Fast Multi-Task SCCA Learning with Feature Selection for Multi-Modal Brain Imaging Genetics

Lei Du, Kefei Liu, Xiaohui Yao, Shannon L. Risacher, Junwei Han, Lei Guo, Andrew J. Saykin, Li Shen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Brain imaging genetics studies the genetic basis of brain structures and functions via integrating both genotypic data such as single nucleotide polymorphism (SNP) and imaging quantitative traits (QTs). In this area, both multi-task learning (MTL) and sparse canonical correlation analysis (SCCA) method-s are widely used since they are superior to those independent and pairwise univariate analyses. MTL methods generally incorporate a few QTs and are not designed for feature selection from a large number of QTs; while existing SCCA methods typically employ only one modality of QTs to study its association with SNPs. Both MTL and SCCA encounter computational challenges as the number of SNPs increases. In this paper, combining the merits of MTL and SCCA, we propose a novel multi-task SCCA (MTSCCA) learning framework to identify bi-multivariate associations between SNPs and multi-modal imaging QTs. MTSCCA could make use of the complementary information carried by different imaging modalities. Using the G21-norm regularization, MTSCCA treats all SNPs in the same group together to enforce sparsity at the group level. The ℓ2,1-norm penalty is used to jointly select features across multiple tasks for SNPs, and across multiple modalities for QTs. A fast optimization algorithm is proposed using the grouping information of SNPs. Compared with conventional SCCA methods, MTSCCA obtains improved performance regarding both correlation coefficients and canonical weights patterns. In addition, our method runs very fast and is easy-to-implement, and thus could provide a powerful tool for genome-wide brain-wide imaging genetic studies.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
EditorsHarald Schmidt, David Griol, Haiying Wang, Jan Baumbach, Huiru Zheng, Zoraida Callejas, Xiaohua Hu, Julie Dickerson, Le Zhang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages356-361
Number of pages6
ISBN (Electronic)9781538654880
DOIs
StatePublished - Jan 21 2019
Externally publishedYes
Event2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 - Madrid, Spain
Duration: Dec 3 2018Dec 6 2018

Publication series

NameProceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

Conference

Conference2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
CountrySpain
CityMadrid
Period12/3/1812/6/18

Keywords

  • Brain Imaging Genetics
  • Multi-task SCCA
  • Sparse Canonical Correlation Analysis

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics

Fingerprint Dive into the research topics of 'Fast Multi-Task SCCA Learning with Feature Selection for Multi-Modal Brain Imaging Genetics'. Together they form a unique fingerprint.

  • Cite this

    Du, L., Liu, K., Yao, X., Risacher, S. L., Han, J., Guo, L., Saykin, A. J., & Shen, L. (2019). Fast Multi-Task SCCA Learning with Feature Selection for Multi-Modal Brain Imaging Genetics. In H. Schmidt, D. Griol, H. Wang, J. Baumbach, H. Zheng, Z. Callejas, X. Hu, J. Dickerson, & L. Zhang (Eds.), Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 (pp. 356-361). [8621298] (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2018.8621298