Genetic signals of origin, spread, and introgression in a large sample of maize landraces

Abstract

The last two decades have seen important advances in our knowledge of maize domestication, thanks in part to the contributions of genetic data. Genetic studies have provided firm evidence that maize was domesticated from Balsas teosinte (Zea mays subspecies parviglumis), a wild relative that is endemic to the mid- to lowland regions of southwestern Mexico. An interesting paradox remains, however: Maize cultivars that are most closely related to Balsas teosinte are found mainly in the Mexican highlands where subspecies parviglumis does not grow. Genetic data thus point to primary diffusion of domesticated maize from the highlands rather than from the region of initial domestication. Recent archeological evidence for early lowland cultivation has been consistent with the genetics of domestication, leaving the issue of the ancestral position of highland maize unresolved. We used a new SNP dataset scored in a large number of accessions of both teosinte and maize to take a second look at the geography of the earliest cultivated maize. We found that gene flow between maize and its wild relatives meaningfully impacts our inference of geographic origins. By analyzing differentiation from inferred ancestral gene frequencies, we obtained results that are fully consistent with current ecological, archeological, and genetic data concerning the geography of early maize cultivation.

Fig. 1.

(A) Map of sampled maize accessions colored by genetic group. (B) First three genetic PCs of all sampled accessions.

Fig. 2.

(Lower) Bar plot of assignment values for the sample of Mexican accessions: Mexicana (red), parviglumis (green), and mays (blue). (Upper) The solid black line indicates the altitude for each sample. The dotted line marks the minimum altitude at which mexicana occurs.

Fig. 3.

Posterior densities of the genetic drift parameter F for 10 genetic groups with respect to (A) mexicana and (B) parviglumis. Only lowland accessions of the West Mexico group (light blue) were included. (C) Drift of all 10 genetic groups with respect to inferred ancestral frequencies. Light blue represents West Mexico; dotted line indicates the division between lowlands (<1,500 m, solid line) and highlands (>2,000 m).

Fig. 4.

Heat maps showing the amount of drift, F, away from (A) observed parviglumis allelic frequencies and (B) mean estimated ancestral frequencies. Each point is based on spatial estimation of current allele frequencies. The colors of the dots range from red for low values to white for high values of F. Black dots mark the lower 0.05 quantile. Upper panels A and B show enlarged sections of the lower panels A and B, respectively.