Song and genetic divergence within a subspecies of white-crowned sparrow (Zonotrichia leucophrys nuttalli)

Abstract

Animal culture evolves alongside genomes, and the two modes of inheritance-culture and genes-interact in myriad ways. For example, stable geographic variation in culture can act as a reproductive barrier, thereby facilitating genetic divergence between "cultural populations." White-crowned sparrows (Zonotrichia leucophrys) are a well-established model species for bird song learning and cultural evolution, as they have distinct, geographically discrete, and culturally transmitted song types (i.e., song dialects). In this study, we tested the hypothesis that divergence between culturally transmitted songs drives genetic divergence within Nuttall's white-crowned sparrows (Z. l. nuttalli). In accordance with sexual selection theory, we hypothesized that cultural divergence between mating signals both preceded and generated genetic divergence. We characterized the population structure and song variation in the subspecies and found two genetically differentiated populations whose boundary coincides with a major song boundary at Monterey Bay, California. We then conducted a song playback experiment that demonstrated males discriminate between songs based on their degree of divergence from their local dialect. These results support the idea that discrimination against non-local songs is driving genetic divergence between the northern and southern populations. Altogether, this study provides evidence that culturally transmitted bird songs can act as the foundation for speciation by sexual selection.

Fig 1. Map of all genetic samples before data filtering.

Classification of Z. l. nuttalli, Z. l. pugetensis, and their hybrids is based on DAPC analysis of SNP data (see Population Structure methods below).

Fig 2. Map of song recording localities included in the song dissimilarity dataset.

Dataset includes 175 songs (18 dialects) from 82 males of Z. l. nuttalli.

Fig 3. White-crowned sparrow song sections and song traits measured for PCA.

Fig 4. Population structure of Z. l. nuttalli.

Light blue indicates the northern population and dark blue the southern population. (A) fastSTRUCTURE assignment probabilities, sorted north to south. (B) Interpolated assignment probabilities to northern and southern Z. l. nuttalli populations, with the white band at Monterey Bay representing admixture.

Fig 5. Song boundaries and acoustic dissimilarity comparisons at boundaries.

Points are sampled songs, and yellow cells represent boundary elements, with darker yellow indicating more intense boundaries. Pink shading shows admixture at the genetic boundary, with the darkest pink indicating an assignment probability of 0.5. Insets show comparisons of mean across-boundary and same-side acoustic dissimilarity.

Fig 6. Song trait principal components by genetic population.

(A) PC1, for which high values indicate higher song maximum frequencies and longer trill notes; (B) PC2, for which high values indicate higher minimum frequencies and longer complex notes; and (C) PC4, for which higher values correspond to higher minimum trill frequencies. Each PC is shown separated by genetic Z. l. nuttalli group. Asterisks indicate statistically significant differences between the groups.

Fig 7. Correlation between behavioral discrimination and song dissimilarity.

Each male is represented by two points: discrimination toward a non-local song (circles) from the same population and toward a song from the other population (triangles).