Evaluating the reliability of Structure outputs in case of relatedness between individuals

Inference of population structure from neutral marker loci is a key issue for association genetics. However, the presence of highly related individuals, commonly observed in breeders' panels, may lead to deviation from model hypotheses and therefore unreliable group assignment. The present note proposes a tool to help interpret Structure software outputs on populations that include highly related individuals, such as plant breeding material. We ran Structure software on simple sequence repeat (SSR) data from two maize (Zea mays L. ssp. mays) inbred panels. We propose a criterion to evaluate Structure stability based on Euclidian distance between outputs. This approach shows a high stability across runs for the panel composed of first cycle inbred lines. On the contrary, the presence of highly related individuals in the second panel induces strong instability in Structure outputs.