We sequenced the three exons and the majority of introns of the MSTN gene in an initial set of 22 whippets. A 2-bp deletion was discovered in the third exon of the MSTN gene (Figure 2). This deletion removes nucleotides 939 and 940 within exon three and leads to a premature stop codon at amino acid 313 instead of the normal cysteine, removing 63 aa from the predicted 375-aa protein. The lost cysteine is one of several highly conserved cysteines known to form disulfide dimers required for protein function [9].

Of the 22 whippets sequenced, all “bully” whippets tested (n = 4) were homozygous for the deletion (mh/mh) while all dogs that sired or whelped a “bully” whippet (n = 5) were heterozygous for the deletion (mh/+). None of the initial set of 13 normal-appearing whippets that lacked a family history of the “bully” phenotype carried the deletion; these dogs were designated wild type (+/+). An additional set of DNA samples from 146 whippets (both racers and nonracers) were collected at racing events and through the mail without regard to the dogs' family histories of the “bully” phenotype. These were sequenced across exon three to determine the frequency of the 2-bp mutation among the dogs sampled. Of these, two were homozygous for the deletion, 20 were heterozygous, and the remaining 124 did not carry the deletion.

The “bully” phenotype displays a simple autosomal recessive mode of inheritance, as all “bullies” resulted from the mating of carriers. The parents have a phenotype of intermediate musculature (Figure 1B). In order to quantify the allelic substitution and dominance effects of the deletion mutation we considered three measures of musculature: mass-to-height ratio, neck girth, and chest girth. For all three measures, heterozygous females (mh/+) were intermediate in musculature, mh/mh females had the highest measures, and female +/+ whippets had the lowest measures. Male mh/+ whippets were more muscular than wild-type males (Figure 3 and Table 1).

Mass (kg) and height at the withers (cm) information was available for 71 female and 55 male whippets; we analyzed the two sexes separately due to a lack of samples from male mh/mh whippets. Two analyses suggest strong statistical support for the idea that the mh deletion mutation affects the mass-to-height ratio. First, a nonparametric Kruskal-Wallis one factor Analysis of Variance for females using genotype as a factor (mh/mh, mh/+, and +/+) was highly significant (p ≈ 7.43 × 10⁻⁶) [10]. Likewise, a two-sample Wilcoxon rank sum test comparing mass-to-height ratio of mh/+ and +/+ males was also significant (p ≈ 0.00017), with whippets heterozygous for the mutation exhibiting, on average, 17% more mass per cm of height (i.e., 0.333 kg/cm for mh/+ as compared to 0.284 kg/cm for +/+ genotypes). Second, we used standard least-squares regression to estimate the allelic substitution (a = 0.0817; p < 2.44 × 10⁻¹⁵) and dominance effects (d = −0.0423; p = 0.00415) in female whippets and found both parameters were significantly different than zero. These results, along with box plots of the phenotype by genotype class (Figure 3), suggest that the mutation is partially recessive with heterozygotes (mh/+) having musculature closer to, but significantly different from, that of wild types (+/+). As reported in Table 1, we found that the mh mutation also affected neck and chest girth in a similar fashion in females with a highly significant effect of MSTN genotype on phenotype. Overall, we estimate that mh explains approximately 60% of the variation in both mass-to-height ratio and neck girth (i.e., r² = 60%) and 31% of the variation in chest girth (Table 1). In male whippets, we also observed a highly significant difference in neck girth (p ≈ 0.0013, Wilcoxon rank sum test) and nearly significant difference in chest girth (p ≈ 0.11, Wilcoxon rank sum test) among wild type (+/+) and heterozygotes (mh/+).

