TY - GEN
T1 - Detecting disease associated genes and gene-gene interactions with penalized AUC maximization
AU - Liu, Zhenqiu
PY - 2008
Y1 - 2008
N2 - In an association study, empirical evidences support the commonality of gene-gene interactions. Although genetic factors play an important role in many human diseases, multiple genes or genes and environmental factors may ultimately influence individual risk for these disease. However, such interactions are difficult to detect. In this paper, we propose a penalized area under ROC curve (AUC) maximization (LpAUC) to detect gene-gene interactions. The proposed approach is demonstrated by a simulation study and real data analysis. Analyses of both real data and simulated data show the effectiveness of our approach.
AB - In an association study, empirical evidences support the commonality of gene-gene interactions. Although genetic factors play an important role in many human diseases, multiple genes or genes and environmental factors may ultimately influence individual risk for these disease. However, such interactions are difficult to detect. In this paper, we propose a penalized area under ROC curve (AUC) maximization (LpAUC) to detect gene-gene interactions. The proposed approach is demonstrated by a simulation study and real data analysis. Analyses of both real data and simulated data show the effectiveness of our approach.
UR - http://www.scopus.com/inward/record.url?scp=60649088245&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=60649088245&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2008.145
DO - 10.1109/ICMLA.2008.145
M3 - Conference contribution
AN - SCOPUS:60649088245
SN - 9780769534954
T3 - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
SP - 599
EP - 603
BT - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
T2 - 7th International Conference on Machine Learning and Applications, ICMLA 2008
Y2 - 11 December 2008 through 13 December 2008
ER -