@article{ebf4510d776243baa02eb25a5ce93f39,
title = "A multi-trait multi-locus stepwise approach for conducting GWAS on correlated traits",
abstract = "The ability to accurately quantify the simultaneous effect of multiple genomic loci on multiple traits is now possible due to current and emerging high-throughput genotyping and phenotyping technologies. To date, most efforts to quantify these genotype-to-phenotype relationships have focused on either multi-trait models that test a single marker at a time or multi-locus models that quantify associations with a single trait. Therefore, the purpose of this study was to compare the performance of a multi-trait, multi-locus stepwise (MSTEP) model selection procedure we developed to (a) a commonly used multi-trait single-locus model and (b) a univariate multi-locus model. We used real marker data in maize (Zea mays L.) and soybean (Glycine max L.) to simulate multiple traits controlled by various combinations of pleiotropic and nonpleiotropic quantitative trait nucleotides (QTNs). In general, we found that both multi-trait models outperformed the univariate multi-locus model, especially when analyzing a trait of low heritability. For traits controlled by either a combination of pleiotropic and nonpleiotropic QTNs or a large number of QTNs (i.e., 50), our MSTEP model often outperformed at least one of the two alternative models. When applied to the analysis of two tocochromanol-related traits in maize grain, MSTEP identified the same peak-associated marker that has been reported in a previous study. We therefore conclude that MSTEP is a useful addition to the suite of statistical models that are commonly used to gain insight into the genetic architecture of agronomically important traits.",
author = "Fernandes, {Samuel B.} and Casstevens, {Terry M.} and Bradbury, {Peter J.} and Lipka, {Alexander E.}",
note = "Funding Information: We thank the editor, three anonymous reviewers, and Matthew D. Murphy for reading through the manuscript and providing suggestions that improved this work substantially. We also thank Prof. Rebecca Smith for providing suggestions and insights into the utility of ROC curves to assess the performance of stepwise models. This work was funded by the National Science Foundation Plant Genome Research Project, Grant Number 1733606 (SBF and AEL), the USDA-ARS (TMC and PJB), and the National Science Foundation, Integrative Organismal Systems, Grant Number 1822330 (TMC and PJB). Mention of trade names or commercial products in this publication is solely for the purpose of providing specific information and does not imply recommendation or endorsement by the USDA. The USDA is an equal opportunity provider and employer. Funding Information: We thank the editor, three anonymous reviewers, and Matthew D. Murphy for reading through the manuscript and providing suggestions that improved this work substantially. We also thank Prof. Rebecca Smith for providing suggestions and insights into the utility of ROC curves to assess the performance of stepwise models. This work was funded by the National Science Foundation Plant Genome Research Project, Grant Number 1733606 (SBF and AEL), the USDA‐ARS (TMC and PJB), and the National Science Foundation, Integrative Organismal Systems, Grant Number 1822330 (TMC and PJB). Mention of trade names or commercial products in this publication is solely for the purpose of providing specific information and does not imply recommendation or endorsement by the USDA. The USDA is an equal opportunity provider and employer. Publisher Copyright: {\textcopyright} 2022 The Authors. The Plant Genome published by Wiley Periodicals LLC on behalf of Crop Science Society of America.",
year = "2022",
month = jun,
doi = "10.1002/tpg2.20200",
language = "English (US)",
volume = "15",
journal = "Plant Genome",
issn = "1940-3372",
publisher = "Crop Science Society of America",
number = "2",
}