We hypothesized that the increased muscle mass of the heterozygotes would allow for increased speed when compared to wild type (+/+) whippets. Analysis of 85 genotyped dogs for which we obtained racing grades revealed an association between a dog's genotype and racing grade using two separate (but not independent) approaches (Figure 4). Only one mh/mh dog competed in racing events and it was a grade-A racer, so we included this dog with the heterozygotes and considered the absence or presence of the deletion for all analyses (i.e., we sum across the mh/+ and mh/mh columns in Table 2. First, we find a significant positive correlation between racing grade (A, B, C, and D in order from fastest to slowest) and the frequency of dogs carrying the mh deletion in either homozygous or heterozygous state (p ≈ 0.00028, τ = 0.3619, Kendall's nonparametric measure). Secondly, standard contingency table analysis reveals strong evidence for heterogeneity in the frequency of dogs carrying the mh deletion among racing grade classes (Table 2; p = 0.00029, Fisher's exact test with degrees of freedom = 3). Since the 4 × 2 contingency table (i.e., combining columns two and three of Table 2) has three degrees of freedom, it is possible to partition the analysis into three tests of one degree of freedom each in order to identify outlier grades. There are several methods by which this can be accomplished, although they are not independent of each other. For example, 12 of 41 dogs in the fastest two racing grades, A and B, carried the deletion, while just one dog of 43 from the slowest two racing grades, C and D, was a heterozygote (p = 0.00073, Fisher's exact test), indicating a strong difference in frequency between (A, B) and (C, D). There is suggestive evidence for a difference between race grades A and B (p = 0.086, Fisher's exact test) but no evidence for a difference between C and D (p = 0.42, Fisher's exact test). A different approach for dividing the degrees of freedom is to compare A versus (B, C, D) (p = 0.00027, Fisher's exact test), C versus (B, D) (p = 0.099, Fisher's exact test), and C versus D (p = 0.42, Fisher's exact test). Thus, each of these two methods for partitioning the test suggests that the presence of the mh mutation strongly influences racing ability.

There was also a marginally significant difference in the mutation genotype frequency in whippets that participated in racing versus conformation events such as breed club regional specialties, where dogs are judged based on their conformation to the physical breed standard (height at the withers or shoulder, head shape, coat color, etc.). Twenty of 119 confirmed racing whippets were heterozygous for the deletion while just two of 42 whippets that competed in conformation events were heterozygous (p = 0.038, one-tailed Fisher's exact test).

To investigate how population substructure within whippets affects our candidate gene analysis, we genotyped 32 unlinked microsatellite markers [11] in 84 whippets with racing grades. Analysis of F_ST revealed that whippets exhibit a low, but measurable, degree of population differentiation with higher levels of interbreeding within racing grades. As a result, genetic distance correlates with racing grade so that there is a moderate differentiation between A and B grades (F_ST = 0.021), little differentiation between B and C (F_ST = 0.0044) or C and D (F_ST = 0.0067) racers, and the largest difference between the population of A and D racing dogs (F_ST = 0.041). These levels of population differentiation are quite typical for mammalian species and are not surprising, given that whippets are bred to race and positive assortative mating is expected (i.e., fast dogs are bred to fast dogs).

Analysis of the data using Structure [12] and InStruct [13] gave comparable results under a range of cluster numbers from K = 1 to K = 15. Neither program found a clustering that clearly correlated with racing grade. The neighbor-joining tree of the 84 dogs used in this analysis based on genetic similarity (i.e., kinship coefficient) tends to differentiate dogs within the A racing grade from those in other grades, but not in a fully exclusive manner (Figure S1). It also demonstrates that dogs carrying the 2-bp deletion are found on all branches of the tree and are not one another's closest relatives, although they do tend to cluster near one another on the tree.

Logistic regression analysis of 73 alleles at moderate frequencies in the sample confirmed that population substructure may be a potentially confounding effect for association mapping within breeds of dog. In particular, we found that 26 of the alleles (36%) across the 32 loci show a nominal p-value of 5% or lower, a huge inflation above the expected 5% (Figure S2A). As a result, many of the 32 loci showed association with racing grade using standard contingency table analysis. However, the association of the 2-bp deletion with racing grade is more significant than all but one of these, suggesting an empirical p-value of 1/72 = 0.014 (Figure S2B).

We sequenced exon three of MSTN in a set of approximately four dogs each from heavily muscled breeds including the bullmastiff, rottweiler, bulldog, Presa Canario, miniature bull terrier, American Staffordshire terrier, and Staffordshire bull terrier. In addition, we sequenced exon three of MSTN in a small set of dogs from breeds known to compete in racing: the greyhound, lurcher, and two mixed-breed dogs (whippet crosses). None of these dogs possessed the 2-bp deletion seen in the whippet.

To obtain haplotype information, we sequenced the MSTN gene and surrouonding area (Figure 5) in one to ten dogs each from the greyhound, Ibizan hound, Pharaoh hound, Afghan hound, saluki, Italian greyhound, mastiff, boxer, Akita, Basenji, Australian shepherd, beagle, German wirehaired pointer, and flat-coated retriever breeds. A golden jackal was also sequenced to determine the ancestral allele for each dog SNP and insertion/deletion (indel). None of the dogs sequenced from any of the above breeds nor the golden jackal possessed the 2-bp deletion. We discovered 28 SNPs and three indels. For the three indels and eight SNPs that were discovered within 50 kb of the MSTN mutation, we inferred haplotypes independently for each breed using PHASE. A total of 13 haplotypes were identified, but only six were observed in more than one breed. Two of these haplotypes are shared across several breeds. The MSTN mutation occurs on just one haplotype that is observed only in the whippet (Figure 5). A haplotype observed in 12 breeds differs from this one only at the mutation itself.

An initial set of 22 whole-blood samples were collected from whippets that participated in racing, conformation, or were simply privately owned pets. Of these 22 dogs, four were reported by owners to be “bullies,” five dogs had either sired or whelped a “bully,” and the owners of the remaining 13 stated there was no known family history of “bullies” in their dog's pedigree. After initial analysis of these 22 samples an additional 46 whole-blood samples and 100 buccal swabs were collected from a mixture of racing, conformation, and pet whippets. No restrictions were placed on age, gender, or relatedness of the dogs sampled. The dog's sex was recorded for 165 (98%) of the dogs (74 males and 91 females). Samples were collected both by mail and at sanctioned Whippet Racing Association (WRA), National Oval Track Racing Association (NOTRA), and Continental Whippet Alliance (CWA) racing events. Blood samples from each dog were collected as whole blood in ACD tubes. Buccal swabs were collected using standard protocols with Cytosoft cytology brushes (Medical Packaging Corporation, http://www.medicalpackaging.com). DNA was extracted from the brushes using a QIAamp Blood Mini kit (Qiagen, http://www.qiagen.com) following the manufacturer's protocol. DNA was extracted from the blood samples using a standard phenol/chloroform extraction method [23].

DNA samples were also collected from 33 greyhounds, two mixed-breed dogs (whippet crosses), seven lurchers, five each of bullmastiffs, rottweilers, and bulldogs, four each of Presa Canarios, miniature bull terriers, mastiffs, Staffordshire bull terriers, Ibizan hounds, and salukis, three each of American Staffordshire terriers, Italian greyhounds, boxers, and Pharaoh hounds, two each of Akitas, Afghan hounds, Australian shepherds, beagles, flat-coated retrievers, and German wirehaired pointers, a single Basenji, and a single golden jackal. Samples were either received as DNA from collaborators or DNA was extracted by the aforementioned methods after collection at dog shows, events, or provided directly by owners and breeders. Informed consent was obtained for all newly collected samples and all protocols were approved by the Animal Care and Use Committee of the Intramural Program of the National Human Genome Research Institute at the National Institutes of Health.

Owners of whippets were asked to provide detailed information about their dogs including American Kennel Club or other registration number, pedigree information, and the events in which their dogs participated. Front and side photos of individual dogs were obtained for comparison. The dog's mass and height at the withers were recorded for 126 dogs (55 males and 71 females). A set of body measurements including neck girth and chest girth were also collected from 137 of the whippets (61 male and 76 female) either by owners or laboratory members as described (N. B. Sutter, D. S. Mosher, and E. A. Ostrander; personal communication).

There are four organizations that govern whippet racing in the United States; straight racing is sponsored by the WRA, CWA, and the North American Whippet Racing Association (NAWRA), while oval racing is sponsored by NOTRA. The standard track length of a straight race is 182.88 m, while the standard oval track is 350 m. A race meet is composed of four heats. Based on their placement in all four heats, dogs are given a total meet score. A dog's racing grade is a simplified assessment of its performance over the last three meets. As a result, a dog's racing grade will vary throughout its career as grade is reassessed following each meet. We used the WRA racing grades: Grade A is 15.0–29.0 points, grade B is 10.0–14.9 points, grade C is 4.0–9.9 points, and grade D is 0–3.9 points (http://www.whippetracing.org/Rules/2006/2006Chapter5.htm). We categorized dogs based on the highest grade ever achieved. Grades for 85 racing whippets were obtained from the WRA website (http://www.whippetracing.org).

