The Correlation-Base-Selection Algorithm for Diagnostic Schizophrenia Based on Blood-Based Gene Expression Signatures

Microarray analysis of gene expression is often used to diagnose different types of disease. Many studies report remarkable achievements in nervous system disease. Clinical diagnosis of schizophrenia (SCZ) still depends on doctors' experience, which is unreliable and needs to be more objective and quantified. To solve this problem, we collected whole blood gene expression data from four studies, including 152 individuals with schizophrenia (SCZ) and 138 normal controls in different regions. The correlation-based feature selection (CFS, one of the machine learning methods) algorithm was applied in this study, and 103 significantly differentially expressed genes between patients and controls, called “feature genes,” were selected; then, a model for SCZ diagnosis was built. The samples were subdivided into 10 groups, and cross-validation showed that the model we constructed achieved nearly 100% classification accuracy. Mathematical evaluation of the datasets before and after data processing proved the effectiveness of our algorithm. Feature genes were enriched in Parkinson's disease, oxidative phosphorylation, and TGF-beta signaling pathways, which were previously reported to be associated with SCZ. These results suggest that the analysis of gene expression in whole blood by our model could be a useful tool for diagnosing SCZ.

[1]  K. Ohi,et al.  The regulation of gene expression involved in TGF-β signaling by ZNF804A, a risk gene for schizophrenia , 2013, Schizophrenia Research.

[2]  R. Płoski,et al.  Possible Association between Suicide Committed under Influence of Ethanol and a Variant in the AUTS2 Gene , 2013, PloS one.

[3]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[4]  Toshiyuki Someya,et al.  Diagnostic classification of schizophrenia by neural network analysis of blood-based gene expression signatures , 2010, Schizophrenia Research.

[5]  Steve Horvath,et al.  WGCNA: an R package for weighted correlation network analysis , 2008, BMC Bioinformatics.

[6]  R. Tibshirani,et al.  Diagnosis of multiple cancer types by shrunken centroids of gene expression , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Toshiro K. Ohsumi,et al.  Sequencing Chromosomal Abnormalities Reveals Neurodevelopmental Loci that Confer Risk across Diagnostic Boundaries , 2012, Cell.

[8]  Ulrich Stephani,et al.  Genome-Wide Copy Number Variation in Epilepsy: Novel Susceptibility Loci in Idiopathic Generalized and Focal Epilepsies , 2010, PLoS genetics.

[9]  S. Libutti,et al.  Three-gene molecular diagnostic model for thyroid cancer. , 2011, Thyroid : official journal of the American Thyroid Association.

[10]  S. Kantarci,et al.  De novo single exon deletion of AUTS2 in a patient with speech and language disorder: A review of disrupted AUTS2 and further evidence for its role in neurodevelopmental disorders , 2014, American journal of medical genetics. Part A.

[11]  Phayung Meesad,et al.  Efficient Feature Selection Model for Gene Expression Data , 2011 .

[12]  Li-Yeh Chuang,et al.  A hybrid feature selection method for DNA microarray data , 2011, Comput. Biol. Medicine.

[13]  Mark A. Hall,et al.  Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning , 1999, ICML.

[14]  P. Stankiewicz,et al.  Detection of copy-number variation in AUTS2 gene by targeted exonic array CGH in patients with developmental delay and autistic spectrum disorders , 2012, European Journal of Human Genetics.

[15]  H. Lane,et al.  Decreased mRNA expression for the two subunits of system xc(-), SLC3A2 and SLC7A11, in WBC in patients with schizophrenia: Evidence in support of the hypo-glutamatergic hypothesis of schizophrenia. , 2016, Journal of psychiatric research.

[16]  L-Y Chuang,et al.  Correlation-based Gene Selection and Classification Using Taguchi-BPSO , 2010, Methods of Information in Medicine.

[17]  C. Spencer,et al.  Identification of loci associated with schizophrenia by genome-wide association and follow-up , 2008, Nature Genetics.

[18]  Zhaoxia Yu,et al.  SNP-based pathway enrichment analysis for genome-wide association studies , 2011, BMC Bioinformatics.

[19]  Katarzyna Chawarska,et al.  Molecular cytogenetic analysis and resequencing of contactin associated protein-like 2 in autism spectrum disorders. , 2008, American journal of human genetics.

[20]  Carlos S. Moreno,et al.  Relative Burden of Large CNVs on a Range of Neurodevelopmental Phenotypes , 2011, PLoS genetics.

[21]  B. Rund.  Is schizophrenia a neurodegenerative disorder? , 2009, Nordic journal of psychiatry.

[22]  Mohamad Saad,et al.  Genetic comorbidities in Parkinson's disease. , 2014, Human molecular genetics.

[23]  W. Maier,et al.  The functional coding variant Asn107Ile of the neuropeptide S receptor gene (NPSR1) is associated with schizophrenia and modulates verbal memory and the acoustic startle response. , 2012, The international journal of neuropsychopharmacology.

[24]  L. Sun,et al.  Gene expression profiling in peripheral blood mononuclear cells of early-onset schizophrenia , 2015, Genomics data.

[25]  E. Domany,et al.  Gene expression signature is shared by patients with Alzheimer’s disease and schizophrenia at the superior temporal gyrus , 2011, European journal of neurology.

[26]  F. Turkheimer,et al.  Imaging Translocator Protein (TSPO) in Subjects at High Risk of Psychosis and in Schizophrenia: An \[\11C] PBR28 Pet Brain Imaging Study , 2015 .

[27]  M. Tsuang,et al.  Negative Symptoms of Psychosis Correlate with Gene Expression of the Wnt/β-Catenin Signaling Pathway in Peripheral Blood , 2013, Psychiatry journal.

[28]  René S. Kahn,et al.  A Gene Co-Expression Network in Whole Blood of Schizophrenia Patients Is Independent of Antipsychotic-Use and Enriched for Brain-Expressed Genes , 2012, PloS one.

[29]  D. Dix,et al.  Effects of storage, RNA extraction, genechip type, and donor sex on gene expression profiling of human whole blood. , 2007, Clinical chemistry.

[30]  David B. Goldstein,et al.  A Genome-Wide Investigation of SNPs and CNVs in Schizophrenia , 2009, PLoS genetics.