Obtaining Critical Values for Simultaneous Confidence Intervals and Multiple Testing

There are many situations where it is desired to make simultaneous tests or give simultaneous confidence intervals for linear combinations (contrasts) of population or treatment means. Somerville (1997, 1999) developed algorithms for calculating the critical values for a large class of simultaneous tests and simultaneous confidence intervals. Fortran 90 and SAS‐IML batch programs and interactive programs were developed. These programs calculate the critical values for 15 different simultaneous confidence interval procedures (and the corresponding simultaneous tests) and for arbitrary procedures where the user specifies a combination of one and two sided contrasts. The programs can also be used to obtain the constants for “step‐down” testing of multiple hypotheses. This paper gives examples of the use of the algorithms and programs and illustrates their versatility and generality. The designs need not be balanced, multiple covariates may be present and there may be many missing values. The use of multiple regression and dummy variables to obtain the required variance covariance matrix is illustrated. Under weak normality assumptions the methods are “exact” and make the use of approximate methods or “simulation” unnecessary.     

Dose finding - a challenge in statistics

A good understanding and characterization of the dose response relationship of any new compound is an important and ubiquitous problem in many areas of scientific investigation. This is especially true in the context of pharmaceutical drug development, where it is mandatory to launch safe drugs which demonstrate a clinically relevant effect. Selecting a dose too high may result in unacceptable safety problems, while selecting a dose too low may lead to ineffective drugs. Dose finding studies thus play a key role in any drug development program and are often the gate-keeper for large confirmatory studies. In this overview paper we focus on definitive and confirmatory dose finding studies in Phase II or III, reviewing relevant statistical design and analysis methods. In particular, we describe multiple comparison procedures, modeling approaches, and hybrid methods combining the advantages of both. An outlook to adaptive dose finding methods is also given. We use a real data example to illustrate the methods, together with a brief overview of relevant software.     

Evaluation of Animal Carcinogenicity Studies: Cochran‐Armitage Trend Test vs. Multiple Contrast Tests

Typical animal carcinogenicity studies involve the comparison of several dose groups to a negative control. The uncorrected asymptotic Cochran‐Armitage trend test with equally spaced dose scores is the most frequently used test in such set‐ups. However, this test based on a weighted linear regression on proportions. It is well known that the Cochran‐Armitage test lacks in power for other shapes than the assumed linear one. Therefore, dichotomous multiple contrast tests are introduced. These build the maximum over several single contrasts, where each of them is chosen appropriately to cover a specific dose‐response shape. An extensive power study has been conducted to compare multiple contrast tests with the approaches used so far. Crucial results will be presented in this paper. Moreover, exact tests and continuity corrected versions are introduced and compared to the traditional uncorrected approaches regarding size and power behaviour. A trend test for any shape of the dose‐response relationship for either crude tumour rates or mortality‐ adjusted rates based on the simple Poly‐3 transformation is proposed for evaluation of carcinogenicity studies.     

Resampling-based multiple testing methods with covariate adjustment: application to investigation of antiretroviral drug susceptibility

Summary .   Identifying genetic mutations that cause clinical resistance to antiretroviral drugs requires adjustment for potential confounders, such as the number of active drugs in a HIV-infected patient's regimen other than the one of interest. Motivated by this problem, we investigated resampling-based methods to test equal mean response across multiple groups defined by HIV genotype, after adjustment for covariates. We consider construction of test statistics and their null distributions under two types of model: parametric and semiparametric. The covariate function is explicitly specified in the parametric but not in the semiparametric approach. The parametric approach is more precise when models are correctly specified, but suffer from bias when they are not; the semiparametric approach is more robust to model misspecification, but may be less efficient. To help preserve type I error while also improving power in both approaches, we propose resampling approaches based on matching of observations with similar covariate values. Matching reduces the impact of model misspecification as well as imprecision in estimation. These methods are evaluated via simulation studies and applied to a data set that combines results from a variety of clinical studies of salvage regimens. Our focus is on relating HIV genotype to viral susceptibility to abacavir after adjustment for the number of active antiretroviral drugs (excluding abacavir) in the patient's regimen.     

Multiple augmentation with partial missing regressors

In large cohort studies, it is common that a subset of the regressors may be missing for some study subjects by design or happenstance. In this article, we apply the multiple data augmentation techniques to semiparametric models for epidemiologic data when a subset of the regressors are missing for some subjects, under the assumption that the data are missing at random in the sense of Rubin (2004) and that the missingness probabilities depend jointly on the observable subset of regressors, on a set of observable extraneous variables and on the outcome. Computational algorithms for the Poor Man's and the Asymptotic Normal data augmentations are investigated. Simulation studies show that the data augmentation approach generates satisfactory estimates and is computationally affordable. Under certain simulation scenarios, the proposed approach can achieve asymptotic efficiency similar to the maximum likelihood approach. We apply the proposed technique to the Multi-Ethic Study of Atherosclerosis (MESA) data and the South Wales Nickel Worker Study data.     

Ordered multiple comparisons with the best and their applications to dose-response studies

This article considers the problem of comparing several treatments (dose levels, interventions, etc.) with the best, where the best treatment is unknown and the treatments are ordered in some sense. Order relations among treatments often occur quite naturally in practice. They may be ordered according to increasing risks, such as tolerability or safety problems with increasing dose levels in a dose-response study, for example. We tackle the problem of constructing a lower confidence bound for the smallest index of all treatments being at most marginally less effective than the (best) treatment having the largest effect. Such a bound ensures at confidence level 1 -alpha that all treatments with lower indices are relevantly less effective than the best competitor. We derive a multiple testing strategy that results in sharp confidence bounds. The proposed lower confidence bound is compared with those derived from other testing strategies. We further derive closed-form expressions for power and sample size calculations. Finally, we investigate several real data sets to illustrate various applications of our methods.     

Multiple imputation methods for multivariate one-sided tests with missing data

Multivariate one-sided hypotheses testing problems arise frequently in practice. Various tests have been developed. In practice, there are often missing values in multivariate data. In this case, standard testing procedures based on complete data may not be applicable or may perform poorly if the missing data are discarded. In this article, we propose several multiple imputation methods for multivariate one-sided testing problem with missing data. Some theoretical results are presented. The proposed methods are evaluated using simulations. A real data example is presented to illustrate the methods.     

Multiple Testing for Detecting Efficient Dose Steps

In the comparison of various dose levels it can often be assumed that the parameters to be tested follow an order restriction. Two closed multiple test procedures for detecting the highest dose level still providing a shift in the response distribution as compared to the adjacent lower dose level is proposed. One is based on one sided comparisons between neighbouring doses, the other uses Helmert-type contrast statistics. If a sequence of testing is fixed in advance the multiple test can be suitably modified. The power of the procedures is simulated under the assumption of normally distributed responses for various constellations of the dose means. It is compared with the power of a general Holm-type procedure discussed in BUDDE & BAUER (1989).     

A statistical framework for eQTL mapping using RNA-seq data

RNA-seq may replace gene expression microarrays in the near future. Using RNA-seq, the expression of a gene can be estimated using the total number of sequence reads mapped to that gene, known as the total read count (TReC). Traditional expression quantitative trait locus (eQTL) mapping methods, such as linear regression, can be applied to TReC measurements after they are properly normalized. In this article, we show that eQTL mapping, by directly modeling TReC using discrete distributions, has higher statistical power than the two-step approach: data normalization followed by linear regression. In addition, RNA-seq provides information on allele-specific expression (ASE) that is not available from microarrays. By combining the information from TReC and ASE, we can computationally distinguish cis- and trans-eQTL and further improve the power of cis-eQTL mapping. Both simulation and real data studies confirm the improved power of our new methods. We also discuss the design issues of RNA-seq experiments. Specifically, we show that by combining TReC and ASE measurements, it is possible to minimize cost and retain the statistical power of cis-eQTL mapping by reducing sample size while increasing the number of sequence reads per sample. In addition to RNA-seq data, our method can also be employed to study the genetic basis of other types of sequencing data, such as chromatin immunoprecipitation followed by DNA sequencing data. In this article, we focus on eQTL mapping of a single gene using the association-based method. However, our method establishes a statistical framework for future developments of eQTL mapping methods using RNA-seq data (e.g., linkage-based eQTL mapping), and the joint study of multiple genetic markers and/or multiple genes.     

Two-drug combinations of memory enhancers: effect of dose ratio upon potency and therapeutic window, in mice

Two-drug combinations have been reported to enhance retention more effectively than when either drug was administered alone at the same dose. Some combinations of cholinergic drugs enhance retention even though the total drug dosage is reduced by as much as 97% compared to the dose needed to improve retention when the same drugs are administered singly. The choice of dose ratio is usually arbitrary or based on empirical results. The present study systematically varied the ratio of two drugs in a combination and at the same time varied the dosage of each drug. The drug combinations were administered to mice immediately after training on T-maze footshock avoidance task. Retention was tested one week later. Three two-drug combinations were selected for presentation because they differed considerably as to (a) the lowest effective total dose that improved memory-retention, (b) the optimal ratio that improved retention and (c) the width of the therapeutic window. The effect of a drug combination on retention was found to be dependent on the particular drugs in the combination, the ratio and the dose administered.     

CPT11 prevents virus replication in JCI cells persistently infected with JC polyomavirus

JC polyomavirus (JCPyV) is the causative agent of the demyelinating disease of the central nervous system known as progressive multifocal leukoencephalopathy (PML), which occurs in immunocompromised patients. Moreover, patients treated with natalizumab for multiple sclerosis or Crohn disease can develop PML, which is then termed natalizumab‐related PML. Because few drugs are currently available for treating PML, many antiviral agents are being investigated. It has been demonstrated that the topoisomerase I inhibitors topotecan and β‐lapachone have inhibitory effects on JCPyV replication in IMR‐32 cells. However, both of these drugs have marginal inhibitory effects on virus propagation in JC1 cells according to RT‐PCR analysis. In the present study, the inhibitory effect of another topoisomerase I inhibitor, 7‐ethy‐10‐[4‐(1‐piperidino)‐1‐piperidino] carbonyloxy camptothecin (CPT11), was assessed by investigating viral replication, propagation, and viral protein 1 (VP1) production in cultured cells. JCPyV replication was assayed using real‐time PCR combined with Dpn I treatment in IMR‐32 cells transfected with JCPyV DNA. It was found that JCPyV replicates less in IMR‐32 cells treated with CPT11 than in untreated cells. Moreover, CPT11 treatment of JCI cells persistently infected with JCPyV led to a dose‐dependent reduction in JCPyV DNA and VP1 production. Additionally, the inhibitory effect of CPT11 was found to be stronger than those of topotecan and β‐lapachone. These findings suggest that CPT11 may be a potential anti‐JCPyV agent that could be used to treat PML.

     

k‐FWER Control without p ‐value Adjustment,with Application to Detection of Genetic Determinants of Multiple Sclerosis in Italian Twins

Summary We show a novel approach for k‐FWER control which does not involve any correction, but only testing the hypotheses along a (possibly data‐driven) order until a suitable number of p‐values are found above the uncorrected α level. p‐values can arise from any linear model in a parametric or nonparametric setting. The approach is not only very simple and computationally undemanding, but also the data‐driven order enhances power when the sample size is small (and also when k and/or the number of tests is large). We illustrate the method on an original study about gene discovery in multiple sclerosis, in which were involved a small number of couples of twins, discordant by disease. The methods are implemented in an R package (someKfwer ), freely available on CRAN.     

