Genome wide association study of agronomic and seed traits in a world collection of proso millet (Panicum miliaceum L.)

Abstract

Background: The climate crisis threatens sustainability of crop production worldwide. Crop diversification may enhance food security while reducing the negative impacts of climate change. Proso millet (Panicum milaceum L.) is a minor cereal crop which holds potential for diversification and adaptation to different environmental conditions. In this study, we assembled a world collection of proso millet consisting of 88 varieties and landraces to investigate its genomic and phenotypic diversity for seed traits, and to identify marker-trait associations (MTA).

Results: Sequencing of restriction-site associated DNA fragments yielded 494 million reads and 2,412 high quality single nucleotide polymorphisms (SNPs). SNPs were used to study the diversity in the collection and perform a genome wide association study (GWAS). A genotypic diversity analysis separated accessions originating in Western Europe, Eastern Asia and Americas from accessions sampled in Southern Asia, Western Asia, and Africa. A Bayesian structure analysis reported four cryptic genetic groups, showing that landraces accessions had a significant level of admixture and that most of the improved proso millet materials clustered separately from landraces. The collection was highly diverse for seed traits, with color varying from white to dark brown and width spanning from 1.8 to 2.6 mm. A GWAS study for seed morphology traits identified 10 MTAs. In addition, we identified three MTAs for agronomic traits that were previously measured on the collection.

Conclusion: Using genomics and automated seed phenotyping, we elucidated phylogenetic relationships and seed diversity in a global millet collection. Overall, we identified 13 MTAs for key agronomic and seed traits indicating the presence of alleles with potential for application in proso breeding programs.

Keywords: Agrobiodiversity; GWAS; NUC; Population genetics; Proso millet; Seed morphology.

Fig. 1

Analysis of seed and morpho-agronomic traits. A Histograms for the seed traits. B Correlation between seed traits and agronomic traits. The direction and intensity of correlations is shown by the tile colour according to legend. Blank tiles mean no significant correlation. SP, seed perimeter; SPL, seed perimeter to length; SL, seed length; SW, seed width; SLW, seed length to width; SLWR, seed length to width ratio; SC, seed circularity; RGB, seed color; PH, plant height; LN, leaf number; BT, basal tiller number; SY, seed yield; GY, grain yield; DB, dry biomass; HI, harvest index; SWT, seed weight

Fig. 2

Phenotypic and molecular diversity of proso millet accessions. A Principal component analysis of phenotypic diversity of seed traits and agronomic traits. B Phylogenetic tree derived from SNPs data. C Principal component analysis derived from SNPs data. Different colors indicate region of origin as shown in the legend

Fig. 3

Bayesian structure analysis of the core collection of proso millet. Bar plot representing accession ancestries according to the most probable Structure model (K = 4). Each accession is represented by a vertical bar with colors proportional to their ancestry to one of K genetic cluster according to legend. The panel to the right reports the likelihood of each K interpretation as revealed by the ΔK output from structure Harvester

Fig. 4

GWAS outcome for plant height and seed width. In the panels to the left, Manhattan plots report individual SNPs across all chromosomes (x-axis) and -log10 P value of each SNP association (y-axis). The horizontal lines represent a stringent Bonferroni threshold for a nominal p-value of 0.05. Note that MTAs are called with and FDR-based threshold. Trait names are given on top. The panels to the right report Quantile–Quantile (Q–Q) plots showing distribution of estimated versus observed -log10 (P) values obtained by the GWAS model for the traits reported