Expression of MUC1, MUC2 and oligosaccharide epitopes in breast cancer: Prognostic significance of a sialylated MUC1 epitope

MUC1 represents a promising marker in breast cancer. However, due to the structural complexity of the MUC1 glycoprotein, multiple epitopes can be detected by monoclonal antibodies. This fact may be responsible for the contradictory results of previous investigations regarding the clinical and prognostic relevance of MUC1 expression in breast cancer. Therefore, we tried to evaluate the role of different glycosylated and non-glycoslyated MUC1 epitopes as well as other mucin-associated peptides (MUC2) and carbohydrates (Thomsen-Friedenreich antigen, sialyl-Lewis(a), sialyl-Lewis(x)) as predictors of the clinical course and prognosis in mammary carcinomas. An immunohistochemical study applying numerous monoclonal antibodies (mabs) was performed to characterize the expression of a selected panel of MUC1 epitopes, and of MUC2, Thomsen-Friedenreich antigen, sialyl-Lewisa, and sialyl-Lewisx in a series of 140 patients with breast cancer. The results were correlated with clinicopathological variables as well as overall survival. Generally, more than 90% of the mammary cancers, were strongly stained with the MUC1-specific mabs. Especially ductal and lobular carcinomas were strongly MUC1- and sialyl Lewis(a)-positive, whereas MUC2 binding was significantly elevated in mucinous neoplasms. Associations between the immunoreactivity of any mab under study and tumor progression as reflected by pTNM staging could not be observed. However, expression of the sialylated MUC1 epitope detected by mab MY1.E12 was revealed as a favourable independent prognostic factor. These results confirm that MUC1 is generally strongly expressed in mammary carcinomas. As an exception, mucinous carcinomas are significantly less MUC1 reactive, but strongly express MUC2. Our data suggest that only the presence of a sialylated short-chain MUC1 glycoform is associated with a better prognosis, whereas the other molecules under study are not correlated with the course of disease and survival probability.