We employed least-squares regression to estimate the allelic substitution (a) and dominance (d) effects of the mutation using a Falconer parameterization for genotypic means [24]. Briefly, we assumed the phenotypes within genotypic classes are normally distributed with mean for wild type (+/+), heterozygotes (mh/+), and homozygotes (mh/mh) of μ_+/+ = μ − a, μ_mh/+ = μ + d, and μ_mh/mh = μ + a, and with common variance σ² within classes. This amounts to using two “dummy” variables to encode the design matrix for the regression with values (−1, 0, and 1) and (0, 1, and 0) for the genotype classes (+/+, +/mh, and mh/mh). All measurements were normalized (i.e., mean subtracted and observations divided by the standard deviation) and Q-Q plots inspected visually to assess the appropriateness of normality assumption within genotypic classes. All statistical analyses were carried out using R 2.4.1 (www.r-project.org).

We genotyped 32 unlinked microsatellite markers [11] in 84 whippets with racing grades. All loci were found to be variable with a total of 135 alleles segregating across all markers. We used GDA [25] to calculate Wright's fixation index (F_ST) and estimated kinship coefficients using Ritland's method [26] and Rousset's genetic distance [27] using Spagedi 1.2f [28]. Population clustering was assayed using the Bayesian clustering algorithm Structure [12], which assumes Hardy-Weinberg equilibrium within clusters and InStruct [13], a Structure-like algorithm that estimates a generalized inbreeding coefficient for each cluster. A neighbor-joining tree was constructed by using Rousset's genetic distance [27] as input into Phylip 3.66 (http://evolution.genetics.washington.edu/phylip.html) and racing grade state was traced across the tree using MacClade 4.0 (http://macclade.org/) (Figure S1).

We analyzed the control loci for association between genotype and racing grade using standard logistic regression analysis for differentiating A racers from B, C, or D racers. For each control locus, we fit a saturated model with n_l parameters, where n_l is the number of microsatellite alleles found at locus l (each analysis had (n_l − 1) allele effects and one intercept parameter). Figure S2 shows the distribution of p-values for the 73 allele effects with p-values below 0.98. In total there were (135 − 32) = 103 independently estimated allele effects, but for 30 of these there was little power to detect an effect because so few dogs carried the allele.

The entire canine MSTN gene was sequenced except for a 1,039-bp GC-rich region in intron one. Twelve pairs of overlapping primers covering the remaining regions of the gene and three primer pairs for SNP genotyping were designed using Primer 3 software [29] (http://frodo.wi.mit.edu/cgi-bin/primer3/primer3_www.cgi). Exon/intron boun-daries were based on the complete canine MSTN mRNA sequence. The resulting amplicons averaged 700 bp in length (653 to 799 bp). PCR was performed in a total volume of 10 μl containing 10 ng of dog DNA, 1× reaction buffer (Applied Biosystems, http://www.appliedbiosystems.com), 0.1 mM dNTP (Promega, http://www.promega.com), 1.5 mM MgCl₂, 0.5 U of AmpliTaq Gold polymerase (Applied Biosystems) and 0.03 μM each specific primer. Touchdown PCR was carried out as follows: 7 min at 95 ^°C followed by 20 cycles of 30 s at 95 ^°C, 30 s at annealing temperature (beginning at 61 ^°C and decreasing 0.5 ^°C per cycle) and 30 s at 72 ^°C then 20 cycles of 30 s at 95 ^°C, 30 s at 51 ^°C and 30 s at 72 ^°C and a final extension phase for 3 min at 72 ^°C.

The resulting PCR products were sequenced using Big Dye version 3.1 on an ABI 3730xl capillary sequencer (Applied Biosystems). Sequence reads were aligned and analyzed using Phred, Phrap, and Consed [30,31,32]. Polyphred [33] was used to assist in the identification of all SNPs and indel polymorphisms.

The Genbank (http://www.ncbi.nlm.nih.gov/gquery/gquery.fcgi) accession number for the complete canine MSTN mRNA sequence is AY367768. The Genbank accession number for the MSTN protein is NP_01002959.