Sofia K. Gruvberger-Saal, Patrik Edén, