This Title All WIREs
How to cite this WIREs title:
WIREs Comp Stat

Multiscalar genetic pathway modeling with hybrid Bayesian networks

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract Bayesian network modeling of real world datasets is often complicated by the fact that they are hybrid datasets that contain both discrete and continuous variables. For example, recent advances in high throughput biotechnologies have made it possible to generate large‐scale data across multiple biological scales—from discrete variables such as DNA variations to continuous variables such as omics traits and disease phenotypes. Such large heterogeneous and multiscalar datasets present a great challenge for biological knowledge discovery. Here we discuss the Bayesian Network Webserver (http://compbio.uthsc.edu/BNW), a web‐based platform for creating hybrid Bayesian network models, and its use in discovering causal relationships from heterogeneous and multiscalar system genetics datasets. This article is categorized under: Statistical and Graphical Methods of Data Analysis > Analysis of High Dimensional Data Statistical Models > Bayesian Models Statistical Models > Graphical Models Applications of Computational Statistics > Computational and Molecular Biology
Conceptual demonstration of structure learning constraints in a genotype‐to‐phenotype pathway model. (a) Variables are separated into three tiers. Directed edges in the network model between variables in different tiers are allowed only if they point in the specified direction. (b) Screenshot of assignment of variables to tiers in BNW
[ Normal View | Magnified View ]
Bayesian network model connecting genotype (rs3653666) with an anxiety‐related activity phenotype (ACT0‐5). Cis‐regulated genes are shown with a green background, while trans‐regulated genes are shown with a blue background. The number next to each directed edge indicates the confidence in the edge based on model averaging of network structures. The edges connecting the genotype with the cis‐regulated genes Rfwd2 and Cacybp do not include model averaging scores as these edges were required to be in the network structure
[ Normal View | Magnified View ]
Genetic network modeling and probabilistic inference with BNW. (a) The network structure after structure learning with the constraints shown in Figure . (b) Effect of observational evidence of genotype on model predictions. (c) Effect of intervention on Trait 1 on the network structure and the distribution of downstream variables. Predicted distributions after observation of evidence in (b) or intervention in (c) are indicated with red lines, while the original distributions are shown in blue
[ Normal View | Magnified View ]

Browse by Topic

Applications of Computational Statistics > Computational and Molecular Biology
Statistical Models > Graphical Models
Statistical Models > Bayesian Models
Statistical and Graphical Methods of Data Analysis > Analysis of High Dimensional Data

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts