Combination of G72 Genetic Variation and G72 Protein Level to Detect Schizophrenia: Machine Learning Approaches.

Eugene Lin,Hsien-Yuan Lane,Chiung-Hsien Huang,Yi-Lun Lai,Chieh-Hsin Lin,Yu-Jhen Huang

doi:10.3389/fpsyt.2018.00566

Abstract

The D-amino acid oxidase activator (DAOA, also known as G72) gene is a strong schizophrenia susceptibility gene. Higher G72 protein levels have been implicated in patients with schizophrenia. The current study aimed to differentiate patients with schizophrenia from healthy individuals using G72 single nucleotide polymorphisms (SNPs) and G72 protein levels by leveraging computational artificial intelligence and machine learning tools. A total of 149 subjects with 89 patients with schizophrenia and 60 healthy controls were recruited. Two G72 genotypes (including rs1421292 and rs2391191) and G72 protein levels were measured with the peripheral blood. We utilized three machine learning algorithms (including logistic regression, naive Bayes, and C4.5 decision tree) to build the optimal predictive model for distinguishing schizophrenia patients from healthy controls. The naive Bayes model using two factors, including G72 rs1421292 and G72 protein, appeared to be the best model for disease susceptibility (sensitivity = 0.7969, specificity = 0.9372, area under the receiver operating characteristic curve (AUC) = 0.9356). However, a model integrating G72 rs1421292 only slightly increased the discriminative power than a model with G72 protein alone (sensitivity = 0.7941, specificity = 0.9503, AUC = 0.9324). Among the three models with G72 protein alone, the naive Bayes with G72 protein alone had the best specificity (0.9503), while logistic regression with G72 protein alone was the most sensitive (0.8765). The findings remained similar after adjusting for age and gender. This study suggests that G72 protein alone, without incorporating the two G72 SNPs, may have been suitable enough to identify schizophrenia patients. We also recommend applying both naive Bayes and logistic regression models for the best specificity and sensitivity, respectively. Larger-scale studies are warranted to confirm the findings.

Highlights

Schizophrenia is a severe mental disorder characterized by symptoms such as delusions, hallucinations, blunted affect, impaired executive function, reduced motivation, and disorganized communication [1]
The results showed that the naive Bayes with G72 rs1421292 single nucleotide polymorphisms (SNPs) and G72 protein levels (Model 2) performed best among all models (Models 1–15)
The combination of G72 rs1421292 SNP and G72 protein levels was the best model using the C4.5 decision tree (Model 7) and logistic regression (Model 12). These results were consistent with another finding of this study; that is, G72 rs1421292 SNP was marginally associated with G72 protein levels (Table 5)

Summary

Introduction

Schizophrenia is a severe mental disorder characterized by symptoms such as delusions, hallucinations, blunted affect, impaired executive function, reduced motivation, and disorganized communication [1]. Converging evidence from genome-wide linkage studies, genetic case-control association studies, and genome-wide association studies indicate that several potential candidate genes are associated with schizophrenia [4]. More and more genetic studies have employed novel computational tools such as naive Bayes to conduct gene discovery and detect new gene loci associated with schizophrenia [5]. Identification of susceptibility genes for schizophrenia will help in early detection and prevention of high-risk individuals, as well as in developing novel therapies [6]. The D-amino-acid oxidase activator (DAOA, named G72) gene is one of the candidate genes

Methods

Results

Discussion

Conclusion