Abstract
Schizophrenia is a complex and severe neurological disorder that affects lots of people worldwide. Despite its strong evidence of heritability revealed by lots of genetic studies, research for locating of schizophrenia associated genes remains frustrating as numerous efforts had failed to identify biomarkers that could strongly impact the diagnosis and prognosis of schizophrenia. The major challenge lies in the weak discrimination of single gene marker and the enormous number of gene variants that exist in human genome. In this paper we propose a hybrid feature selection method that utilizes the biological structural information of the gene variants to tackle this problem. A set of statistical techniques are developed to encourage the clustering of multiple informative SNP variants on the same gene, which boost the probability of finding biologically meaningful features and suppresses false discoveries. As a result, the proposed method achieves significantly better performance on a published schizophrenia human genome data set compared with previous studies, with an area-under-ROC-curve of 65% and an odd ratio of 2.82 (95%CI: 1.80 – 4.40). 36 gene markers are discovered to be associated with the onset of schizophrenia with many of which verified directly or indirectly by previous literature. The method proposed in this paper can be also adopted for efficient control of false discoveries in finding biomarkers from genomic data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Takahashi, S.: Heterogeneity of schizophrenia: Genetic and symptomatic factors. Am. J. Med. Genet. B Neuropsychiatr. Genet. 162B, 648–652 (2013)
Rethelyi, J.M., Benkovits, J., Bitter, I.: Genes and environments in schizophrenia: The different pieces of a manifold puzzle. Neurosci. Biobehav. Rev. 37, 2424–2437 (2013)
Purcell, S.M., Wray, N.R., Stone, J.L., Visscher, P.M., O’Donovan, M.C., Sullivan, P.F., Sklar, P.: Common polygenic variation contributes to risk of schizophrenia and bipolar disorder. Nature. 460, 748–752 (2009)
Shatz, C.J.: MHC class I: an unexpected role in neuronal plasticity. Neuron. 64, 40–45 (2009)
Kwon, E., Wang, W., Tsai, L.H.: Validation of schizophrenia-associated genes CSMD1, C10orf26, CACNA1C and TCF4 as miR-137 targets. Mol. Psychiatry 18, 11–12 (2013)
Shi, Y.Y., Li, Z.Q., Xu, Q., Wang, T., Li, T., et al.: Common variants on 8p12 and 1q24.2 confer risk of schizophrenia. Nature Genetics 43, 1224–1227 (2011)
Hall, H., Lawyer, G., Sillen, A., Jonsson, E.G., Agartz, I., Terenius, L., Arnborg, S.: Potential genetic variants in schizophrenia: a Bayesian analysis. World J. Biol. Psychiatry 8, 12–22 (2007)
Laywer, G., Nyman, H., Agartz, I., Arnborg, S., Jonsson, E.G., Sedvall, G.C., Hall, H.: Morphological correlates to cognitive dysfunction in schizophrenia as studied with Bayesian regression. BMC Psychiatry 6, 31 (2006)
Lawyer, G., Nesvag, R., Varnas, K., Frigessi, A., Agartz, I.: Investigating possible subtypes of schizophrenia patients and controls based on brain cortical thickness. Psychiatry Res. 164, 254–264 (2008)
Yang, H., Liu, J., Sui, J., Pearlson, G., Calhoun, V.D.: A Hybrid Machine Learning Method for Fusing fMRI and Genetic Data: Combining both Improves Classification of Schizophrenia. Front. Hum. Neurosci. 4, 192 (2010)
Yamada, K., Iwayama, Y., Hattori, E., Iwamoto, K., Toyota, T., Ohnishi, T., Ohba, H., Maekawa, M., Kato, T., Yoshikawa, T.: Genome-wide association study of schizophrenia in Japanese population. PLoS One 6, e20468 (2011)
