Authors:
Swetha S. Bobba
1
;
Amin Zollanvari
2
and
Gil Alterovitz
3
Affiliations:
1
Vignana Bharathi Institute of Technology, Harvard Medical School and Children’s Hospital Informatics Program at Harvard-MIT, India
;
2
Harvard Medical School, Children’s Hospital Informatics Program at Harvard-MIT and Partners Healthcare Center for Personalized Genetic Medicine, United States
;
3
Harvard Medical School, Children’s Hospital Informatics Program at Harvard-MIT, Partners Healthcare Center for Personalized Genetic Medicine and MIT, United States
Keyword(s):
Bayesian Theory, Gene Expression, Bipolar Disorder, External Cross-Validation.
Related
Ontology
Subjects/Areas/Topics:
Algorithms and Software Tools
;
Bioinformatics
;
Biomedical Engineering
;
Data Mining and Machine Learning
;
Genomics and Proteomics
Abstract:
Integrative approaches that incorporate multiple experiments have shown a potential application in the
discovery of disease-related attributes. This study presents a unique, data-driven, integrative, Bayesian
approach to merge gene expression data from various experiments into prognostic models and evaluate
them for the discovery of bipolar-related attributes. Two prognostic models were constructed: a singlystructured
Bayesian and a Bayesian multi-net model, which differentiated Bipolar disease state at a higher
level of abstraction. These prognostic models were evaluated to find the most common attributes
responsible for the disease and their AUROC, using external crossvalidation.
The multi-net model achieved an AUROC of 0.907 significantly outperforming the single-structured model
with an AUROC of 0.631. The study found six new genes and five chromosomal regions associated with
the bipolar state. Enrichment analysis performed in this study revealed biological concepts and proteins
responsible for the disease. We anticipate this method and results will be used in the future to integrate
information from multiple experiments for the same or related phenotypes of various diseases and also to
predict the disease state earlier.
(More)