贝叶斯网潜变量模型在抑郁患者单核苷酸多态性(SNPs)研究中的应用

Bayesian Network Latent Variable Model's Application in the Research of Single Nucleotide Polymorphism of Depression Patients

目的采用基于贝叶斯(Bayesian)网络的潜类模型进行高维度SNPs数据的分析,为复杂性状疾病遗传以及基因定位等方面的研究提供新的方法支持。方法采用Bayesian网络潜类模型对一组抑郁障碍性疾病的单核苷酸多态性SNPs检测数据进行分析,每个研究对象分别测量7个SNP,一共检测了801个个体。结果按照累计信息贡献率达到95%的原则,应用贝叶斯网络潜变量模型选出rs11568817和rs130058两个SNPs位点将研究对象分为2个潜在类别,各类别的概率分别为0.216和0.784,其中一类倾向于杂合子,一类倾向于纯合子。结论两个类别人群不同特征正是由于分类和解释两个类别的SNPs造成的,从而为进一步的研究SNPs是否为可疑致病位点提供依据。

Objective To use latent class model based on bayesian network to analyse the high-dimensional SNPs data, providing new methodology to the study of heredity and gene location of complex traints diseases. Methods Using latent class model based on bayesian network to analyse single nucleotide polymorphism data of depressive disorders. Each individual detect 7 SNPs and the total respondents is 807. Results According to the principle of accumulation information contribution rate reaching to 95% ,the model selects rs11568817 and rs130058. Individuals is divided into 2 latent classes and the probability of the 2 classes is 0. 216 and 0. 784. One class is inclined to heterozygote, the other is inclined to he- mozygote. Conclusion This difference is caused by the SNPs which are used to classify and interpreted the classes. So we have reasons to consider these SNPs are suspicious disease locus, which provide clear idea to the next researchl