The Recombination Landscape in Wild House Mice Inferred Using Population Genomic Data

Abstract

Characterizing variation in the rate of recombination across the genome is important for understanding several evolutionary processes. Previous analysis of the recombination landscape in laboratory mice has revealed that the different subspecies have different suites of recombination hotspots. It is unknown, however, whether hotspots identified in laboratory strains reflect the hotspot diversity of natural populations or whether broad-scale variation in the rate of recombination is conserved between subspecies. In this study, we constructed fine-scale recombination rate maps for a natural population of the Eastern house mouse, Mus musculus castaneus We performed simulations to assess the accuracy of recombination rate inference in the presence of phase errors, and we used a novel approach to quantify phase error. The spatial distribution of recombination events is strongly positively correlated between our castaneus map, and a map constructed using inbred lines derived predominantly from M. m. domesticus Recombination hotspots in wild castaneus show little overlap, however, with the locations of double-strand breaks in wild-derived house mouse strains. Finally, we also find that genetic diversity in M. m. castaneus is positively correlated with the rate of recombination, consistent with pervasive natural selection operating in the genome. Our study suggests that recombination rate variation is conserved at broad scales between house mouse subspecies, but it is not strongly conserved at fine scales.

Keywords: Mus musculus; population genomics; recombination; wild Mice.

Figure 1

The effect of switch errors on the mean recombination rate inferred using LDhelmet with a block penalty of 100. Each black point represents results for a window of 4000 SNPs, with 200 SNPs overlapping between adjacent windows, using sequences simulated in SLiM for a constant value of ρ/bp. Red points are mean values. Switch errors were randomly incorporated at heterozygous SNPs with probability 0.0046. The dotted line shows the value when the inferred and true rates are equal.

Figure 2

Comparison of sex-averaged recombination rates for chromosomes 1 and 19 of M. musculus castaneus inferred by LDhelmet (red) with rates estimated in the pedigree-based study of Cox et al. (2009) (blue). Recombination rates were scaled to units of centimorgans per megabase for the castaneus map by setting the total map length of each chromosome to the corresponding map length of Cox et al. (2009).

Figure 3

Pearson correlation coefficients between the recombination map inferred for M. m. castaneus, the Brunschwig et al. (2012) map and the Cox et al. (2009) map. Correlations were calculated in nonoverlapping windows of varying size across all autosomes. Confidence intervals (95%) are indicated by shading.