Adjusting for Berkson error in exposure in ordinary and conditional logistic regression and in Poisson regression.

BACKGROUND: INTEROCC is a seven-country cohort study of occupational exposures and brain cancer risk, including occupational exposure to electromagnetic fields (EMF). In the absence of data on individual exposures, a Job Exposure Matrix (JEM) may be used to construct likely exposure scenarios in occupational settings. This tool was constructed using statistical summaries of exposure to EMF for various occupational categories for a comparable group of workers. METHODS: In this study, we use the Canadian data from INTEROCC to determine the best EMF exposure surrogate/estimate from three appropriately chosen surrogates from the JEM, along with a fourth surrogate based on Berkson error adjustments obtained via numerical approximation of the likelihood function. In this article, we examine the case in which exposures are gamma-distributed for each occupation in the JEM, as an alternative to the log-normal exposure distribution considered in a previous study conducted by our research team. We also study using those surrogates and the Berkson error adjustment in Poisson regression and conditional logistic regression. RESULTS: Simulations show that the introduced methods of Berkson error adjustment for non-stratified analyses provide accurate estimates of the risk of developing tumors in case of gamma exposure model. Alternatively, and under some technical assumptions, the arithmetic mean is the best surrogate when a gamma-distribution is used as an exposure model. Simulations also show that none of the present methods could provide an accurate estimate of the risk in case of stratified analyses. CONCLUSION: While our previous study found the geometric mean to be the best exposure surrogate, the present study suggests that the best surrogate is dependent on the exposure model; the arithmetic means in case of gamma-exposure model and the geometric means in case of log-normal exposure model. However, we could present a better method of Berkson error adjustment for each of the two exposure models. Our results provide useful guidance on the application of JEMs for occupational exposure assessments, with adjustment for Berkson error.

Bayesian regularization for a nonstationary Gaussian linear mixed effects model.

In omics experiments, estimation and variable selection can involve thousands of proteins/genes observed from a relatively small number of subjects. Many regression regularization procedures have been developed for estimation and variable selection in such high-dimensional problems. However, approaches have predominantly focused on linear regression models that ignore correlation arising from long sequences of repeated measurements on the outcome. Our work is motivated by the need to identify proteomic biomarkers that improve the prediction of rapid lung-function decline for individuals with cystic fibrosis (CF) lung disease. We extend four Bayesian penalized regression approaches for a Gaussian linear mixed effects model with nonstationary covariance structure to account for the complicated structure of longitudinal lung function data while simultaneously estimating unknown parameters and selecting important protein isoforms to improve predictive performance. Different types of shrinkage priors are evaluated to induce variable selection in a fully Bayesian framework. The approaches are studied with simulations. We apply the proposed method to real proteomics and lung-function outcome data from our motivating CF study, identifying a set of relevant clinical/demographic predictors and a proteomic biomarker for rapid decline of lung function. We also illustrate the methods on CD4 yeast cell-cycle genomic data, confirming that the proposed method identifies transcription factors that have been highlighted in the literature for their importance as cell cycle transcription factors.

The Library of Integrated Network-Based Cellular Signatures NIH Program: System-Level Cataloging of Human Cells Response to Perturbations.

The Library of Integrated Network-Based Cellular Signatures (LINCS) is an NIH Common Fund program that catalogs how human cells globally respond to chemical, genetic, and disease perturbations. Resources generated by LINCS include experimental and computational methods, visualization tools, molecular and imaging data, and signatures. By assembling an integrated picture of the range of responses of human cells exposed to many perturbations, the LINCS program aims to better understand human disease and to advance the development of new therapies. Perturbations under study include drugs, genetic perturbations, tissue micro-environments, antibodies, and disease-causing mutations. Responses to perturbations are measured by transcript profiling, mass spectrometry, cell imaging, and biochemical methods, among other assays. The LINCS program focuses on cellular physiology shared among tissues and cell types relevant to an array of diseases, including cancer, heart disease, and neurodegenerative disorders. This Perspective describes LINCS technologies, datasets, tools, and approaches to data accessibility and reusability.

Berkson error adjustment and other exposure surrogates in occupational case-control studies, with application to the Canadian INTEROCC study.

Many epidemiological studies assessing the relationship between exposure and disease are carried out without data on individual exposures. When this barrier is encountered in occupational studies, the subject exposures are often evaluated with a job-exposure matrix (JEM), which consists of mean exposure for occupational categories measured on a comparable group of workers. One of the objectives of the seven-country case-control study of occupational exposure and brain cancer risk, INTEROCC, was to investigate the relationship of occupational exposure to electromagnetic fields (EMF) in different frequency ranges and brain cancer risk. In this paper, we use the Canadian data from INTEROCC to estimate the odds of developing brain tumours due to occupational exposure to EMF. The first step was to find the best EMF exposure surrogate among the arithmetic mean, the geometric mean, and the mean of log-normal exposure distribution for each occupation in the JEM, in comparison to Berkson error adjustments via numerical approximation of the likelihood function. Contrary to previous studies of Berkson errors in JEMs, we found that the geometric mean was the best exposure surrogate. This analysis provided no evidence that cumulative lifetime exposure to extremely low frequency magnetic fields increases brain cancer risk, a finding consistent with other recent epidemiological studies.

A probabilistic approach for lateralization of seizure onset zone in drug-resistant epilepsy with bilateral cerebral pathology.

BACKGROUND: Lateralization of seizure-onset zone (SOZ) during electroencephalography (EEG) monitoring in people with bilateral potentially epileptogenic lesions is important to facilitate clinical decision making for resective surgery. METHODS: We develop two Bayesian approaches for estimating the number of consecutive ipsilateral seizures required to lateralize the SOZ to a given lower limit of 95% credible interval (LLI, assuming continuous prior distribution), or to a given posterior probability (assuming mixture of discrete and continuous prior probabilities). RESULTS: With estimation approach, if both the cerebral hemispheres are a priori equi-probable to contain SOZ, then using Jeffrey's prior, a minimum of 9, 18, and 38 consecutive ipsilateral seizures will yield an LLI of 0.81, 0.90, and 0.95 respectively. If one of the hemisphere is a priori more likely to have SOZ, then prior beta distributions with α=3, ß=2, and α=4, ß=3 will require a minimum of 18 and 24 consecutive ipsilateral seizures to yield an LLI of 0.80. Contrariwise, the testing approach allows approximation of the number of consecutive ipsilateral seizures to lateralize the SOZ depending on an estimate of prior probability of lateralized SOZ, to a desired posterior probability. For a prior probability of 0.5, using uniform prior, mixture model will require 7, 17, and 37 consecutive ipsilateral seizures to lateralize the SOZ with a posterior probability of 0.8, 0.9, and 0.95 respectively. CONCLUSION: While the reasoning presented here is based on probability theory, it is hoped that it may help clinical decision making and stimulate further validation with actual clinical data.

Generalized random set framework for functional enrichment analysis using primary genomics datasets.

MOTIVATION: Functional enrichment analysis using primary genomics datasets is an emerging approach to complement established methods for functional enrichment based on predefined lists of functionally related genes. Currently used methods depend on creating lists of 'significant' and 'non-significant' genes based on ad hoc significance cutoffs. This can lead to loss of statistical power and can introduce biases affecting the interpretation of experimental results. RESULTS: We developed and validated a new statistical framework, generalized random set (GRS) analysis, for comparing the genomic signatures in two datasets without the need for gene categorization. In our tests, GRS produced correct measures of statistical significance, and it showed dramatic improvement in the statistical power over other methods currently used in this setting. We also developed a procedure for identifying genes driving the concordance of the genomics profiles and demonstrated a dramatic improvement in functional coherence of genes identified in such analysis. AVAILABILITY: GRS can be downloaded as part of the R package CLEAN from http://ClusterAnalysis.org/. An online implementation is available at http://GenomicsPortals.org/.

A semi-parametric Bayesian model for unsupervised differential co-expression analysis.

BACKGROUND: Differential co-expression analysis is an emerging strategy for characterizing disease related dysregulation of gene expression regulatory networks. Given pre-defined sets of biological samples, such analysis aims at identifying genes that are co-expressed in one, but not in the other set of samples. RESULTS: We developed a novel probabilistic framework for jointly uncovering contexts (i.e. groups of samples) with specific co-expression patterns, and groups of genes with different co-expression patterns across such contexts. In contrast to current clustering and bi-clustering procedures, the implicit similarity measure in this model used for grouping biological samples is based on the clustering structure of genes within each sample and not on traditional measures of gene expression level similarities. Within this framework, biological samples with widely discordant expression patterns can be placed in the same context as long as the co-clustering structure of genes is concordant within these samples. To the best of our knowledge, this is the first method to date for unsupervised differential co-expression analysis in this generality. When applied to the problem of identifying molecular subtypes of breast cancer, our method identified reproducible patterns of differential co-expression across several independent expression datasets. Sample groupings induced by these patterns were highly informative of the disease outcome. Expression patterns of differentially co-expressed genes provided new insights into the complex nature of the ERalpha regulatory network. CONCLUSIONS: We demonstrated that the use of the co-clustering structure as the similarity measure in the unsupervised analysis of sample gene expression profiles provides valuable information about expression regulatory networks.

Effect of lot variability on ultraviolet radiation inactivation kinetics of Cryptosporidium parvum oocysts.

Numerous studies have demonstrated the efficiency of ultraviolet (UV) radiation for the inactivation of oocysts of Cryptosporidium parvum. In these studies inactivation is measured as reduction in oocysts. A primary goal is to estimate the UV radiation required to achieve a high degree of inactivation. Different lots of Cryptosporidium parvum oocysts are used in these studies, and the inactivation rate may vary depending on the lot of oocysts used. The goal of this paper is to account for the error in estimating the amount of inactivation after exposure to UV radiation, and for the effect of lot variability in determining the required UV radiation. A Bayesian approach is used to simultaneously model the logistic dose-response model and the UV inactivation kinetic model. The oocysts lot variability is incorporated using a hierarchical Bayesian model. Posterior distributions using Markov Chain Monte Carlo method is used to obtain estimates and Bayesian credible interval for the required UV radiation to achieve a given inactivation level of Cryptosporidium parvum oocysts.