An information-gain approach to detecting three-way epistatic interactions in genetic association studies

Hu, Ting; Chen, Yuanzhu Peter; Kiralis, Jeff; Collins, Ryan L.; Wejse, Christian; Sirugo, Giorgio; Williams, Scott M.; Moore, Jason H.

doi:10.1136/amiajnl-2012-001525

Cited by 75 publications

(71 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two metrics are chosen due to their wide applications in the literature, their effectiveness in high-dimensional binary data (Sebastiani & Ricerche, 2002;Sun & Wu, 2008), and also their distinct characteristics. The two metrics were previously used in several bio-data mining applications (Granizo-MacKenzie & Moore, 2013; Hu et al, 2013) and achieved good results. Figure 5 shows an overview of the proposed GP method.…”

Section: The Proposed Gp Approachmentioning

confidence: 87%

Improving feature ranking for biomarker discovery in proteomics mass spectrometry data using genetic programming

2014

View full text Add to dashboard Cite

Feature selection on mass spectrometry (MS) data is essential for improving classification performance and biomarker discovery. The number of MS samples is typically very small compared with the high dimensionality of the samples, which makes the problem of biomarker discovery very hard. In this paper, we propose the use of genetic programming for biomarker detection and classification of MS data. The proposed approach is composed of two phases: in the first phase, feature selection and ranking are performed. In the second phase, classification is performed. The results show that the proposed method can achieve better classification performance and biomarker detection rate than the information gain-(IG) based and the RELIEF feature selection methods. Meanwhile, four classifiers, Naive Bayes, J48 decision tree, random forest and support vector machines, are also used to further test the performance of the top ranked features. The results show that the four classifiers using the top ranked features from the proposed method achieve better performance than the IG and the RELIEF methods. Furthermore, GP also outperforms a genetic algorithm approach on most of the used data sets.

show abstract

Section: The Proposed Gp Approachmentioning

confidence: 87%

Improving feature ranking for biomarker discovery in proteomics mass spectrometry data using genetic programming

2014

View full text Add to dashboard Cite

show abstract

“…Specifically, we used a new measure of three-way epistasis that adjusts for lower-order effects 10. This approach was used to confirm high-order non-additive interactions.…”

Section: Methodsmentioning

confidence: 99%

Multifactor dimensionality reduction reveals a three-locus epistatic interaction associated with susceptibility to pulmonary tuberculosis

Collins

Wejse

et al. 2013

BioData Mining

Self Cite

View full text Add to dashboard Cite

BackgroundIdentifying high-order genetics associations with non-additive (i.e. epistatic) effects in population-based studies of common human diseases is a computational challenge. Multifactor dimensionality reduction (MDR) is a machine learning method that was designed specifically for this problem. The goal of the present study was to apply MDR to mining high-order epistatic interactions in a population-based genetic study of tuberculosis (TB).ResultsThe study used a previously published data set consisting of 19 candidate single-nucleotide polymorphisms (SNPs) in 321 pulmonary TB cases and 347 healthy controls from Guniea-Bissau in Africa. The ReliefF algorithm was applied first to generate a smaller set of the five most informative SNPs. MDR with 10-fold cross-validation was then applied to look at all possible combinations of two, three, four and five SNPs. The MDR model with the best testing accuracy (TA) consisted of SNPs rs2305619, rs187084, and rs11465421 (TA = 0.588) in PTX3, TLR9 and DC-Sign, respectively. A general 1000-fold permutation test of the null hypothesis of no association confirmed the statistical significance of the model (p = 0.008). An additional 1000-fold permutation test designed specifically to test the linear null hypothesis that the association effects are only additive confirmed the presence of non-additive (i.e. nonlinear) or epistatic effects (p = 0.013). An independent information-gain measure corroborated these results with a third-order epistatic interaction that was stronger than any lower-order associations.ConclusionsWe have identified statistically significant evidence for a three-way epistatic interaction that is associated with susceptibility to TB. This interaction is stronger than any previously described one-way or two-way associations. This study highlights the importance of using machine learning methods that are designed to embrace, rather than ignore, the complexity of common diseases such as TB. We recommend future studies of the genetics of TB take into account the possibility that high-order epistatic interactions might play an important role in disease susceptibility.

show abstract

“…Gene-gene and gene-environment interactions: A number of studies have suggested that TB susceptibility genes interact with each other (Table 1) [7, 20, 22, 25, 36, 37]. When interaction exists between two genes, it is possible that significant main effects may not be observed due to different allele frequencies at the second gene or environmental exposure [38].…”

Section: Previous Genetic Studies Of Tbmentioning

confidence: 99%

Genomics of Human Pulmonary Tuberculosis: from Genes to Pathways

et al. 2017

Self Cite

View full text Add to dashboard Cite

Purpose of review Tuberculosis (TB), caused by Mycobacterium tuberculosis (MTB), remains a major public health threat globally. Several lines of evidence support a role for host genetic factors in resistance/susceptibility to TB disease and MTB infection. However, results across candidate gene and genome-wide association studies (GWAS) are largely inconsistent, so a cohesive genetic model underlying TB risk has not emerged. Recent Findings Despite the difficulties in identifying consistent genetic associations, genetic studies of TB and MTB infection have revealed a few well-documented loci. These well validated genes are presented in this review, but there remains a large gap in how these genes translate into better understanding of TB. To address this, we present a pathway based extension of standard association analyses, seeding the results with the best validated genes from candidate gene and GWAS studies. Summary Several pathways were significantly enriched using pathway analyses that may help to explain population patterns of TB risk. In conclusion, we advocate for novel approaches to the study of host genetic analysis of TB that extend traditional association approaches.

show abstract

An information-gain approach to detecting three-way epistatic interactions in genetic association studies

Cited by 75 publications

References 41 publications

Improving feature ranking for biomarker discovery in proteomics mass spectrometry data using genetic programming

Improving feature ranking for biomarker discovery in proteomics mass spectrometry data using genetic programming

Multifactor dimensionality reduction reveals a three-locus epistatic interaction associated with susceptibility to pulmonary tuberculosis

Genomics of Human Pulmonary Tuberculosis: from Genes to Pathways

Contact Info

Product

Resources

About