbiome, we propose a two-step compositional knockoff filter to provide the effective finite-sample false discovery rate (FDR) control in high-dimensional linear log-contrast regression analysis of microbiome compositional data. In the first step, we propose a new compositional screening procedure to remove insignificant microbial taxa while retaining the essential sum-to-zero constraint. In the second step, we extend the knockoff filter to identify the significant microbial taxa in the sparse regression model for compositional data. Thereby, a subset of the microbes is selected from the high-dimensional microbial taxa as related to the response under a prespecified FDR threshold. We study the theoretical properties of the proposed two-step procedure, including both sure screening and effective false discovery control. We demonstrate these properties in numerical simulation studies to compare our methods to some existing ones and show power gain of the new method while controlling the nominal FDR. The potential usefulness of the proposed method is also illustrated with application to an inflammatory bowel disease data set to identify microbial taxa that influence host geneexpressions.

Simultaneous Covariance Inference for Multimodal Integrative Analysis

Multimodal integrative analysis fuses different types of data collected on the same set of experimental subjects. It is becoming a norm in many branches of scientific research, such as multi-omics and multimodal neuroimaging analysis. In this article, we address the problem of simultaneous covariance inference of associations between multiple modalities, which is of a vital interest in multimodal integrative analysis. Recognizing that there are few readily available solutions in the literature for this type of problem, we develop a new simultaneous testing procedure. It provides an explicit quantification of statistical significance, a much improved detection power, as well as a rigid false discovery control. Our proposal makes novel and useful contributions from both the scientific perspective and the statistical methodological perspective. We demonstrate the efficacy of the new method through both simulations and a multimodal positron emission tomography study of associations between two hallmark pathological proteins of Alzheimer’s disease.

False Discovery Rate Control in Cancer Biomarker Selection Using Knockoffs.

The discovery of biomarkers that are informative for cancer risk assessment, diagnosis, prognosis and treatment predictions is crucial. Recent advances in high-throughput genomics make it plausible to select biomarkers from the vast number of human genes in an unbiased manner. Yet, control of false discoveries is challenging given the large number of genes versus the relatively small number of patients in a typical cancer study. To ensure that most of the discoveries are true, we employ a knockoff procedure to control false discoveries. Our method is general and flexible, accommodating arbitrary covariate distributions, linear and nonlinear associations, and survival models. In simulations, our method compares favorably to the alternatives; its utility of identifying important genes in real clinical applications is demonstrated by the identification of seven genes associated with Breslow thickness in skin cutaneous melanoma patients.