Maize inbreds exhibit high levels of copy number variation (CNV) and presence/absence variation (PAV) in genome content

Abstract

Following the domestication of maize over the past approximately 10,000 years, breeders have exploited the extensive genetic diversity of this species to mold its phenotype to meet human needs. The extent of structural variation, including copy number variation (CNV) and presence/absence variation (PAV), which are thought to contribute to the extraordinary phenotypic diversity and plasticity of this important crop, have not been elucidated. Whole-genome, array-based, comparative genomic hybridization (CGH) revealed a level of structural diversity between the inbred lines B73 and Mo17 that is unprecedented among higher eukaryotes. A detailed analysis of altered segments of DNA conservatively estimates that there are several hundred CNV sequences among the two genotypes, as well as several thousand PAV sequences that are present in B73 but not Mo17. Haplotype-specific PAVs contain hundreds of single-copy, expressed genes that may contribute to heterosis and to the extraordinary phenotypic diversity of this important crop.

Figure 1. Significant hybridization differences are due to structural variation.

(A) The B73 and Mo17 sequences for a portion of the 9,009 locus (sequenced by [28]) were aligned using Vista which displays the percent identity as a sliding window of 100 bp (y-axis is 50% to 100% identity). The location of genes annotated by Brunner et al. (indicated by light blue sequences in the alignment) and repeat elements (the color-coded track right above the alignments; pink indicates retrotransposons and orange indicates transposons) are shown above the VISTA alignment. The log₂(Mo17 signal/B73 signal) is shown for each probe in this region. The red probes exhibit significantly different (q<0.0001) signal in B73 and Mo17. The blue line indicates a segment with altered hybridization that was identified using DNAcopy. There are also data tracks that display the repeat annotation and B73/Mo17 similarity for each probe. Note that these annotations are based on the genome-wide analysis, not detailed analyses of these regions. In (B) we present the annotation, alignment and CGH data for a portion of the 9008 loci (sequence and annotated by Brunner et al., [28]).

Figure 2. Genomic distribution of log₂(Mo17/B73) signals.

The log₂(Mo17/B73) hybridization intensities are plotted for each chromosome. Data points below the line indicate higher hybridization in B73 than in Mo17. The positions of the centromeres are indicated by black boxes. Note that there are chromosomal regions with high rates of variation (example near 42–44 MB on chromosome 6) and regions with low rates of variation (example from 140–160 MB on chromosome 8).

Figure 3. Identification of regions of low structural diversity.

The proportion of probes that exhibit significantly higher hybridization to B73 genomic DNA than Mo17 (q<0.0001) was determined for a sliding window of 1 Mb probes with increments of 0.33 Mb. The approximate position of each centromere (from Wolfgruber et al., [72]) is indicated by a red circle on each chromosome. The locations of the tb1 and y1 genes, which are known to have undergone selective sweeps, are indicated. The gene density (based on the filtered gene set from the MGSP) is shown below each chromosome. The gene density was determined based on the number of genes per Mb. The dark color indicates low gene density while the yellow color indicates higher gene density.

Figure 4. Characterization of 2 Mb region on chromosome 6 that is present in B73 but missing in the Mo17 genome.

(A) A 10 Mb region on chromosome 6 is shown. The color-coding for each probe indicates the level of conservation of the probe sequence to the Mo17 WGS sequence. The coordinates on the x-axis refer to base pair position within chromosome 6 of the B73 Refgen_v1. The 2.6 Mb region from 42.2 to 44.8 is enriched for probes that are poorly conserved or have no match in the Mo17 sequence and the majority of these probes exhibit much higher signal in B73 than in Mo17. (B) The data from 38 primer pairs are shown. Blue indicates successful amplification for a particular inbred by primer combination while red indicates no amplification. The full set of 38 primer pairs (see Table S1 for details) amplify products in B73 but not in Mo17.

Figure 5. Distribution of average log2(M/B) for DNA segments.

The distribution of the average log₂(M/B) across segments was modeled using a four-component normal mixture model . The EM algorithm was used to estimate the mixing proportion, the mean, and the variance associated with each of the four normal component densities, corresponding to four segment classes (labeled with arrows). Class membership probabilities for each segment were computed using the EM estimates.

Figure 6. Distribution of CNV and PAV throughout the maize genome.

The position and average log₂(M/B) for each Mo17>B73_CNV, B73>Mo17_CNV, B73>Mo17_I and B73>Mo17_PA segment is plotted for all 10 maize chromosomes. The color-coding indicates the type of segment. The positions of the centromeres are indicated by the black boxes.