Identifying diagnosis-specific genotype–phenotype associations via joint multitask sparse canonical correlation analysis and classification

Abstract

Motivation Brain imaging genetics studies the complex associations between genotypic data such as single nucleotide polymorphisms (SNPs) and imaging quantitative traits (QTs). The neurodegenerative disorders usually exhibit the diversity and heterogeneity, originating from which different diagnostic groups might carry distinct imaging QTs, SNPs and their interactions. Sparse canonical correlation analysis (SCCA) is widely used to identify bi-multivariate genotype–phenotype associations. However, most existing SCCA methods are unsupervised, leading to an inability to identify diagnosis-specific genotype–phenotype associations. Results In this article, we propose a new joint multitask learning method, named MT–SCCALR, which absorbs the merits of both SCCA and logistic regression. MT–SCCALR learns genotype–phenotype associations of multiple tasks jointly, with each task focusing on identifying one diagnosis-specific genotype–phenotype pattern. Meanwhile, MT–SCCALR cannot only select relevant SNPs and imaging QTs for each diagnostic group alone, but also allows the selection of those shared by multiple diagnostic groups. We derive an efficient optimization algorithm whose convergence to a local optimum is guaranteed. Compared with two state-of-the-art methods, MT–SCCALR yields better or similar canonical correlation coefficients and classification performances. In addition, it owns much better discriminative canonical weight patterns of great interest than competitors. This demonstrates the power and capability of MTSCCAR in identifying diagnostically heterogeneous genotype–phenotype patterns, which would be helpful to understand the pathophysiology of brain disorders. Availability and implementation The software is publicly available at https://github.com/dulei323/MTSCCALR. Supplementary information Supplementary data are available at Bioinformatics online.

An Improved Multi-Task Sparse Canonical Correlation Analysis of Imaging Genetics for Detecting Biomarkers of Alzheimer’s Disease

“…SCCA is a robust and scalable multiple association analysis algorithm, which has been widely used in the field of image genetics [2][3][4][5][6][7][8][9]. Compared with the constraints of existing methods, we propose an improved multi-task SCCA method.…”

“…Multi-task SCCA (multi-task-SCCA, MTSCCA) is recently proposed to study the genetic problems of multimodal imaging by jointly constructing multiple SCCA tasks in the literature [7]. The newly proposed MT-SCCALR [8] is superior to its sophisticated modeling strategy, which enables it to identify the characteristics of the diagnostic group and is of great significance for clinical research.…”

A single-mode associates global patterns of brain network structure and behavior across the human lifespan

“…For example, CCA has been generalized to higher-order models beyond 2 domains, similar to variations of Independent Component Analysis (joint- or linked-ICA; [117–119]. Imaging genetics is one of the fastest growing fields that are capitalizing the most on methods such as CCA especially requiring to combine multiple data domains [6,16,106,111,120,121]. These studies typically look at thousands of genetic markers from a single blood assay, similar to how a single MRI imaging session can be used to generate thousands of measures of brain structure and function.…”

Identifying Imaging Genetics Biomarkers of Alzheimer’s Disease by Multi-Task Sparse Canonical Correlation Analysis and Regression

“…To detect more complex and meaningful associations, studies to date have applied diagnostic information into SCCA methods (Yan et al, 2018;Du et al, 2020). Yan et al proposed an outcomerelevant SCCA model based on a subject similarity matrix (Yan et al, 2018).…”

“…Yan et al proposed an outcomerelevant SCCA model based on a subject similarity matrix (Yan et al, 2018). Du et al integrated multi-task SCCA and logistic regression in a sophisticated model to identify robust diseaserelated imaging and genetic patterns by incorporating diagnostic status information (Du et al, 2020). Classified diagnostic information, such as AD, mild cognitive impairment (MCI), and healthy control (HC), facilitates the association between SNPs and QTs; however, roughly dividing the disease stages does not provide any more accurate information than do continuous neuropsychological assessments measured from different angles.…”