Dataset Information

Detecting PCOS susceptibility loci from genome-wide association studies via iterative trend correlation based feature screening.

ABSTRACT: BACKGROUND:Feature screening plays a critical role in handling ultrahigh dimensional data analyses when the number of features exponentially exceeds the number of observations. It is increasingly common in biomedical research to have case-control (binary) response and an extremely large-scale categorical features. However, the approach considering such data types is limited in extant literature. In this article, we propose a new feature screening approach based on the iterative trend correlation (ITC-SIS, for short) to detect important susceptibility loci that are associated with the polycystic ovary syndrome (PCOS) affection status by screening 731,442 SNP features that were collected from the genome-wide association studies. RESULTS:We prove that the trend correlation based screening approach satisfies the theoretical strong screening consistency property under a set of reasonable conditions, which provides an appealing theoretical support for its outperformance. We demonstrate that the finite sample performance of ITC-SIS is accurate and fast through various simulation designs. CONCLUSION:ITC-SIS serves as a good alternative method to detect disease susceptibility loci for clinic genomic data.

SUBMITTER: Dai X

PROVIDER: S-EPMC7199379 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Detecting PCOS susceptibility loci from genome-wide association studies via iterative trend correlation based feature screening.

Dai Xiaotian X Fu Guifang G Reese Randall R

BMC bioinformatics 20200504 1

<h4>Background</h4>Feature screening plays a critical role in handling ultrahigh dimensional data analyses when the number of features exponentially exceeds the number of observations. It is increasingly common in biomedical research to have case-control (binary) response and an extremely large-scale categorical features. However, the approach considering such data types is limited in extant literature. In this article, we propose a new feature screening approach based on the iterative trend cor ...[more]

PMID: 32366216

Similar Datasets

Project description:Ulcerative colitis (UC), a complex polygenic disorder, is one of the main subphenotypes of inflammatory bowel disease. A comprehensive dissection of the genetic etiology of UC needs to assess the contribution of rare genetic variants including copy number variations (CNVs) to disease risk. In this study, we performed a multi-step genome-wide case-control analysis to interrogate the presence of disease-relevant rare copy number variants.One thousand one hundred twenty-one German UC patients and 1770 healthy controls were initially screened for rare deletions and duplications employing SNP-array data. Quantitative PCR and high density custom array-CGH were used for validation of identified CNVs and fine mapping. Two main follow-up panels consisted of an independent cohort of 451 cases and 1274 controls, in which CNVs were assayed through quantitative PCR, and a British cohort of 2396 cases versus 4886 controls with CNV genotypes based on array data. Additional sample sets were assessed for targeted and in silico replication.Twenty-four rare copy number variants (14 deletions and 10 duplications), overrepresented in UC patients were identified in the initial screening panel. Follow-up of these CNV regions in four independent case-control series as well as an additional public in silico control group (totaling 4439 UC patients and 15,961 healthy controls) revealed three copy number variants enriched in UC patients; a 15.8 kb deletion upstream of ABCC4 and CLDN10 at13q32.1 (0.43% cases, 0.11% controls), a 119 kb duplication at 7p22.1, overlapping RNF216, ZNF815, OCM and CCZ1 (0.13% cases, 0.01% controls) and a 134 kb large duplication upstream of the KCNK9 gene at 8q24.3 (0.22% carriers among cases, 0.03% carriers among controls). The trend of association with UC was present after the P-values were corrected for combining data from different subpopulations. Break-point mapping of the deleted region suggested non-allelic homologous recombination as the mechanism underlying its formation.Our study presents a pragmatic approach for effective rare CNV screening of SNP-array data sets and implicates the potential contribution of rare structural variants in the pathogenesis of UC.

Project description:BACKGROUND: We introduce Iterative Feature Removal (IFR) as an unbiased approach for selecting features with diagnostic capacity from large data sets. The algorithm is based on recently developed tools in machine learning that are driven by sparse feature selection goals. When applied to genomic data, our method is designed to identify genes that can provide deeper insight into complex interactions while remaining directly connected to diagnostic utility. We contrast this approach with the search for a minimal best set of discriminative genes, which can provide only an incomplete picture of the biological complexity. RESULTS: Microarray data sets typically contain far more features (genes) than samples. For this type of data, we demonstrate that there are many equivalently-predictive subsets of genes. We iteratively train a classifier using features identified via a sparse support vector machine. At each iteration, we remove all the features that were previously selected. We found that we could iterate many times before a sustained drop in accuracy occurs, with each iteration removing approximately 30 genes from consideration. The classification accuracy on test data remains essentially flat even as hundreds of top-genes are removed.Our method identifies sets of genes that are highly predictive, even when comprised of genes that individually are not. Through automated and manual analysis of the selected genes, we demonstrate that the selected features expose relevant pathways that other approaches would have missed. CONCLUSIONS: Our results challenge the paradigm of using feature selection techniques to design parsimonious classifiers from microarray and similar high-dimensional, small-sample-size data sets. The fact that there are many subsets of genes that work equally well to classify the data provides a strong counter-result to the notion that there is a small number of "top genes" that should be used to build classifiers. In our results, the best classifiers were formed using genes with limited univariate power, thus illustrating that deeper mining of features using multivariate techniques is important.

Project description:Non-targeted mass spectrometry-based approaches for detecting novel xenobiotics in biological samples are hampered by the occurrence of naturally fluctuating endogenous substances, which are difficult to distinguish from environmental contaminants. Here, we investigate a data reduction strategy for datasets derived from a biological time series. The objective is to flag reoccurring peaks in the time series based on increasing peak intensities, thereby reducing peak lists to only those which may be associated with emerging bioaccumulative contaminants. As a result, compounds with increasing concentrations are flagged while compounds displaying random, decreasing, or steady-state time trends are removed. As an initial proof of concept, we created artificial time trends by fortifying human whole blood samples with isotopically labelled standards. Different scenarios were investigated: eight model compounds had a continuously increasing trend in the last two to nine time points, and four model compounds had a trend that reached steady state after an initial increase. Each time series was investigated at three fortification levels and one unfortified series. Following extraction, analysis by ultra performance liquid chromatography high-resolution mass spectrometry, and data processing, a total of 21,700 aligned peaks were obtained. Peaks displaying an increasing trend were filtered from randomly fluctuating peaks using time trend ratios and Spearman's rank correlation coefficients. The first approach was successful in flagging model compounds spiked at only two to three time points, while the latter approach resulted in all model compounds ranking in the top 11 % of the peak lists. Compared to initial peak lists, a combination of both approaches reduced the size of datasets by 80-85 %. Overall, non-target time trend screening represents a promising data reduction strategy for identifying emerging bioaccumulative contaminants in biological samples. Graphical abstract Using time trends to filter out emerging contaminants from large peak lists.

Dataset Information

Detecting PCOS susceptibility loci from genome-wide association studies via iterative trend correlation based feature screening.

Publications

Detecting PCOS susceptibility loci from genome-wide association studies via iterative trend correlation based feature screening.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets