We present a Bayesian hierarchical model for detecting differentially expressing genes that includes simultaneous estimation of array effects, and show how to use the output for choosing lists of genes for further investigation. We give empirical evidence that expression-level dependent array effects are needed, and explore different nonlinear functions as part of our model-based approach to normalization. The model includes gene-specific variances but imposes some necessary shrinkage through a hierarchical structure. Model criticism via posterior predictive checks is discussed. Modeling the array effects (normalization) simultaneously with differential expression gives fewer false positive results. To choose a list of genes, we propose to combine various criteria (for instance, fold change and overall expression) into a single indicator variable for each gene. The posterior distribution of these variables is used to pick the list of genes, thereby taking into account uncertainty in parameter estimates. In an application to mouse knockout data, Gene Ontology annotations over- and underrepresented among the genes on the chosen list are consistent with biological expectations.

We present a Bayesian hierarchical model for detecting differentially expressed genes using a mixture prior on the parameters representing differential effects. We formulate an easily interpretable 3-component mixture to classify genes as over-expressed, under-expressed and non-differentially expressed, and model gene variances as exchangeable to allow for variability between genes. We show how the proportion of differentially expressed genes, and the mixture parameters, can be estimated in a fully Bayesian way, extending previous approaches where this proportion was fixed and empirically estimated. Good estimates of the false discovery rates are also obtained. Different parametric families for the mixture components can lead to quite different classifications of genes for a given data set. Using Affymetrix data from a knock out and wildtype mice experiment, we show how predictive model checks can be used to guide the choice between possible mixture priors. These checks show that extending the mixture model to allow extra variability around zero instead of the usual point mass null fits the data better. A software package for R is available.

BackgroundCystic fibrosis (CF) is a life-threatening genetic disease, affecting around 10 500 people in the UK. Precision medicines have been developed to treat specific CF-gene mutations. The newest, elexacaftor/tezacaftor/ivacaftor (ELEX/TEZ/IVA), has been found to be highly effective in randomised controlled trials (RCTs) and became available to a large proportion of UK CF patients in 2020. Understanding the potential health economic impacts of ELEX/TEZ/IVA is vital to planning service provision.MethodsWe combined observational UK CF Registry data with RCT results to project the impact of ELEX/TEZ/IVA on total days of intravenous (IV) antibiotic treatment at a population level. Registry data from 2015 to 2017 were used to develop prediction models for IV days over a 1-year period using several predictors, and to estimate 1-year population total IV days based on standards of care pre-ELEX/TEZ/IVA. We considered two approaches to imposing the impact of ELEX/TEZ/IVA on projected outcomes using effect estimates from RCTs: approach 1 based on effect estimates on FEV1% and approach 2 based on effect estimates on exacerbation rate.ResultsELEX/TEZ/IVA is expected to result in significant reductions in population-level requirements for IV antibiotics of 16.1% (~17 800 days) using approach 1 and 43.6% (~39 500 days) using approach 2. The two approaches require different assumptions. Increased understanding of the mechanisms through which ELEX/TEZ/IVA acts on these outcomes would enable further refinements to our projections.ConclusionsThis work contributes to increased understanding of the changing healthcare needs of people with CF and illustrates how Registry data can be used in combination with RCT evidence to estimate population-level treatment impacts.

In this paper we propose a new statistic capable of detecting non-Gaussianity in the CMB. The statistic is defined in Fourier space, and therefore naturally separates angular scales. It consists of taking another Fourier transform, in angle, over the Fourier modes within a given ring of scales. Like other Fourier space statistics, our statistic outdoes more conventional methods when faced with combinations of Gaussian processes (be they noise or signal) and a non-Gaussian signal which dominates only on some scales. However, unlike previous efforts along these lines, our statistic is successful in recognizing multiple non-Gaussian patterns in a single field. We discuss various applications, in which the Gaussian component may be noise or primordial signal, and the non-Gaussian component may be a cosmic string map, or some geometrical construction mimicking, say, small scale dust maps.

Background Psychological stress is commonly cited as a risk factor for melanoma, but clinical evidence is limited. Objectives This study aimed to evaluate the association between partner bereavement and (i) first-time melanoma diagnosis and (ii) mortality in patients with melanoma. Methods We conducted two cohort studies using data from the U.K. Clinical Practice Research Datalink (1997-2017) and Danish nationwide registries (1997-2016). In study 1, we compared the risk of first melanoma diagnosis in bereaved vs. matched nonbereaved people using stratified Cox regression. In study 2 we estimated hazard ratios (HRs) for death from melanoma in bereaved compared with nonbereaved individuals with melanoma using Cox regression. We estimated HRs separately for the U.K. and for Denmark, and then pooled the data to perform a random-effects meta-analysis. Results In study 1, the pooled adjusted HR for the association between partner bereavement and melanoma diagnosis was 0Á88 [95% confidence interval (CI) 0Á84-0Á92] across the entire follow-up period. In study 2, we observed increased melanoma-specific mortality in people experiencing partner bereavement across the entire follow-up period (HR 1Á17, 95% CI 1Á06-1Á30), with the peak occurring during the first year of follow-up (HR 1Á31, 95% CI 1Á07-1Á60). Conclusions We found decreased risk of melanoma diagnosis, but increased mortality associated with partner bereavement. These findings may be partly explained by delayed detection resulting from the loss of a partner who could notice skin changes. Stress may play a role in melanoma progression. Our findings indicate the need for a low threshold for skin examination in individuals whose partners have died. What is already known about this topic? • Psychological stress has been proposed as a risk factor for the development and progression of cancer, including melanoma, but evidence is conflicting. • Clinical evidence is limited by small sample sizes, potential recall bias associated with self-report, and heterogeneous stress definitions. What does this study add? • We found a decreased risk of melanoma diagnosis, but increased mortality associated with partner bereavement.