Regularized Machine Learning in the Genetic Prediction of Complex Traits

Okser, Sebastian; Pahikkala, Tapio; Airola, Antti; Salakoski, Tapio; Ripatti, Samuli; Aittokallio, Tero

doi:10.1371/journal.pgen.1004754

Cited by 137 publications

(144 citation statements)

References 115 publications

(152 reference statements)

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…One group of methods builds regularized regression models based on established or suggestive trait loci. 6 In its simplest form, such a method selects independent SNPs reaching a pre-specified p value threshold. At each SNP, one allele is designated as the trait-increasing allele, while the other allele is a trait-decreasing allele.…”

Section: Introductionmentioning

confidence: 99%

Leveraging Multi-ethnic Evidence for Risk Assessment of Quantitative Traits in Minority Populations

Coram

Fang

Candille

et al. 2017

The American Journal of Human Genetics

View full text Add to dashboard Cite

An essential component of precision medicine is the ability to predict an individual's risk of disease based on genetic and non-genetic factors. For complex traits and diseases, assessing the risk due to genetic factors is challenging because it requires knowledge of both the identity of variants that influence the trait and their corresponding allelic effects. Although the set of risk variants and their allelic effects may vary between populations, a large proportion of these variants were identified based on studies in populations of European descent. Heterogeneity in genetic architecture underlying complex traits and diseases, while broadly acknowledged, remains poorly characterized. Ignoring such heterogeneity likely reduces predictive accuracy for minority individuals. In this study, we propose an approach, called XP-BLUP, which ameliorates this ethnic disparity by combining trans-ethnic and ethnic-specific information. We build a polygenic model for complex traits that distinguishes candidate trait-relevant variants from the rest of the genome. The set of candidate variants are selected based on studies in any human population, yet the allelic effects are evaluated in a population-specific fashion. Simulation studies and real data analyses demonstrate that XP-BLUP adaptively utilizes trans-ethnic information and can substantially improve predictive accuracy in minority populations. At the same time, our study highlights the importance of the continued expansion of minority cohorts.

show abstract

Section: Introductionmentioning

confidence: 99%

Leveraging Multi-ethnic Evidence for Risk Assessment of Quantitative Traits in Minority Populations

Coram

Fang

Candille

et al. 2017

The American Journal of Human Genetics

View full text Add to dashboard Cite

show abstract

“…These approaches can be classified into two groups:Methods that construct a model from genetic data in order to carry out accurate predictions on a phenotype4344454647484950515253545556.Methods that use machine learning to construct a statistical association test or rank genetic markers according to their predicted association with a phenotype30315758596061626364656667.…”

Section: Discussionmentioning

confidence: 99%

“…Methods that construct a model from genetic data in order to carry out accurate predictions on a phenotype4344454647484950515253545556.…”

Section: Discussionmentioning

confidence: 99%

Combining Multiple Hypothesis Testing with Machine Learning Increases the Statistical Power of Genome-wide Association Studies

Mieth

Kloft

Rodríguez

et al. 2016

Sci Rep

100

View full text Add to dashboard Cite

The standard approach to the analysis of genome-wide association studies (GWAS) is based on testing each position in the genome individually for statistical significance of its association with the phenotype under investigation. To improve the analysis of GWAS, we propose a combination of machine learning and statistical testing that takes correlation structures within the set of SNPs under investigation in a mathematically well-controlled manner into account. The novel two-step algorithm, COMBI, first trains a support vector machine to determine a subset of candidate SNPs and then performs hypothesis tests for these SNPs together with an adequate threshold correction. Applying COMBI to data from a WTCCC study (2007) and measuring performance as replication by independent GWAS published within the 2008–2015 period, we show that our method outperforms ordinary raw p-value thresholding as well as other state-of-the-art methods. COMBI presents higher power and precision than the examined alternatives while yielding fewer false (i.e. non-replicated) and more true (i.e. replicated) discoveries when its results are validated on later GWAS studies. More than 80% of the discoveries made by COMBI upon WTCCC data have been validated by independent studies. Implementations of the COMBI method are available as a part of the GWASpi toolbox 2.0.

show abstract

“…Many studies are nowadays making use of ML procedures in prediction and prognosis of complex traits [1], [2]. In particular, there is a huge investment of resources in cancer research since the identification of genetic signatures correlated with clinical outcome remains as a challenging task in clinical assistance [3], [4], [5], [6], [7] Nevertheless, the use of gene expression profiles in the estimation of prognosis models to find genetic signatures is a complex task in ML.…”

Section: Introductionmentioning

confidence: 99%

Machine learning models to search relevant genetic signatures in clinical context

Urda

Luque‐Baena

Franco

et al. 2017

2017 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-Clinicians are interested in the estimation of robust and relevant genetic signatures from gene sequencing data. Many machine learning approaches have been proposed trying to address well-known issues of this complex task (feature or gene selection, classification or model selection, and prediction assessment). Addressing this problem often requires a deep knowledge of these methods and some of them demand high computational resources that may not be affordable. In this paper, an exhaustive study that includes different types of feature selection methods and classifiers is presented, providing clinicians an useful insight of the most suitable methods for this purpose. Predictions assessment is performed using a bootstrap crossvalidation strategy as an honest validation scheme. The results of this study for six benchmark datasets show that filter or embedded methods are preferred, in general, to wrapper methods according to their better statistical significant results, in terms of accuracy, and lower demand for computational resources.

show abstract

Regularized Machine Learning in the Genetic Prediction of Complex Traits

Cited by 137 publications

References 115 publications

Leveraging Multi-ethnic Evidence for Risk Assessment of Quantitative Traits in Minority Populations

Leveraging Multi-ethnic Evidence for Risk Assessment of Quantitative Traits in Minority Populations

Combining Multiple Hypothesis Testing with Machine Learning Increases the Statistical Power of Genome-wide Association Studies

Machine learning models to search relevant genetic signatures in clinical context

Contact Info

Product

Resources

About