PCNA/CYCLIN EXPRESSION AND BRDU UPTAKE DEFINE DIFFERENT SUBPOPULATIONS IN DIFFERENT CELL-LINES

Monoclonal antibodies (MAb) to a 36 KD protein, proliferating cell nuclear antigen (PCNA/cyclin), have been previously shown to be capable of identifying proliferating cells in vitro as well as in alcohol-fixed, paraffin-embedded tissue specimens. The routine use of these anti-PCNA/cyclin MAb in investigative studies and in diagnostic pathology requires a clearer understanding of the distribution of PCNA/cyclin in the different cell populations found in tissue specimens. We therefore compared the ability of MAb to three nucleus-associated proliferation markers (MAb 19A2 to PCNA/cyclin; Ki-67 to an undefined proliferation-related marker; BU-1 to 5'-bromodeoxyuridine (BrdU) incorporated into DNA) to identify the proliferating cell fraction of various cells in vitro. The cell lines were chosen to represent a spectrum of proliferation rates (high to low) and cell lineage (mesenchymal vs epithelial, non-transformed vs malignant): (a) HeLa and A-431 (two malignant carcinoma cell lines with high proliferation rates); (b) SK-5 (a non-transformed fibroblast cell line with a low proliferation rate); (c) HUVE (a non-transformed human umbilical vein endothelial cell line with a low proliferation rate). Single and double labeling immunofluorescence studies were performed after uniform 1-hr incubations with BrdU. Comparison of the overlapping distributions of detectable PCNA/cyclin expression and BrdU incorporation demonstrated substantial qualitative and quantitative differences between the different cell lines. In two of the four cell lines (HeLa, A-431) the BrdU staining distributions formed inclusive subsets of the PCNA-positive cell populations. In the HUVE cell line the two populations overlapped incompletely. In one cell line, SK-5, the two populations were mutually exclusive. MAb Ki-67 demonstrated a pattern in the SK-5 cell line that was strongly predictive of PCNA positivity, while showing no associated patterns in the other three cell lines. We conclude that PCNA/cyclin expression detected by MAb may define different cell subpopulations in different cell types relative to those incorporating BrdU or expressing the target antigen for Ki-67. This has implications for the clinical study of mixed cell populations using these antibodies.