TY - GEN
T1 - Predicting schizophrenia by fusing networks from SNPs, DNA methylation and fMRI data
AU - Deng, Su Ping
AU - Lin, Dongdong
AU - Calhoun, Vince D.
AU - Wang, Yu Ping
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/10/13
Y1 - 2016/10/13
N2 - In order to comprehensively utilize complementary information from multiple types of data for better disease diagnosis, in this study, we applied a network fusion based approach to integrating three types of data including genetic, epigenetic and neuroimaging data from a study of schizophrenia patients (SCZ). A network is a map of interactions, which contributes to investigating the connectivity of components or links between sub-units. We exploited the potential of using networks as features for discriminating SCZ from healthy controls. We first constructed a single network from each type of data. Then we built four fused networks by the network fusion method: three fused networks for each combination of two types of data and one fused network for all three data types. Based on the local consistency of network, we can predict the group of the unlabeled SCZ subjects. The group prediction method was applied to test the power of network-based features and the performance was evaluated by a 10-fold cross validation. The results show that the prediction accuracy is the highest when applying our prediction method to the fused network derived from three data types among 7 tested networks. As a conclusion, integrative approaches that can comprehensively utilize multiple types of data are more useful for diagnosis and prediction.
AB - In order to comprehensively utilize complementary information from multiple types of data for better disease diagnosis, in this study, we applied a network fusion based approach to integrating three types of data including genetic, epigenetic and neuroimaging data from a study of schizophrenia patients (SCZ). A network is a map of interactions, which contributes to investigating the connectivity of components or links between sub-units. We exploited the potential of using networks as features for discriminating SCZ from healthy controls. We first constructed a single network from each type of data. Then we built four fused networks by the network fusion method: three fused networks for each combination of two types of data and one fused network for all three data types. Based on the local consistency of network, we can predict the group of the unlabeled SCZ subjects. The group prediction method was applied to test the power of network-based features and the performance was evaluated by a 10-fold cross validation. The results show that the prediction accuracy is the highest when applying our prediction method to the fused network derived from three data types among 7 tested networks. As a conclusion, integrative approaches that can comprehensively utilize multiple types of data are more useful for diagnosis and prediction.
UR - http://www.scopus.com/inward/record.url?scp=85009143740&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85009143740&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2016.7590981
DO - 10.1109/EMBC.2016.7590981
M3 - Conference contribution
C2 - 28268598
AN - SCOPUS:85009143740
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 1447
EP - 1450
BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
Y2 - 16 August 2016 through 20 August 2016
ER -