Uncovering complementary sets of variants for predicting quantitative phenotypes

Yilmaz, Serhan and Fakhouri, Mohamad and Koyuturk, Mehmet and Ercument Cicek, A. and Taştan, Öznur (2022) Uncovering complementary sets of variants for predicting quantitative phenotypes. Bioinformatics, 38 (4). pp. 908-917. ISSN 1367-4803 (Print) 1460-2059 (Online)

Full text not available from this repository. (Request a copy)


Motivation: Genome-wide association studies show that variants in individual genomic loci alone are not sufficient to explain the heritability of complex, quantitative phenotypes. Many computational methods have been developed to address this issue by considering subsets of loci that can collectively predict the phenotype. This problem can be considered a challenging instance of feature selection in which the number of dimensions (loci that are screened) is much larger than the number of samples. While currently available methods can achieve decent phenotype prediction performance, they either do not scale to large datasets or have parameters that require extensive tuning. Results: We propose a fast and simple algorithm, Macarons, to select a small, complementary subset of variants by avoiding redundant pairs that are likely to be in linkage disequilibrium. Our method features two interpretable parameters that control the time/performance trade-off without requiring parameter tuning. In our computational experiments, we show that Macarons consistently achieves similar or better prediction performance than state-ofthe- art selection methods while having a simpler premise and being at least two orders of magnitude faster. Overall, Macarons can seamlessly scale to the human genome with _107 variants in a matter of minutes while taking the dependencies between the variants into account.
Item Type: Article
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Öznur Taştan
Date Deposited: 22 Aug 2022 11:59
Last Modified: 22 Aug 2022 11:59
URI: https://research.sabanciuniv.edu/id/eprint/44179

Actions (login required)

View Item
View Item