TY - GEN
T1 - Learning schizophrenia imaging genetics data via Multiple Kernel Canonical Correlation Analysis
AU - Richfield, Owen
AU - Alam, Md Ashad
AU - Calhoun, Vince
AU - Wang, Yu Ping
N1 - Funding Information:
The authors wish to thank the NIH (R01 GM109068, R01 MH104680, R01 MH107354) and NSF (1539067) for support
Publisher Copyright:
© 2016 IEEE.
PY - 2017/1/17
Y1 - 2017/1/17
N2 - Kernel and Multiple Kernel Canonical Correlation Analysis (CCA) are employed to classify schizophrenic and healthy patients based on their SNPs, DNA Methylation and fMRI data. Kernel and Multiple Kernel CCA are popular methods for finding nonlinear correlations between high-dimensional datasets. Data was gathered from 183 patients, 79 with schizophrenia and 104 healthy controls. Kernel and Multiple Kernel CCA represent new avenues for studying schizophrenia, because, to our knowledge, these methods have not been used on these data before. Classification is performed via k nearest neighbors on the kernel matrix outputs of the Kernel and Multiple Kernel CCA algorithm. Accuracies of the Kernel and Multiple Kernel CCA classification are compared to that of the regularized linear CCA algorithm classification, and are found to be significantly more accurate. Both algorithms demonstrate maximal accuracies when the combination of DNA methylation and fMRI data are used, and experience lower accuracies when the SNP data are incorporated.
AB - Kernel and Multiple Kernel Canonical Correlation Analysis (CCA) are employed to classify schizophrenic and healthy patients based on their SNPs, DNA Methylation and fMRI data. Kernel and Multiple Kernel CCA are popular methods for finding nonlinear correlations between high-dimensional datasets. Data was gathered from 183 patients, 79 with schizophrenia and 104 healthy controls. Kernel and Multiple Kernel CCA represent new avenues for studying schizophrenia, because, to our knowledge, these methods have not been used on these data before. Classification is performed via k nearest neighbors on the kernel matrix outputs of the Kernel and Multiple Kernel CCA algorithm. Accuracies of the Kernel and Multiple Kernel CCA classification are compared to that of the regularized linear CCA algorithm classification, and are found to be significantly more accurate. Both algorithms demonstrate maximal accuracies when the combination of DNA methylation and fMRI data are used, and experience lower accuracies when the SNP data are incorporated.
UR - http://www.scopus.com/inward/record.url?scp=85013347585&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85013347585&partnerID=8YFLogxK
U2 - 10.1109/BIBM.2016.7822570
DO - 10.1109/BIBM.2016.7822570
M3 - Conference contribution
AN - SCOPUS:85013347585
T3 - Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016
SP - 507
EP - 511
BT - Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016
A2 - Burrage, Kevin
A2 - Zhu, Qian
A2 - Liu, Yunlong
A2 - Tian, Tianhai
A2 - Wang, Yadong
A2 - Hu, Xiaohua Tony
A2 - Jiang, Qinghua
A2 - Song, Jiangning
A2 - Morishita, Shinichi
A2 - Burrage, Kevin
A2 - Wang, Guohua
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016
Y2 - 15 December 2016 through 18 December 2016
ER -