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 singly-structured 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 cross-validation. 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. 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.
| Original language | English |
|---|---|
| Title of host publication | 2014 IEEE Healthcare Innovation Conference, HIC 2014 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 247-250 |
| Number of pages | 4 |
| ISBN (Print) | 9781467363648 |
| DOIs | |
| Publication status | Published - Feb 10 2014 |
| Externally published | Yes |
| Event | 2014 IEEE Healthcare Innovation Conference, HIC 2014 - Seattle, United States Duration: Oct 8 2014 → Oct 10 2014 |
Other
| Other | 2014 IEEE Healthcare Innovation Conference, HIC 2014 |
|---|---|
| Country | United States |
| City | Seattle |
| Period | 10/8/14 → 10/10/14 |
Fingerprint
ASJC Scopus subject areas
- Medicine(all)
- Biomedical Engineering
Cite this
Bayesian prognostic model for genomic discovery in bipolar disorder. / Bobba, Swetha S.; Zollanvari, Amin; Alterovitz, Gil.
2014 IEEE Healthcare Innovation Conference, HIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 247-250 7038921.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Bayesian prognostic model for genomic discovery in bipolar disorder
AU - Bobba, Swetha S.
AU - Zollanvari, Amin
AU - Alterovitz, Gil
PY - 2014/2/10
Y1 - 2014/2/10
N2 - 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 singly-structured 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 cross-validation. 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. 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.
AB - 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 singly-structured 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 cross-validation. 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. 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.
UR - http://www.scopus.com/inward/record.url?scp=84949923133&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949923133&partnerID=8YFLogxK
U2 - 10.1109/HIC.2014.7038921
DO - 10.1109/HIC.2014.7038921
M3 - Conference contribution
SN - 9781467363648
SP - 247
EP - 250
BT - 2014 IEEE Healthcare Innovation Conference, HIC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
ER -