Edgar, R., Domrachev, M., Lash, A.E.: Gene Expression Omnibus: NCBI gene expression and hybridization array data repository. Nucleic Acids Res. 30, 207–210 (2002)
Barrett, T., Wilhite, S.E., Ledoux, P., Evangelista, C., Kim, I.F., Tomashevsky, M., Marshall, K.A., Phillippy, K.H., Sherman, P.M., Holko, M., et al.: NCBI GEO: archive for functional genomics data sets–update. Nucleic Acids Res. 41, D991–995 (2013)
Sherry, S.T., Ward, M.H., Kholodov, M., Baker, J., Phan, L., Smigielski, E.M., Sirotkin, K.: dbSNP: the NCBI database of genetic variation. Nucleic Acids Res. 29, 308–311 (2001)
Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Amsterdam (2011). ISBN: 978-0-12-374856-0
Lei, Y., Liu, H.: Feature selection for high-dimensional data: A fast correlation-based filter solution. In Proc. Intl. Conf. Mach. Learn. 3, 856–863 (2003)
Benjamini, Y.: HochbergY: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Royal Stat. Soc. B 57(1), 289–300 (1995)
Manning, C.D., Raghavan, P., Schutze, M.: Introduction to Information Retrieval. Cambridge University Press (2008)
Fawcett, T.: An Introduction to ROC Analysis. Pattern Recognition Letters 7(8), 861–874 (2006)
Hakak, Y., Walker, J.R., Li, C., Wong, W.H., Davis, K.L., Buxbaum, J.D., et al.: Genome-wide expression analysis reveals dysregulation of myelination-related genes in chronic schizophrenia. Proc. Natl. Acad Sci. 98(8), 4746–4751 (2001)
Zong, M., Wu, X.G., Chan, C.W.L., Chio, M.Y., Chan, H.S., Tanner, J.A., Yu, S.: The Adaptor Function of TRAPPC2 in Mammalian TRAPPs Explains TRAPPC2-Associated SEDT and TRAPPC9-Associated Congenital Intellectual Disability. PLOS ONE 6(8), e23350 (2011)
Teixeira, A.L., et al.: Increased serum levels of CCL11/eotaxin in schizophrenia. Prog. Neuropsychopharmacol Biol. Psychiatry 32, 710–714 (2008)
Morawski, M., et al.: Tenascin-R promotes assembly of the extracellular matrix of perineuronal nets via clustering of aggrecan. Philos. Trans. R. Soc. Lond. B. Biol. Sci. 369 (2014)
Kahler, A.K., et al.: Candidate gene analysis of the human natural killer-1 carbohydrate pathway and perineuronal nets in schizophrenia: B3GAT2 is associated with disease risk and cortical surface area. Biol. Psychiatry 69, 90–96 (2011)
Lindor, N.M., Sobell, J.L., Heston, L.L., Thibodeau, S.N., Sommer, S.S.: Screening the dystrophin gene suggests a high rate of polymorphism in general but no exonic deletions in schizophrenics. American journal of medical genetics 54(1), 1–4 (1994)
Bowden, N.A., Weidenhofer, J., Scott, R.J., Schall, U., Todd, J., Michie, P.T., Tooney, P.A.: Preliminary investigation of gene expression profiles in peripheral blood lymphocytes in schizophrenia. Schizophrenia research 82(2), 175–183 (2006)
Hattori, K., Tanaka, H., Wakabayashi, C., Yamamoto, N., Uchiyama, H., Teraishi, T., et al.: Expression of Ca2+-dependent activator protein for secretion 2 is increased in the brains of schizophrenic patients. Prog. in Neuro-Psycho. & Biol. Psyc. 35(7), 1738–1743 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, Y., Zeng, Z., Cai, Y. (2015). Identification of Schizophrenia-Associated Gene Polymorphisms Using Hybrid Filtering Feature Selection with Structural Information. In: Yin, X., Ho, K., Zeng, D., Aickelin, U., Zhou, R., Wang, H. (eds) Health Information Science. HIS 2015. Lecture Notes in Computer Science(), vol 9085. Springer, Cham. https://doi.org/10.1007/978-3-319-19156-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-19156-0_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19155-3
Online ISBN: 978-3-319-19156-0
eBook Packages: Computer ScienceComputer Science (R0)