Molecular classification of selective oestrogen receptor modulators on the basis of gene expression profiles of breast cancer cells expressing oestrogen receptor alpha

Abstract

The purpose of this study was to classify selective oestrogen receptor modulators based on gene expression profiles produced in breast cancer cells expressing either wtERalpha or mutant(351)ERalpha. In total, 54 microarray experiments were carried out by using a commercially available Atlas cDNA Expression Arrays (Clontech), containing 588 cancer-related genes. Nine sets of data were generated for each cell line following 24 h of treatment: expression data were obtained for cells treated with vehicle EtOH (Control); with 10(-9) or 10(-8) M oestradiol; with 10(-6) M 4-hydroxytamoxifen; with 10(-6) M raloxifene; with 10(-6) M idoxifene, with 10(-6) M EM 652, with 10(-6) M GW 7604; with 5 x 10(-5) M resveratrol and with 10(-6) M ICI 182,780. We developed a new algorithm 'Expression Signatures' to classify compounds on the basis of differential gene expression profiles. We created dendrograms for each cell line, in which branches represent relationships between compounds. Additionally, clustering analysis was performed using different subsets of genes to assess the robustness of the analysis. In general, only small differences between gene expression profiles treated with compounds were observed with correlation coefficients ranged from 0.83 to 0.98. This observation may be explained by the use of the same cell context for treatments with compounds that essentially belong to the same class of drugs with oestrogen receptors related mechanisms. The most surprising observation was that ICI 182,780 clustered together with oestrodiol and raloxifene for cells expressing wtERalpha and clustered together with EM 652 for cells expressing mutant(351)ERalpha. These data provide a rationale for a more precise and elaborate study in which custom made oligonucleotide arrays can be used with comprehensive sets of genes known to have consensus and putative oestrogen response elements in their promoter regions.

Figure 1

Expression signatures of cells treated with different compounds (E2, SERMs and ICI) versus the untreated control cells are shown. Eighty-seven selected genes were used to create ‘Signatures’ for cells expressing wtERα (A) and dendrogram representing similarities in the expression patterns of cells treated with different compounds were created from ‘expression signatures’ on the basis of data from distance metric and correlation coefficients (B). The branching patterns in the resulting dendrogram organised the compounds into three main groups: E2 : Ral : ICI; 4OHT : GW; and Res : Idox: EM. Normalised values for selected subset of genes were used for all manipulations. The values of normalised adjusted intensities representing levels of expressions of the vehicle-treated control (X-axis) and the compound-treated (Y-axis) cells are shown for A.

Figure 2

Expression signatures of cells treated with different compounds (E2, SERMs and ICI) versus the untreated control cells are shown. One hundred and 17 selected genes were used to create ‘Signatures’ for cells expressing mutant₃₅₁ERα (D351Y) (A) and dendrogram representing similarities in the expression patterns of cells treated with different compounds were created from ‘expression signatures’ on the basis of data from distance metric and correlation coefficients (B). The branching patterns in the resulting dendrogram organised the compounds into three main groups: E2 : 4OHT : Ral; ICI : EM; and GW : Idox: Res. Normalised values for selected subset of genes were used for all manipulations. The values of normalised adjusted intensities representing levels of expressions of the vehicle-treated control (X-axis) and the compound-treated (Y-axis) cells are shown for A.

Figure 3

Gene expression patterns of cells expressing wtER related to treatment with compounds (E2, SERMs and ICI). Two-dimensional hierarchical clustering was applied to up-regulated subset of expression data from a total of 588 cDNAs measured across seven different treatments. A cluster dendrogram representing the hierarchical relationships between gene expression profiles of cells (vertically) and compounds (horizontally) was then generated. Colour-coded gene expression values for genes are shown. The colour reflects the mean-adjusted expression level of the gene: black is the mean, red is greater than the mean and green is less than the mean.