Analysis of coastal cod (Gadus morhua L.) sampled on spawning sites reveals a genetic gradient throughout Norway's coastline

Abstract

Background: Atlantic cod (Gadus morhua L.) has formed the basis of many economically significant fisheries in the North Atlantic, and is one of the best studied marine fishes, but a legacy of overexploitation has depleted populations and collapsed fisheries in several regions. Previous studies have identified considerable population genetic structure for Atlantic cod. However, within Norway, which is the country with the largest remaining catch in the Atlantic, the population genetic structure of coastal cod (NCC) along the entire coastline has not yet been investigated. We sampled > 4000 cod from 55 spawning sites. All fish were genotyped with 6 microsatellite markers and Pan I (Dataset 1). A sub-set of the samples (1295 fish from 17 locations) were also genotyped with an additional 9 microsatellites (Dataset 2). Otoliths were read in order to exclude North East Arctic Cod (NEAC) from the analyses, as and where appropriate.

Results: We found no difference in genetic diversity, measured as number of alleles, allelic richness, heterozygosity nor effective population sizes, in the north-south gradient. In both data sets, weak but significant population genetic structure was revealed (Dataset 1: global F_ST = 0.008, P < 0.0001. Dataset 2: global F_ST = 0.004, P < 0.0001). While no clear genetic groups were identified, genetic differentiation increased among geographically-distinct samples. Although the locus Gmo132 was identified as a candidate for positive selection, possibly through linkage with a genomic region under selection, overall trends remained when this locus was excluded from the analyses. The most common allele in loci Gmo132 and Gmo34 showed a marked frequency change in the north-south gradient, increasing towards the frequency observed in NEAC in the north.

Conclusion: We conclude that Norwegian coastal cod displays significant population genetic structure throughout its entire range, that follows a trend of isolation by distance. Furthermore, we suggest that a gradient of genetic introgression between NEAC and NCC contributes to the observed population genetic structure. The current management regime for coastal cod in Norway, dividing it into two stocks at 62°N, represents a simplification of the level of genetic connectivity among coastal cod in Norway, and needs revision.

Keywords: Fish; Fishery; NCC; Otolith; Outlier; Population.

Fig. 1

Location of the sampling sites along the Norwegian coastline (Figure produced specifically for this manuscript)

Fig. 2

Number of alleles (black line) and allelic richness, Ar (red line) per sampling site for (a) Dataset 1 (6 microsatellites) and (b) Dataset 2 (15 microsatellites). Samples are ordered from north to south. In graph a), Ar experienced an increasing N-S trend (τ = 0.296, P = 0.00045) but not the number of alleles (τ = 0.153, P = 0.074); whereas in graph b), neither number of alleles nor Ar showed any sort of geographic trend (τ = 0.243, P = 0.1721; and τ = 0.0543, P = 0.7888, respectively)

Fig. 3

Pairwise F_ST for: a) Dataset 1 and b) Dataset 2. Black empty circles depict the pairwise F_ST for pairs of sites within the same rank of distances whereas filled red circles dots depict the median for each class. Both trends are highly significant and reveal increasing levels of differentiation correlating with the rank of distances: τ = 0.899, P ≤ 2.22 e-16; τ = 0.895, P = 1.79 e-06 and τ = 0.871, P < 2.22 e-16 for a) and b), respectively

Fig. 4

Frequency of the most common alleles within loci Gmo132, Gmo34 and Pan I in Dataset 1. Populations are ordered from north to south and the first one, called NEAC, consists of the 76 Pan I BB individuals with otolith types 4 and 5 that were purged from the dataset. Alleles Gmo132_115 and Gmo34_96 experienced a highly significant negative trend southwards (τ = − 0.626, P = 1.11 e-13, and τ = − 0.448, P = 1.17e-07, respectively), whereas for Pan I _A, this tendency was reversed (τ = 0.23, P = 0.007). The allele frequency for NEAC assessed in the Barents Sea was 0.745 for Gmo132_115, and 0.959 for Gmo34_96 [28]

Fig. 5

Frequency of the three different genotypes of locus Pan I in Dataset 1. Sites are ordered from north to south

Fig. 6

Bayesian clustering of cod samples. Inferred ancestry was assessed after clumping STRUCTURE runs where NEAC was used as an outgroup for NCC in the following datasets: Dataset 1 genotyped at (a) 6 microsatellites and (b) outlier loci Gmo32 and Gmo134; and (c) Dataset 2 genotyped at 15 loci. Sites were ordered from north to south as in Table 1