In purebred and non-pedigreed domestic cats (felis catus), the AB blood group system with type A, B, and C (usually called AB) is of main concern, as blood incompatibilities can result in acute hemolytic transfusion reactions and hemolysis of the newborn (neonatal isoerythrolysis) due to naturally occurring alloantibodies [1–3]. The enzyme cytidine monophosphate-N-acetylneuraminic acid hydroxylase (CMAH; EC 1.14.18.2) converts sialic acid N-acetylneuraminic acid (NeuAc; type B antigen) to N-glycolylneuraminic acid (NeuGc; type A antigen) [3]. Depending on the blood type, plasma contains strong naturally occurring anti-A and sometimes anti-B antibodies against the other red blood cell (RBC) antigens [4]. Cats with blood type C express both NeuAc and NeuGc in varied amounts and have no anti-A and anti-B alloantibodies. Furthermore, their RBCs agglutinate with antibodies against both NeuGc and NeuAc [5, 6].

The frequencies of type A, B, and C vary among feline breeds and geographic regions [3, 7]. The A allele was determined to be dominant to the b allele, and the a^c allele (causing blood type C) was found to be separately inherited, being (co-) dominant to b and recessive to the A allele [5, 7]. Thus, the following genotypes can be observed: A/A, A/b and A/a^c for type A, b/b for type B, and a^c/ a^c or a^c/b for type C.

While good immunological typing assays are available for clinics and diagnostic laboratories [3], genotyping could also be used to determine the recessive b and a^c alleles in type A and C cats to confirm and predict blood types in offspring. In recent limited molecular genetic studies several variants in the CMAH gene were thought to be responsible for type A, B, and C [8–11]. The b allele was ascribed to two single nucleotide variants (SNVs) upstream of the open reading frame (ORF) of the CMAH gene (-371C>T and -217G>A), alongside an insertion/deletion of 18 bp in the 5´-untranslated region (UTR) 53 bp upstream (Δ-53) and four non-synonymous variants within the ORF (c.139C>T, c.142G>A, c.268T>A, and c.1603G>A) [8, 9]. However, there were many examples of phenotype-genotype discordances for cats with type B and C (personal unpublished results) [10, 11], making genotyping unreliable particularly for cats with type B and C blood, where genotyping would be most helpful. In a fourth study, additional variants were associated with a specific blood type as diplotypes and haplotypes, but not as individual variants [11]. The variant c.364C>T (p.Pro122Ser) was reported to cause type C in Ragdolls and some non-pedigreed cats, whereby the few type C cats from other breeds did not show this variant. It is speculated that the variant c.364C>T reduces the activity of CMAH leading to the presence of both NeuGc and NeuAc, but no biochemical studies have been performed [10]. These prior studies included a limited number of cats with unconfirmed phenotyping results; blood typing is done immunologically in clinics and diagnostic laboratories, and it is recommended to confirm type B and C results with back typing and or crossmatching by a reference laboratory [3, 12–14]. Additionally, the effects of the discovered variants were not studied by protein modeling, expression, and/or function experiments to determine which might be the variants impairing CMAH function and thus type B and C blood. A DNA screening scheme involving CMAH variants that could accurately determine the blood type within the feline AB blood group system would be highly desirable to complement the phenotypic tests. It should be noted that in humans a large deletion makes CMAH a pseudogene, which is the cause for the lack of NeuGc expression in all humans [15]. Similarly, in several species other than felides the AB blood group system has not been found to be clinically important [16, 17].

In the present study, we sequenced the exons and regulatory regions of the CMAH gene from 70 purebred and non-pedigreed domestic cats which had been carefully phenotyped as having type A, B, and C blood, assessed the non-synonymous variants by modeling, and genotyped an additional 351 blood typed cats. We discovered new variants associated with type A, B, and C, report their predicted effect on the enzyme, and are proposing a simple scheme with SNVs to accurately screen cats genetically for all three blood types in different breeds.

Since Landsteiner’s seminal discovery of the ABO blood group system, the discovery and diagnostic blood typing in humans and animals has been pursued by RBC surface antigen to alloantibody interactions [1, 2]. Polyclonal (antisera) and later monoclonal antibodies have been principally used in hemagglutination and other immunohematological assays (forward typing). If naturally or induced alloantibodies are present, back typing with RBCs of known type can substantiate the test results [3]. To that end, we utilized an agglutination gel column laboratory method with anti-B lectin and feline anti-A serum and immunochromatographic strip kit with murine anti-A and anti-B monoclonal antibodies to type 421 domestic cats for blood type A, B, and C (usually called AB type). The resulting blood types were completely concordant, similarly accurate to prior feline typing surveys with these methods but better compared to card and cartridge hemagglutination kits.

While immunohematological assays are simple, practical, and accurate, when properly performed, they have, beside obvious sample quality and operator related problems, various limitations related to the strength and specificity of alloantibody and RBC antigen leading to typing inconsistences and inaccuracies. Weaker RBC antigens may not be consistently identified in complicated clinical situations due to prior transfusions and autoantibodies, and recessive blood type alleles cannot be detected in the heterozygous state [12–14]. Therefore, molecular approaches that are capable of detecting DNA variants underlying the phenotypic blood type have been established to complement immunohematological methods as diagnostic tools in humans [19, 20]. They cannot resolve all complex clinical situations, but these methods are readily standardized as well as automated and lend themselves to high throughput.

While in humans CMAH is a pseudogene due to an universal ancestral large deletion, the CMAH enzyme, when functional, converts NeuAc (type B antigen) to NeuGc (type A) in domestic cats [3]. In limited prior studies, several SNVs have been found in the feline CMAH gene, and a few variants, without showing their deleterious effects, were thought to be related to blood type B and C. Furthermore, when genotyping cats with those variants, blood typing results showed inconsistent phenotype to genotype correlations. In this large survey of 421 carefully blood typed cats, we demonstrate few specific CMAH variants, predicted to be deleterious by PROVEAN, to be responsible for blood type B and C, and describe a novel genotyping scheme to accurately determine blood type A, B, and C in cats.

In this study we show that the variant c.268T>A was homozygously present in 86% of all type B cats. The remaining type B cats were either homozygous for the variants c.179G>T and c.1322delT or compound heterozygous for two of these three SNVs. Genotyping these three SNVs leads to an excellent screening method to molecularly type cats for blood type A and B (99%). Thereby, we propose a genotyping scheme with four variants c.179C>T, c.268T>A, c.1322delT (for blood type B) and c.364C>T to include the most common variant for blood type C (Table 4).

Homozygosity or heterozygosity of the wildtype T at position c.268 (p.90Tyr) consistently predicted blood type A as expected for a dominant trait. The c.268T codes for non-polar tyrosine in the functional domain of the CMAH enzyme (Rieske-domain), while the variant A at position c.268 results in a polar asparagine acid (p.90Asn) which is predicted to be deleterious and to cause enzymatic dysfunction. And indeed, p.90Asn homozygosity (genotype b/b) explained blood type B in 86% of typed cats in this study. In contrast, the previously reported nsSNV c.142G>A [8] is predicted to be a neutral valine to methionine (Val48Met) exchange, and while frequently co-segregating, it also was found to be non-predictive in 15.6% of the cats studied here. In fact the missense variant c.142G>A (p.Val48Met), which was proposed to be a DNA diagnostic marker for type B blood [8], is predicted to be neutral by PROVEAN and was indeed observed with all three blood types in this study. Thus, determining the c.268T>A nsSNV (p.Tyr90Asn), and not c.142G>A, is most critical in screening and differentiating type A and B cats. Other nsSNVs seen in type A cats in this study either co-segregated with c.268T and were neutral or could be attributed to diplotypes causing type B blood when homozygous or compound heterozygous.

The previously reported [11] but ignored variant c.179G>T (p.Gly60Val) and newly discovered c.1322delT (p.Leu441*) variant in CMAH are predicted to be deleterious and are shown here to also result in type B blood when homozygous (b/b) for either in Turkish Angora (and thus likely Turkish Van) and Ragdoll cats, respectively. Furthermore, some DSH cats (e.g. from Israel) were either also homozygous for c.179T variant or were probably compound heterozygotes in combination with the c.268A variant. All type B Ragdolls were either homozygous c.268A or c.1322delT or were likely compound heterozygotes at these two positions. Thus, when screening cats by combining the missense variants c.268T>A and c.179G>T and nonsense variant c.1322delT, we were able to genotypically classify 99.5% of the 351 screened type A and B cats; missing two type B cats with different variants (see below).

Based upon these analyses, the previously described [10] missense variant c.364C>T (p.Pro122Ser) is predicted to be deleterious, and diminishes CMAH activity permitting both A and B antigen expression in 12 homozygous (a^c/ a^c) type C Ragdolls. All nine heterozygous type C Ragdolls (genotype a^c/b) showed a heterozygous state at either position c.268 or c.1322. Furthermore, we propose that c.179G>T (Gly60Val) in a heterozygous state may have impaired CMAH activity and led to blood type C as seen in six DSH cats and one Siberian cat as seen in this study here.

Thus, including the c.364C>T (p.Pro122Ser) in a genotyping screening program will identify many but not all C type cats and should be combined with testing for c.268T>A (p.Tyr90Asn), c.1322delT (p.Leu441*), and c.179G>T (Gly60Val) (Table 4). The initial step is the variant c.268T>A, because the c.268T>A variant (genotype AA) was responsible for the vast majority of type B cats (86%). Heterozygous cats with genotype TA at position 268 may have blood type A and simply carry the b allele or have type B or C blood based upon other variants shown above or to be determined.

Homozygosity for the deletion c.1322delT can be responsible for type B alone or as a compound heterozygote with c.268T>A. Determination of just these two variants permitted the correct identification of all type A and B Ragdolls but not type C Ragdolls.

Homozygosity at nsSNV c.179 (genotype TT) also causes type B as shown here in Turkish Angora (and likely related Van) cats as well as related Neva Masquerade but also type B DSH cats from Israel and Turkish DSH cats (unpublished).

Homozygosity for T at position c.364 is not the only genotype associated with type C, compound heterozygotes with c.364CT and c.268TA or c.179CT may also result in type C in Ragdolls and other breeds of cats.

Unfortunately, in vitro gene expression studies were neither performed nor in previously published studies. Blood type relates directly to the expression of NeuAc and/or NeuGc which was shown in our prior studies by thin layer chromatography and flow cytometry [6]. Furthermore, we used three typing methods to assure proper classification or RBC antigen expression. However, we did not perform further biochemical and gene expression studies to directly document the reduced enzymatic CMAH activity and did not perform crystallographic and other structural analyses of CMAH.

In feline medicine, genotyping for the AB blood group system is highly desirable to confirm the rare B and C blood types, to assure A-B compatible transfusions, and to determine if a type A cat carries one b (A/b) or a^c (A/a^c) allele for breeding. Based upon our identification of deleterious genetic variants in the CMAH gene and correlation to the phenotypic A, B, and C blood types, we propose, in combination with immunohematological typing, a novel simple genotyping algorithm which may be expanded when additional variants are identified as causes of type B and C in certain breeds and geographic regions. The proposed algorithm for determining blood types A, B, and C can be readily standardized and automated by software programs to assure technical as well as blood type calling accuracy. However, finding additional unique variants in certain breeds and geographic regions, as already shown here with this study, also illustrates that other variants may be found causing type B and C and thus the algorithm may need to be expanded in the future. This should not be difficult considering the ease of multiplexing and expanding existing panels.

In summary, we sequenced the CMAH coding and regulatory region of 70 cats and genotyped additional 351 carefully blood typed purebred and non-pedigreed cats and document novel variants predicting hydrolase dysfunction and unique haplotypes to explain their blood type A, B, and C. Thereby, a new diagnostic scheme to genotype all cats for the AB blood group system differentiating types A, B, and C was shown to be 99% accurate and is proposed to replace prior genotyping schemes. Furthermore, additional genetic variants responsible for type A, B, and C in unique breeds or geographical regions could be simply added to this genotyping scheme.