High-order SNP combinations associated with complex diseases: efficient discovery, statistical power and functional interactions

There has been increased interest in discovering combinations of single-nucleotide polymorphisms (SNPs) that are strongly associated with a phenotype even if each SNP has little individual effect. Efficient approaches have been proposed for searching two-locus combinations from genome-wide datasets. However, for high-order combinations, existing methods either adopt a brute-force search which only handles a small number of SNPs (up to few hundreds), or use heuristic search that may miss informative combinations. In addition, existing approaches lack statistical power because of the use of statistics with high degrees-of-freedom and the huge number of hypotheses tested during combinatorial search. Due to these challenges, functional interactions in high-order combinations have not been systematically explored. We leverage discriminative-pattern-mining algorithms from the data-mining community to search for high-order combinations in case-control datasets. The substantially improved efficiency and scalability demonstrated on synthetic and real datasets with several thousands of SNPs allows the study of several important mathematical and statistical properties of SNP combinations with order as high as eleven. We further explore functional interactions in high-order combinations and reveal a general connection between the increase in discriminative power of a combination over its subsets and the functional coherence among the genes comprising the combination, supported by multiple datasets. Finally, we study several significant high-order combinations discovered from a lung-cancer dataset and a kidney-transplant-rejection dataset in detail to provide novel insights on the complex diseases. Interestingly, many of these associations involve combinations of common variations that occur in small fractions of population. Thus, our approach is an alternative methodology for exploring the genetics of rare diseases for which the current focus is on individually rare variations.     

Exploring the extremes of sequence/structure space with ensemble fold recognition in the program Phyre

Structural and functional annotation of the large and growing database of genomic sequences is a major problem in modern biology. Protein structure prediction by detecting remote homology to known structures is a well-established and successful annotation technique. However, the broad spectrum of evolutionary change that accompanies the divergence of close homologues to become remote homologues cannot easily be captured with a single algorithm. Recent advances to tackle this problem have involved the use of multiple predictive algorithms available on the Internet. Here we demonstrate how such ensembles of predictors can be designed in-house under controlled conditions and permit significant improvements in recognition by using a concept taken from protein loop energetics and applying it to the general problem of 3D clustering. We have developed a stringent test that simulates the situation where a protein sequence of interest is submitted to multiple different algorithms and not one of these algorithms can make a confident (95%) correct assignment. A method of meta-server prediction (Phyre) that exploits the benefits of a controlled environment for the component methods was implemented. At 95% precision or higher, Phyre identified 64.0% of all correct homologous query-template relationships, and 84.0% of the individual test query proteins could be accurately annotated. In comparison to the improvement that the single best fold recognition algorithm (according to training) has over PSI-Blast, this represents a 29.6% increase in the number of correct homologous query-template relationships, and a 46.2% increase in the number of accurately annotated queries. It has been well recognised in fold prediction, other bioinformatics applications, and in many other areas, that ensemble predictions generally are superior in accuracy to any of the component individual methods. However there is a paucity of information as to why the ensemble methods are superior and indeed this has never been systematically addressed in fold recognition. Here we show that the source of ensemble power stems from noise reduction in filtering out false positive matches. The results indicate greater coverage of sequence space and improved model quality, which can consequently lead to a reduction in the experimental workload of structural genomics initiatives.     

A Bayesian seamless phase I–II trial design with two stages for cancer clinical trials with drug combinations

The use of drug combinations in clinical trials is increasingly common during the last years since a more favorable therapeutic response may be obtained by combining drugs. In phase I clinical trials, most of the existing methodology recommends a one unique dose combination as “optimal,” which may result in a subsequent failed phase II clinical trial since other dose combinations may present higher treatment efficacy for the same level of toxicity. We are particularly interested in the setting where it is necessary to wait a few cycles of therapy to observe an efficacy outcome and the phase I and II population of patients are different with respect to treatment efficacy. Under these circumstances, it is common practice to implement two-stage designs where a set of maximum tolerated dose combinations is selected in a first stage, and then studied in a second stage for treatment efficacy. In this article we present a new two-stage design for early phase clinical trials with drug combinations. In the first stage, binary toxicity data is used to guide the dose escalation and set the maximum tolerated dose combinations. In the second stage, we take the set of maximum tolerated dose combinations recommended from the first stage, which remains fixed along the entire second stage, and through adaptive randomization, we allocate subsequent cohorts of patients in dose combinations that are likely to have high posterior median time to progression. The methodology is assessed with extensive simulations and exemplified with a real trial.     

Genotype-Based Ancestral Background Consistently Predicts Efficacy and Side Effects across Treatments in CATIE and STAR*D

Only a subset of patients will typically respond to any given prescribed drug. The time it takes clinicians to declare a treatment ineffective leaves the patient in an impaired state and at unnecessary risk for adverse drug effects. Thus, diagnostic tests robustly predicting the most effective and safe medication for each patient prior to starting pharmacotherapy would have tremendous clinical value. In this article, we evaluated the use of genetic markers to estimate ancestry as a predictive component of such diagnostic tests. We first estimated each patient’s unique mosaic of ancestral backgrounds using genome-wide SNP data collected in the Clinical Antipsychotic Trials of Intervention Effectiveness (CATIE) (n = 765) and the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) (n = 1892). Next, we performed multiple regression analyses to estimate the predictive power of these ancestral dimensions. For 136/89 treatment-outcome combinations tested in CATIE/STAR*D, results indicated 1.67/1.84 times higher median test statistics than expected under the null hypothesis assuming no predictive power (p<0.01, both samples). Thus, ancestry showed robust and pervasive correlations with drug efficacy and side effects in both CATIE and STAR*D. Comparison of the marginal predictive power of MDS ancestral dimensions and self-reported race indicated significant improvements to model fit with the inclusion of MDS dimensions, but mixed evidence for self-reported race. Knowledge of each patient’s unique mosaic of ancestral backgrounds provides a potent immediate starting point for developing algorithms identifying the most effective and safe medication for a wide variety of drug-treatment response combinations. As relatively few new psychiatric drugs are currently under development, such personalized medicine offers a promising approach toward optimizing pharmacotherapy for psychiatric conditions.     

Gaussian Process Based Bayesian Semiparametric Quantitative Trait Loci Interval Mapping

Summary .  In linkage analysis, it is often necessary to include covariates such as age or weight to increase power or avoid spurious false positive findings. However, if a covariate term in the model is specified incorrectly (e.g., a quadratic term misspecified as a linear term), then the inclusion of the covariate may adversely affect power and accuracy of the identification of quantitative trait loci (QTL). Furthermore, some covariates may interact with each other in a complicated fashion. We implement semiparametric models for single and multiple QTL mapping. Both mapping methods include an unspecified function of any covariate found or suspected to have a more complex than linear but unknown relationship with the response variable. They also allow for interactions among different covariates. This analysis is performed in a Bayesian inference framework using Markov chain Monte Carlo. The advantages of our methods are demonstrated via extensive simulations and real data analysis.     

Bayesian analysis of case control polygenic etiology studies with missing data

Many genetic studies are based on analysing multiple DNA regions of cases and controls. Usually each is tested separately for association with disease. However, some diseases may require interacting polymorphisms at several regions, and most disease susceptibility is polygenic. In this paper, we develop new methods for determining combinations of polymorphisms that affect the risk of disease. For example, two different genes might produce normal proteins, but these proteins improperly function when they occur together. We consider a Bayesian approach to analyse studies where DNA data from cases and controls have been analysed for polymorphisms at multiple regions and a polygenic etiology is suspected. The method of Gibbs sampling is used to incorporate data from individuals who have not had every region analysed at the DNA sequence or amino acid level. The Gibbs sampling algorithm alternatively generates a sample from the posterior distribution of the sequence of combinations of polymorphisms in cases and controls and then uses this sample to impute the data that are missing. After convergence the algorithm is used to generate a sample from the posterior distribution for the probability of each combination in order to identify groups of polymorphisms that best discriminate cases from controls. We apply the methods to a genetic study of type I diabetes. The protein encoded by the TAP2 gene is important in T cell function, and thus may affect the development of autoimmune diseases such as insulin dependent diabetes mellitus (IDDM). We determine pairs of polymorphisms of genetic fragments in the coding regions of linked HLA genes that may impact the risk of IDDM.