Identification of type 2 diabetes-associated combination of SNPs using support vector machine.

BACKGROUND: Type 2 diabetes mellitus (T2D), a metabolic disorder characterized by insulin resistance and relative insulin deficiency, is a complex disease of major public health importance. Its incidence is rapidly increasing in the developed countries. Complex diseases are caused by interactions between multiple genes and environmental factors. Most association studies aim to identify individual susceptibility single markers using a simple disease model. Recent studies are trying to estimate the effects of multiple genes and multi-locus in genome-wide association. However, estimating the effects of association is very difficult. We aim to assess the rules for classifying diseased and normal subjects by evaluating potential gene-gene interactions in the same or distinct biological pathways. RESULTS: We analyzed the importance of gene-gene interactions in T2D susceptibility by investigating 408 single nucleotide polymorphisms (SNPs) in 87 genes involved in major T2D-related pathways in 462 T2D patients and 456 healthy controls from the Korean cohort studies. We evaluated the support vector machine (SVM) method to differentiate between cases and controls using SNP information in a 10-fold cross-validation test. We achieved a 65.3% prediction rate with a combination of 14 SNPs in 12 genes by using the radial basis function (RBF)-kernel SVM. Similarly, we investigated subpopulation data sets of men and women and identified different SNP combinations with the prediction rates of 70.9% and 70.6%, respectively. As the high-throughput technology for genome-wide SNPs improves, it is likely that a much higher prediction rate with biologically more interesting combination of SNPs can be acquired by using this method. CONCLUSIONS: Support Vector Machine based feature selection method in this research found novel association between combinations of SNPs and T2D in a Korean population.

A pathway-based classification of breast cancer integrating data on differentially expressed genes, copy number variations and microRNA target genes.

Breast cancer is a clinically heterogeneous disease characterized by distinct molecular aberrations. Understanding the heterogeneity and identifying subgroups of breast cancer are essential to improving diagnoses and predicting therapeutic responses. In this paper, we propose a classification scheme for breast cancer which integrates data on differentially expressed genes (DEGs), copy number variations (CNVs) and microRNAs (miRNAs)-regulated mRNAs. Pathway information based on the estimation of molecular pathway activity is also applied as a postprocessor to optimize the classifier. A total of 250 malignant breast tumors were analyzed by k-means clustering based on the patterns of the expression profiles of 215 intrinsic genes, and the classification performances were compared with existing breast cancer classifiers including the BluePrint and the 625-gene classifier. We show that a classification scheme which incorporates pathway information with various genetic variations achieves better performance than classifiers based on the expression levels of individual genes, and propose that the identified signature serves as a basic tool for identifying rational therapeutic opportunities for breast cancer patients.

A large-scale genome-wide association study of Asian populations uncovers genetic factors influencing eight quantitative traits.

To identify genetic factors influencing quantitative traits of biomedical importance, we conducted a genome-wide association study in 8,842 samples from population-based cohorts recruited in Korea. For height and body mass index, most variants detected overlapped those reported in European samples. For the other traits examined, replication of promising GWAS signals in 7,861 independent Korean samples identified six previously unknown loci. For pulse rate, signals reaching genome-wide significance mapped to chromosomes 1q32 (rs12731740, P = 2.9 x 10(-9)) and 6q22 (rs12110693, P = 1.6 x 10(-9)), with the latter approximately 400 kb from the coding sequence of GJA1. For systolic blood pressure, the most compelling association involved chromosome 12q21 and variants near the ATP2B1 gene (rs17249754, P = 1.3 x 10(-7)). For waist-hip ratio, variants on chromosome 12q24 (rs2074356, P = 7.8 x 10(-12)) showed convincing associations, although no regional transcript has strong biological candidacy. Finally, we identified two loci influencing bone mineral density at multiple sites. On chromosome 7q31, rs7776725 (within the FAM3C gene) was associated with bone density at the radius (P = 1.0 x 10(-11)), tibia (P = 1.6 x 10(-6)) and heel (P = 1.9 x 10(-10)). On chromosome 7p14, rs1721400 (mapping close to SFRP4, a frizzled protein gene) showed consistent associations at the same three sites (P = 2.2 x 10(-3), P = 1.4 x 10(-7) and P = 6.0 x 10(-4), respectively). This large-scale GWA analysis of well-characterized Korean population-based samples highlights previously unknown biological pathways.

Gene-based single nucleotide polymorphisms and linkage disequilibrium patterns of 29 asthma candidate genes in the chromosome 5q31-33 region in Koreans.

BACKGROUND AND METHODS: Numerous genetic studies have mapped asthma susceptibility genes to a region on chromosome 5q31-33 in several populations. This region contains a cluster of cytokines and other immune-related genes important in immune response. In the present study, to determine the genetic variations and patterns of linkage disequilibrium (LD), we resequenced all the exons and promoter regions of the 29 asthma candidate genes in the chromosome 5q31-33 region. RESULTS: We identified a total of 314 genetic variants, including 289 single nucleotide polymorphisms (SNPs), 22 insertion/deletion polymorphisms and 3 microsatellites. Standardized variance data for allele frequency revealed substantial differences in SNP allele frequencies among different ethnic groups. Interestingly, significant ethnic differences were observed mainly in intron SNPs. LD block analysis using 174 common SNPs with a frequency of >10% disclosed strong LD within most candidate genes. No significant LD was observed across genes, except for one LD block (CD14-IK block). Gene-based haplotype analyses showed that 1-5 haplotype-tagging SNPs may be used to define the six or fewer common haplotypes with a frequency of >5%, regardless of the number of SNPs. CONCLUSION: Overall, our results provide useful information for the identification of immune-mediated disease genes in the chromosome 5q31-33 region, as well as valuable evidence for gene-based haplotype analysis in disease association studies.