A Correlation Analysis between SNPs and ROIs of Alzheimer’s Disease Based on Deep Learning

Abstract

Motivation. At present, the research methods for image genetics of Alzheimer’s disease based on machine learning are mainly divided into three steps: the first step is to preprocess the original image and gene information into digital signals that are easy to calculate; the second step is feature selection aiming at eliminating redundant signals and obtain representative features; and the third step is to build a learning model and predict the unknown data with regression or bivariate correlation analysis. This type of method requires manual extraction of feature single-nucleotide polymorphisms (SNPs), and the extraction process relies on empirical knowledge to a certain extent, such as linkage imbalance and gene function information in a group sparse model, which puts forward certain requirements for applicable scenarios and application personnel. To solve the problems of insufficient biological significance and large errors in the previous methods of association analysis and disease diagnosis, this paper presents a method of correlation analysis and disease diagnosis between SNP and region of interest (ROI) based on a deep learning model. It is a data-driven method, which has no obvious feature selection process. Results. The deep learning method adopted in this paper has no obvious feature extraction process relying on prior knowledge and model assumptions. From the results of correlation analysis between SNP and ROI, this method is complementary to other regression model methods in application scenarios. In order to improve the disease diagnosis performance of deep learning, we use the deep learning model to integrate SNP characteristics and ROI characteristics. The SNP feature, ROI feature, and SNP-ROI joint feature were input into the deep learning model and trained by cross-validation technique. The experimental results show that the SNP-ROI joint feature describes the information of the samples from different angles, which makes the diagnosis accuracy higher.

Deep Learning with Neuroimaging and Genomics in Alzheimer’s Disease

“…As described in the following subsections, there are some studies for AD research with genomics data using various deep learning models (Table 1), including the prediction of AD risk, the prediction of AD-specific nucleotide alteration sites (i.e., splicing sites), and the prediction of the virtual disease/molecular progress of AD. [41] FNNs Gene expression Predict AD risk Park, J. et al [42] GANs Gene expression Predict the virtual disease/molecular progress of AD Kim et al [43] Residual CNNs Gene expression Predict AD-specific nucleotide alteration sites (i.e., splicing sites) Park, C. et al [44] FNNs Gene expression, DNA methylation Predict AD risk Ju et al [45] Autoencoders MRI Predict early diagnosis of AD Shen et al [46] DBNs PET Distinguish AD from MCI Zhou, P. et al [47] Sparse-response DBNs PET, MRI Predict AD risk Ning et al [48] FNNs SNPs, MRI (brain measures) Predict AD risk Zhou, T. et al [49] Three-stage FNNs SNPs, ROIs in PET, ROIs in MRI Predict AD risk Zhou, J. et al [50] CNNs SNPs, ROIs in MRI Predict AD risk…”

“…Zhou, J. et al [ 50 ] employed a deep learning-based model to perform the prediction of AD risk using genetic variants (i.e., SNPs) and neuroimaging data (i.e., ROIs in MRI). Their deep learning-based model was established on the concept of CNNs (see Section 3.2.2 .).…”

“…Their results suggested that the performance for the integrated data of SNPs and ROIs (AUC = 0.8) was better than the one for SNP-only (AUC = 0.6) or ROIs-only (AUC = 0.77) [ 50 ]. Moreover, the proposed deep learning-based model surpassed various benchmarking machine learning models such as multivariate regression, ridge regression, group-sparse multi-task regression and feature selection, and multi-task feature learning [ 50 ]. Note that for the previous statement, no specific values for accuracy/AUC (i.e., only figures) were reported in their study.…”

“…The main limitation of the study by Zhou, J. et al [ 50 ] is that only single-modal brain imaging data, namely MRI, was examined and thereby other likely morphological changes from multimodal brain image data may be disregarded. Likewise, only one genomic component, namely SNPs, was considered and thereby other potential genomic effects may be overlooked.…”

Machine learning and deep learning-based approaches on various biomarkers for Alzheimer’s disease early detection: A review

“…Although ML and DL have achieved high precision at detecting AD with neuroimaging data, most of these approaches could lack the ability to discover the susceptibility of the disease early enough [16]. Therefore, some researchers have supported their analysis by including genetic data to other neuroimaging modalities [17]- [19] . This is because AD is considered as a complex disease with a genetic basis [20].…”