Signatures of natural selection among lineages and habitats in Oncorhynchus mykiss

Abstract

Recent advances in molecular interrogation techniques now allow unprecedented genomic inference about the role of adaptive genetic divergence in wild populations. We used high-throughput genotyping to screen a genome-wide panel of 276 single nucleotide polymorphisms (SNPs) for the economically and culturally important salmonid Oncorhynchus mykiss. Samples included 805 individuals from 11 anadromous and resident populations from the northwestern United States and British Columbia, and represented two major lineages including paired populations of each life history within single drainages of each lineage. Overall patterns of variation affirmed clear distinctions between lineages and in most instances, isolation by distance within them. Evidence for divergent selection at eight candidate loci included significant landscape correlations, particularly with temperature. High diversity of two nonsynonymous mutations within the peptide-binding region of the major histocompatibility complex (MHC) class II (DAB) gene provided signatures of balancing selection. Weak signals for potential selection between sympatric resident and anadromous populations were revealed from genome scans and allele frequency comparisons. Our results suggest an important adaptive role for immune-related functions and present a large genomic resource for future studies.

Keywords: Candidate genes; Interleukin; Local adaptation; MHC; Salmonid; Steelhead.

Figure 1

Wild rainbow trout (Oncorhynchus mykiss) in their natural environment (Photo by Finn Sivebæk).

Figure 2

Map of sampling locations. An approximate projection of the current divide between the inland and coastal lineages is shown by a thick broken line (From Behnke 1992).

Figure 3

Multi dimensional scaling (MDS) plot showing: (a) spatial population structure for all populations including the two resident populations, and (b) a similar plot without the SKAGRES population. Population symbols follow Figure 2.

Figure 4

Outlier tests for identifying signatures of selection. (a) F_ST-based global test assuming hierarchical structure by grouping all anadromous populations within each lineage into two major groups. (b) F_CT-based global test assuming hierarchical structure as in (a). Local outlier tests for the Skagit River (c) and Twisp River (d) anadromous and resident population pairs are also shown. All outliers above the 99% confidence threshold are labeled including two interleukin genes at the 95% threshold (c and d) shown in italic. Plotted heterozygosity values are scaled by estimates of within population heterozygosity (h₀) and locus specific F_ST as: (H₁ = h₀/[1 –F_ST]) as described in Excoffier et al. (2009).

Figure 5

Frequency plots of major allele frequencies for loci detected as outliers (P < 0.01) in the global genome scan including nine anadromous populations. (a) Allele frequencies for five outliers detected at both the F_ST and F_CT level. (b) Allele frequencies for three outliers only detected at the F_ST level.

Figure 6

Frequency plots of major allele frequencies for loci detected as outliers (P < 0.01) between sympatric and resident population pairs. (a) Allele frequencies for six markers detected as outliers between the Twisp River populations. (b) Allele frequencies for one outlier detected between the populations within the Skagit River. Arrows denote populations included in the local genome scans.

Appendix 1

SNP exclusion pipeline. Ellipses isolate numbers of SNPs in the various categories. Solid arrows connect the stages of analysis, and broken arrows identify sets of SNPs that were excluded at each stage.

Appendix 4

Frequency plots of major allele frequencies for five MHC-related SNPs. Omy_DAB_431 and Omy_DABb are nonsynonymous mutations in the peptide-binding region of a MHC class II gene, while Omy_DABc represents a synonymous mutation in the same gene. Omy_UBA3a and Omy_UBA3b show allele frequencies for two SNPs residing within a MHC class I gene.