A categorical network approach for discovering differentially expressed regulations in cancer.

BACKGROUND: The problem of efficient utilization of genome-wide expression profiles for identification and prediction of complex disease conditions is both important and challenging. Polygenic pathologies such as most types of cancer involve disregulation of many interacting genes which has prompted search for suitable statistical models for their representation. By accounting for changes in gene regulations between comparable conditions, graphical statistical models are expected to improve prediction precision. METHODS: In comparison problems with two or more experimental conditions, we represent the classes by categorical Bayesian networks that share one and the same graph structure but have class-specific probability parameters. The graph structure is learned by a score-based procedure that maximizes the difference between class probabilities using a suitable measure of divergence. The proposed framework includes an indirect model selection by adhering to a principle of optimal class separation and identifies interactions presenting significant difference between the compared conditions. RESULTS: We evaluate the performance of the new model against some benchmark algorithms such as support vector machine, penalized linear regression and linear Gaussian networks. The classifiers are compared by prediction accuracy across 15 different data sets from breast, lung, gastric and renal cancer studies. In addition to the demonstrated strong performance against the competitors, the proposed method is able to identify disease specific changes in gene regulations which are inaccessible by other approaches. The latter is illustrated by analyzing some gene interactions differentiating adenocarcinoma and squamous cell lung cancers.

A Gaussian Mixed Model for Learning Discrete Bayesian Networks.

In this paper we address the problem of learning discrete Bayesian networks from noisy data. Considered is a graphical model based on mixture of Gaussian distributions with categorical mixing structure coming from a discrete Bayesian network. The network learning is formulated as a Maximum Likelihood estimation problem and performed by employing an EM algorithm. The proposed approach is relevant to a variety of statistical problems for which Bayesian network models are suitable - from simple regression analysis to learning gene/protein regulatory networks from microarray data.

Genetics of brain fiber architecture and intellectual performance.

The study is the first to analyze genetic and environmental factors that affect brain fiber architecture and its genetic linkage with cognitive function. We assessed white matter integrity voxelwise using diffusion tensor imaging at high magnetic field (4 Tesla), in 92 identical and fraternal twins. White matter integrity, quantified using fractional anisotropy (FA), was used to fit structural equation models (SEM) at each point in the brain, generating three-dimensional maps of heritability. We visualized the anatomical profile of correlations between white matter integrity and full-scale, verbal, and performance intelligence quotients (FIQ, VIQ, and PIQ). White matter integrity (FA) was under strong genetic control and was highly heritable in bilateral frontal (a(2)=0.55, p=0.04, left; a(2)=0.74, p=0.006, right), bilateral parietal (a(2)=0.85, p<0.001, left; a(2)=0.84, p<0.001, right), and left occipital (a(2)=0.76, p=0.003) lobes, and was correlated with FIQ and PIQ in the cingulum, optic radiations, superior fronto-occipital fasciculus, internal capsule, callosal isthmus, and the corona radiata (p=0.04 for FIQ and p=0.01 for PIQ, corrected for multiple comparisons). In a cross-trait mapping approach, common genetic factors mediated the correlation between IQ and white matter integrity, suggesting a common physiological mechanism for both, and common genetic determination. These genetic brain maps reveal heritable aspects of white matter integrity and should expedite the discovery of single-nucleotide polymorphisms affecting fiber connectivity and cognition.

Brain fiber architecture, genetics, and intelligence: a high angular resolution diffusion imaging (HARDI) study.

We developed an analysis pipeline enabling population studies of HARDI data, and applied it to map genetic influences on fiber architecture in 90 twin subjects. We applied tensor-driven 3D fluid registration to HARDI, resampling the spherical fiber orientation distribution functions (ODFs) in appropriate Riemannian manifolds, after ODF regularization and sharpening. Fitting structural equation models (SEM) from quantitative genetics, we evaluated genetic influences on the Jensen-Shannon divergence (JSD), a novel measure of fiber spatial coherence, and on the generalized fiber anisotropy (GFA) a measure of fiber integrity. With random-effects regression, we mapped regions where diffusion profiles were highly correlated with subjects' intelligence quotient (IQ). Fiber complexity was predominantly under genetic control, and higher in more highly anisotropic regions; the proportion of genetic versus environmental control varied spatially. Our methods show promise for discovering genes affecting fiber connectivity in the brain.