Maternal effects represent the influence of a mother's genotype or phenotype to her offspring's phenotype independently of additive genetic effects [1] and have numerous implications in a wide range of species on prenatal (development, immunity, stress level) and postnatal life (social rank, dispersal, reproductive performance, etc.) [2]–[5].

For mammals, the intrauterine environment is a potentially important source of maternal effects on a variety of life history traits [6]. Pre-natal exposure to sex steroid hormones emerges from the complex hormonal environment fetuses are exposed to. Each individual is exposed to androgens produced by its male siblings via transplacental and transamniotic diffusion [7]. Testosterone has organisational and activational effects on the central nervous system, masculinising and defeminising the behavior exhibited later in life [8], [9]. For instance, female rats (Rattus norvegicus) exposed to neonatal testosterone engaged in more masculinised impulsive behavior [9]. Similarly, masculinised yellow-bellied female marmots (Marmota flaviventris) had lower survival, were more likely to disperse, and had reduced weaning success compared with females exposed to reduced levels of intrauterine testosterone [10]. Thus, testosterone is an important modulator of life-history traits [10].

Apart from male siblings' testosterone, androgens are secreted by the mother's placenta, adrenal glands, and ovaries [11], [12], and they might contribute to offspring defeminisation or masculinisation. However, the importance of this maternal source has not been studied in the wild.

Early exposure to androgens is morphologically evident by the anogenital distance (AGD), the distance between the anus and the genital papilla. AGD results from the elongation of the perineal tissue, which is triggered by testosterone during the early development, and thus, males have larger AGD than females [13], [14]. AGD, at young ages, is thus a proxy of early exposure to androgens [15], [16] and is relatively easy to quantify under field conditions. Females (of several species) with larger AGD are masculinized. They are less likely to survive and more likely to disperse [10], are less likely to become pregnant [17], are less preferred by males, and have smaller and male-biased litters [18]. Similar findings have been observed as well in humans, including positive correlations between AGD and fertility in men [19], and ovarian follicles numbers in women [20].

We studied a population of individually marked wild yellow-bellied marmots for which litter effects but not maternal effects on anogenital distance were known: female yellow-bellied marmots' morphology, behavior, survival, and dispersal are influenced by the proportion of males in the litter [4], [10]. Given the strong relation between androgenization and life-history traits later in life, it seems crucial to disentangle the different sources of variation that might affect the offspring phenotype. For that we fitted an animal model, a statistical technique designed to decompose variance components, to assess how much of the variance in AGD in neonates was due to maternal, genetic and environmental effects.

As expected from previous analyses [10], we found a significant effect of litter sex ratio on AGD (Table 1), whereby pups in male-biased litters had greater AGDs. Male AGD was significantly greater than female AGD (Table 1) as previously [10], [29]. In addition, larger animals had larger AGDs (Table 1). For our sample of animals trapped within 10 days of emergence, there was no significant effect of the number of days since emergence, nor was there a significant effect of litter size (Table 1).

There were significant maternal effects at the phenotypic level accounting for 5.8% of the remaining variance (Fig. 1, Table 2, model 1, LRT  = 3.98, df  = 1, P = 0.046). When we decomposed the variance into additive genetic (LRT  = 1.51, df  = 1, P = 0.219), maternal environment (LRT  = 1.18, df  = 1, P = 0.277), and maternal genetic (LRT <0.001, df  = 1, P>0.999) components, we found that none of them were significant (Table 2, model 2). However, the inclusion of both additive genetic and maternal genetic effects provided a marginally better fit than when they were excluded (Fig. 1, Table 2, model 1 vs. model 2: LRT  = 5.56, df  = 2, P = 0.053). In addition, additive genetic (LRT  = 4.70, df  = 1, P = 0.030) and maternal genetic (LRT  = 4.39, df  = 1, P = 0.036) effects were both found to be significant if only one of them was included in the model and their estimates were larger (Fig. 1, Table 2, models 3 and 4). This suggests that despite nearly a decade's worth of data, we had insufficient power to conclusively isolate both effects. Nonetheless, it suggests that both effects could be important. When a maternal genetic effect was included in a model, the maternal environment explained <0.001 of the variance, a finding that suggests that most of the variance between mothers were due to maternal genetic effects. Litter identity effects were not significant in any model (Fig. 1, Table 2, all P>0.141). Year was significant in all models (all P<0.001) and explained 36% of the remaining variance in AGD (Fig. 1, Table 2).

We have shown that 6% of the remaining variation in the AGD of marmot pups is explained by a maternal effect. Our results also suggest that AGD is heritable and influenced by maternal genetic and non-maternal environmental effects, thus indicating that a mother's genotype produces specific developmental conditions for her offspring. The presence of a maternal genetic effect on AGD could result from various mechanisms during gestation or lactation. It could be due to genetic differences in maternal care, maternal milk content or maternal stress. A more promising avenue of explanation might reside in utero during development. AGD is widely used as a proxy for prenatal androgen hormone exposure in rodents [14]. Prenatal exposure to androgens may influence vertebrate life-history traits [29]–[32], because organizational and activational events take place at this stage. This androgen-sensitive prenatal developmental window is thus a key period that may influence life-history traits. Here, a possible explanation of the maternal effects on the AGD would be such a hormonal transfer from the mother to her pups. However, some studies in laboratory rats, Rattus norvegicus, have found no correlation between maternal testosterone levels and fetal testosterone levels. However, they did find a negative relationship between maternal testosterone levels and the capacity of nutrient transport across the placenta, resulting in reduced fetal growth [33]. Therefore, maternal testosterone might indirectly affect offspring AGD by influencing the offspring mass. In primates, in utero exposure to androgens has been explored mainly through the study of the 2d:4d ratio. There is evidence that up to 66% of the variance is explained by additive genetic effects. In addition, there is evidence of strong environmental effects and for shared environment effects (including maternal environment and part of maternal genetic effects) [34]–[37]. Our results are thus in line with previous studies suggesting additive genetic, maternal environment and maternal genetic effects on in utero exposition to androgens. Nevertheless, further quantitative measurements of maternal and pup androgen levels, in addition to formal genetic analyses of maternal endocrinological traits are needed to formally evaluate the mechanism underlying the maternal genetic effect on AGD. Such studies, beyond the scope of our study of free-living animals, would greatly improve our understanding of the mechanistic origin of the maternal effect we identified.

While the existence of a significant litter composition fixed effect agrees with previous findings [10], it is noteworthy that the bulk of the remaining variation in AGD variance was explained by annual variation. Despite extensive training, personnel turnover between years could be responsible for some of this variation. However, other biologically relevant factors could also explain annual variation. For instance, the current environment (food availability, predation level, weather conditions) could also explain annual variation through its influence on maternal stress and body condition [4], [10].

In conclusion, AGD is a widely used proxy of early exposure to testosterone, and it is related to numerous other life-history traits [4], [10], [16], [38]. We showed that by decomposing sources of variation using the animal model, we were able to identify, for the first time in a wild population, both an additive genetic and a maternal genetic effect on AGD that is expected to also impact future life-history traits and fitness of the pups. When other researchers quantify the magnitude of maternal effects on AGD and its genetic basis, we will be in a better position to understand its general importance.