A unified model based multifactor dimensionality reduction framework for detecting gene–gene interactions

Yu, Wenbao,Lee, Seungyeoun,Park, Taesung Oxford University Press 2016 Bioinformatics Vol.32 No.17

<P>Motivation: Gene-gene interaction (GGI) is one of the most popular approaches for finding and explaining the missing heritability of common complex traits in genome-wide association studies. The multifactor dimensionality reduction (MDR) method has been widely studied for detecting GGI effects. However, there are several disadvantages of the existing MDR-based approaches, such as the lack of an efficient way of evaluating the significance of multi-locus models and the high computational burden due to intensive permutation. Furthermore, the MDR method does not distinguish marginal effects from pure interaction effects. Methods: We propose a two-step unified model based MDR approach (UM-MDR), in which, the significance of a multi-locus model, even a high-order model, can be easily obtained through a regression framework with a semi-parametric correction procedure for controlling Type I error rates. In comparison to the conventional permutation approach, the proposed semi-parametric correction procedure avoids heavy computation in order to achieve the significance of a multi-locus model. The proposed UM-MDR approach is flexible in the sense that it is able to incorporate different types of traits and evaluate significances of the existing MDR extensions. Results: The simulation studies and the analysis of a real example are provided to demonstrate the utility of the proposed method. UM-MDR can achieve at least the same power as MDR for most scenarios, and it outperforms MDR especially when there are some single nucleotide polymorphisms that only have marginal effects, which masks the detection of causal epistasis for the existing MDR approaches. Conclusions: UM-MDR provides a very good supplement of existing MDR method due to its efficiency in achieving significance for every multi-locus model, its power and its flexibility of handling different types of traits.</P>

Applying a modified AUC to gene ranking

Yu, Wenbao,Chang, Yuan-Chin Ivan,Park, Eunsik The Korean Statistical Society 2018 Communications for statistical applications and me Vol.25 No.3

High-throughput technologies enable the simultaneous evaluation of thousands of genes that could discriminate different subclasses of complex diseases. Ranking genes according to differential expression is an important screening step for follow-up analysis. Many statistical measures have been proposed for this purpose. A good ranked list should provide a stable rank (at least for top-ranked gene), and the top ranked genes should have a high power in differentiating different disease status. However, there is a lack of emphasis in the literature on ranking genes based on these two criteria simultaneously. To achieve the above two criteria simultaneously, we proposed to apply a previously reported metric, the modified area under the receiver operating characteristic cure, to gene ranking. The proposed ranking method is found to be promising in leading to a stable ranking list and good prediction performances of top ranked genes. The findings are illustrated through studies on both synthesized data and real microarray gene expression data. The proposed method is recommended for ranking genes or other biomarkers for high-dimensional omics studies.

A modified area under the ROC curve and its application to marker selection and classification

WenBao Yu,Yuan-chin Ivan Chang,Eun-Sik Park 한국통계학회 2014 Journal of the Korean Statistical Society Vol.43 No.2

sificationscores of a diseased subject is larger than that of a non-diseased subject for arandomly sampled pair of subjects. From the perspective of classification, we want to finda way to separate two groups as distinctly as possible via AUC. When the difference ofthe scores of a marker is small, its impact on classification is less important. Thus, a newdiagnostic/classification measure based on a modified area under the ROC curve (mAUC)is proposed, which is defined as a weighted sum of two AUCs, where the AUC with thesmaller difference is assigned a lower weight, and vice versa. Using mAUC is robust in thesense that mAUC gets larger as AUC gets larger as long as they are not equal. Moreover, inmany diagnostic situations, only a specific range of specificity is of interest. Under normaldistributions, we show that if the AUCs of two markers are within similar ranges, the largermAUC implies the larger partial AUC for a given specificity. This property of mAUC will helpto identify the marker with the higher partial AUC, even when the AUCs are similar. Twononparametric estimates of an mAUC and their variances are given.Wealso suggest the useof mAUC as the objective function for classification, and the use of the gradient Lasso algorithmfor classifier construction and marker selection. Application to simulation datasetsand real microarray gene expression datasets show that our method finds a linear classifierwith a higher ROC curve than some other existing linear classifiers, especially in the rangeof low false positive rates.

Gene-Gene Interaction Analysis for the Accelerated Failure Time Model Using a Unified Model-Based Multifactor Dimensionality Reduction Method

이승연,손동희,Wenbao Yu,박태성 한국유전체학회 2016 Genomics & informatics Vol.14 No.4

Although a large number of genetic variants have been identified to be associated with common diseases through genome-wide association studies, there still exits limitations in explaining the missing heritability. One approach to solving this missing heritability problem is to investigate gene-gene interactions, rather than a single-locus approach. For gene-gene interaction analysis, the multifactor dimensionality reduction (MDR) method has been widely applied, since the constructive induction algorithm of MDR efficiently reduces high-order dimensions into one dimension by classifying multi-level genotypes into high- and low-risk groups. The MDR method has been extended to various phenotypes and has been improved to provide a significance test for gene-gene interactions. In this paper, we propose a simple method, called accelerated failure time (AFT) UM-MDR, in which the idea of a unified model-based MDR is extended to the survival phenotype by incorporating AFT-MDR into the classification step. The proposed AFT UM-MDR method is compared with AFT-MDR through simulation studies, and a short discussion is given.

Gene-Gene Interaction Analysis for the Accelerated Failure Time Model Using a Unified Model-Based Multifactor Dimensionality Reduction Method

Lee, Seungyeoun,Son, Donghee,Yu, Wenbao,Park, Taesung Korea Genome Organization 2016 Genomics & informatics Vol.14 No.4

Although a large number of genetic variants have been identified to be associated with common diseases through genome-wide association studies, there still exits limitations in explaining the missing heritability. One approach to solving this missing heritability problem is to investigate gene-gene interactions, rather than a single-locus approach. For gene-gene interaction analysis, the multifactor dimensionality reduction (MDR) method has been widely applied, since the constructive induction algorithm of MDR efficiently reduces high-order dimensions into one dimension by classifying multi-level genotypes into high- and low-risk groups. The MDR method has been extended to various phenotypes and has been improved to provide a significance test for gene-gene interactions. In this paper, we propose a simple method, called accelerated failure time (AFT) UM-MDR, in which the idea of a unified model-based MDR is extended to the survival phenotype by incorporating AFT-MDR into the classification step. The proposed AFT UM-MDR method is compared with AFT-MDR through simulation studies, and a short discussion is given.