Search

Aim: We investigated the use of non-linear, multidimensional factor analysis for the study of observational data on death from breast cancer. These data were obtained in the context of a clinical practice and not in a clinical trial. We looked into the correlations between patient characteristics and time of death and/or disease-free interval., Patients and Methods: We first analyzed the characteristics of a population of patients that had died from breast cancer (n = 295), then of a population including patients still alive 7 years after surgery (n = 344). We used correspondence analysis (CA) which is based on chi(2)-metrics, does not assume linear relationships, and provides graphic overviews., Results: The CA mapped variables (clinical stage, histoprognostic grade, node status, receptor positivity) in a way that fits in well with available knowledge on their importance as prognostic factors. We observed, however, that death occurred during three main periods (1-3, 4-7, < OR = 8 years after surgery) defined by different mixes of variables as if the disease progressed by stage rather than continuously. The CA distinguished long-term survivors (>7 years) from patients who died 8-10 years after surgery. Long-term survivors tended to be node-negative; those who died at 8-10 years tended to be the youngest patients (under 40)., Conclusions: Because correspondence analysis combines the advantages of multidimensional and non-linear methods, it is a valuable exploratory tool for describing multiple correlations within a population before attempting to establish statistical significance of selected variables by more classic methods.

A multivariate statistical method, correspondence factorial (CF) analysis, was used to examine the correlations among the protein binding and cell proliferation effects of a series of 36 di- and triphenylethylenes (DPEs and TPEs). The analysis was applied to a study which measured their competition for estradiol binding to cytosol estrogen receptor (ER), their influence on protein kinase C (PKC) activity under different conditions of enzyme activation, their ability to promote the growth of a breast cancer cell line and to inhibit growth at high concentrations (cytotoxicity). The CF analysis revealed several levels of correlation. First, it distinguished those molecules within the population that stimulated rather than inhibited PKC activity. Second, it made apparent a strong correlation between cytotoxicity and inhibition of Ca++ and phosphatidylserine-dependent PKC activity, which was most marked when the enzyme had been activated by diacylglycerol indicating that PKC inhibition under physiological conditions might contribute to the overall cytotoxicity of these compounds. Third, a lower level of correlation was established between competition for ER binding and cytotoxicity. Taken together, the results suggest that MCF7 cells might be most sensitive to a cytotoxic effect of TPEs (via PKC and other targets) when they at the same time decrease estrogen-stimulated proliferation via an ER-mediated antiestrogenic effect.

In a study of a series of 26 triphenylacrylonitrile derivatives (TPEs), we investigated the influence of several possibly interrelated factors on the proliferation of human breast cancer cell lines. (1) Chemical substituents: the test compounds were for the most part para-hydroxylated with increasingly bulky hydrophobic and/or basic side chains [isopropyloxy or (diethylamino)ethoxy] or standard reference compounds. (2) Relative binding affinities (RBAs): they competed diversely for [3H]estradiol (E2) binding to calf uterus cytosol and little, if at all, for binding to the [3H]tamoxifen-labeled antiestrogen binding site (AEBS) in lower speed supernatant. A multiparametric comparison of RBAs recorded for calf, rat, and mouse uterus cytosol estrogen receptor (ER) revealed a possible influence of species-specific receptor conformation and/or environment on binding. (3) Estrogen/antiestrogen potency: their stimulation and inhibition of the proliferation of the ER-positive human breast cancer cell line (MCF7) was measured. Compounds with only hydroxy substituents stimulated proliferation more markedly than methylated derivatives and had a maximum effect at 10(-11)-10(-6) M. Stimulation was related to the RBA for ER. Compounds with isopropyloxy or (diethylamino)ethoxy side chains only weakly stimulated MCF7 cell growth and more powerfully antagonized E2-promoted growth. The extent of inhibition depended upon the bulk of the side chain and could be reversed by 10(-7) M E2. Within the same concentration ranges, the test compounds were without effect on the BT20 ER-negative cell line. (4) Cytostatic and/or cytolytic activity: most compounds could arrest the proliferation of both MCF7 and BT20 cells at concentrations above 3 x 10(-6) M. This activity was thus independent of ER. Nevertheless, those compounds with a charged hydrophobic side chain, which were the most powerful antagonists of E2-promoted cell growth, were also the most cytotoxic. The overall results for all molecules on all parameters were submitted to a multivariate analysis (correspondence analysis) which revealed the progressive influence of increasing substitution by hydroxy and more bulky groups on the generation of antagonist activity and cytotoxicity.