Discovering Alzheimer Genetic Biomarkers Using Bayesian Networks

Abstract

Single nucleotide polymorphisms (SNPs) contribute most of the genetic variation to the human genome. SNPs associate with many complex and common diseases like Alzheimer's disease (AD). Discovering SNP biomarkers at different loci can improve early diagnosis and treatment of these diseases. Bayesian network provides a comprehensible and modular framework for representing interactions between genes or single SNPs. Here, different Bayesian network structure learning algorithms have been applied in whole genome sequencing (WGS) data for detecting the causal AD SNPs and gene-SNP interactions. We focused on polymorphisms in the top ten genes associated with AD and identified by genome-wide association (GWA) studies. New SNP biomarkers were observed to be significantly associated with Alzheimer's disease. These SNPs are rs7530069, rs113464261, rs114506298, rs73504429, rs7929589, rs76306710, and rs668134. The obtained results demonstrated the effectiveness of using BN for identifying AD causal SNPs with acceptable accuracy. The results guarantee that the SNP set detected by Markov blanket based methods has a strong association with AD disease and achieves better performance than both naïve Bayes and tree augmented naïve Bayes. Minimal augmented Markov blanket reaches accuracy of 66.13% and sensitivity of 88.87% versus 61.58% and 59.43% in naïve Bayes, respectively.

New Algorithm and Software (BNOmics) for Inferring and Visualizing Bayesian Networks from Heterogeneous Big Biological and Genetic Data

“…BNOmics has been very useful in our own research projects and collaborations. Currently, there is a substantial interest in applying systems biology thinking and analysis methods to the large-scale omics data (Qi et al, 2014; Agostinho et al, 2015; Sherif et al, 2015; Marini et al, 2015; Yin et al, 2015b; Kaiser et al, 2016). However, the assortment of workable systems biology data analysis tools is very limited especially if the ultimate goal is reverse engineering of biological networks from the massive flat datasets.…”

Geographical distribution of complement receptor type 1 variants and their associated disease risk

“…Further studies are warranted with increased sample sizes, to determine the role of CR1 in disease associations and pathogenesis mechanisms. [38] Malaria [36,37,40,42] Tuberculosis [46] Leprosy [47] rs17047661 (4841A>G) Sl1/Sl2 R1601G Sickle cell trait [38] Malaria [36,37,39,41,42,48] Tuberculosis [46] rs4844609 (4868T>A) Sl4/Sl5 T1610S Alzheimer disease [49][50][51][52] Cognitive decline [53,54] rs6691117 (4883A>G) KCAM +/-I1615V Erythrocyte Sedimentation Rate [55] Alzheimer Disease [56] Gastric cancer [57] Lung cancer [58] Glioblastoma multiforme [59]…”

Verification of Three-Phase Dependency Analysis Bayesian Network Learning Method for Maize Carotenoid Gene Mining

“…At present, the search scoring based method is mainly used in the gene mining research work. For example, using heuristic search of k2 algorithm to construct the network of gene locus and autologous stem cell transplant disease [ 21 ], using heuristic search method to get the obesity-related genetic variants [ 22 ], mining the genes related to smoking disease using the minimum description length principle (MDL) scoring search method [ 12 , 23 ], mining the genes related to wheat multiple quantitative trait using the Bayesian information criterion (BIC) scoring search method [ 24 ], discovering Alzheimer genetic biomarkers using tree augmented naive Bayes method [ 25 ], and using the scoring method for the detection of loci associated with human complex diseases (Han et al 2013).…”