Genomic and phenotypic analysis of Vavilov's historic landraces reveals the impact of environment and genomic islands of agronomic traits

Abstract

The Vavilov Institute of Plant Genetic Resources (VIR), in St. Petersburg, Russia, houses a unique genebank, with historical collections of landraces. When they were collected, the geographical distribution and genetic diversity of most crops closely reflected their historical patterns of cultivation established over the preceding millennia. We employed a combination of genomics, computational biology and phenotyping to characterize VIR's 147 chickpea accessions from Turkey and Ethiopia, representing chickpea's center of origin and a major location of secondary diversity. Genotyping by sequencing identified 14,059 segregating polymorphisms and genome-wide association studies revealed 28 GWAS hits in potential candidate genes likely to affect traits of agricultural importance. The proportion of polymorphisms shared among accessions is a strong predictor of phenotypic resemblance, and of environmental similarity between historical sampling sites. We found that 20 out of 28 polymorphisms, associated with multiple traits, including days to maturity, plant phenology, and yield-related traits such as pod number, localized to chromosome 4. We hypothesize that selection and introgression via inadvertent hybridization between more and less advanced morphotypes might have resulted in agricultural improvement genes being aggregated to genomic 'agro islands', and in genotype-to-phenotype relationships resembling widespread pleiotropy.

Figure 1

Analysis of 14,059 genome-wide SNP reveals patterns associated with chromosome of origin, geographical distribution, and a secondary bottleneck from Turkey to Ethiopia. Colour scheme in all panels of the figure (red, green and blue) corresponds to separation of accessions on PC-plot (a), into three clades on whole genome tree (b) and into three clades on chromosome 4 tree (c). (a) Principal component plot constructed for all SNPs separates accessions by the country of origin (Ethiopia and Turkey) and reveals three clusters that correspond to genetic structure revealed on maximum likelihood tree of all accessions shown in (b). (b) Maximum likelihood phylogenetic tree for the chickpea landraces based on the whole genetic material. (c) Maximum likelihood phylogenetic tree showing relationships among accessions based on chromosome 4 SNPs, and (d) the rest of the genome. (e) Geography of accessions with origin in Turkey or Ethiopia, (the map was created with ArcGIS 10.3.1 software, http://www.esri.com/). Map coloration depicts annual precipitation – a variable predictive of the plant phenology. Twenty of 45 Ethiopian accessions were collected in Addis Ababa and appear as a single point on the graph.

Figure 2

Factor analysis of phenotypic data reveal correlated traits. Factor loadings for Syrian field trial (a) and Astrakhan (Russian) field trial (b) phenotype data (red colour corresponds to positive loadings while turquoise colour to negative ones). (c) and (d): Factor 1 of Syrian phenotype data separates accessions according to colour scheme in all panels of Fig. 1. Green and red clusters are phenotypically distinct, while blue and green clusters partially overlap. As Factor 1 is driven by seed size and flower colour characteristics that differ between Desi and Kabuli varieties, it distinguishes market classes. (e) Factor 1 of Astrakhan phenotype data separates accessions largely based on seed characteristics that distinguish Kabuli and Desi varieties.

Figure 3

Genomic analyses reveal genetic control of traits and an enrichment of trait associations on chromosome 4 (a) LD measured by r² as a function of genetic distance between SNPs for all landraces and (b) for landraces from Turkey. (c) Proportion of phenotypic variance explained by genotype for different traits. y-axis ratio of genetic variance to phenotypic variance of a trait, x-axis – different trait phenotypes. (d) Summary of GWAS analyses for Astrakhan (Russia) and Allepo (Syria) phenotype data (different colours corresponds to different chromosomes). SNPs with q-value < 0.05 are shown for each chromosome, marked as triangles. When one position associates with a number of phenotypes with different q-values, only the most significant SNP is represented.

Figure 4

Phenotypic and genomic patterns correlate with bioclimatic variables. (a) Correlations between bioclimatic variables and Factors of Syrian phenotype data (*p-value < 0.05; **p-value < 0.01). (b) Genomic heritability of bioclimatic variables.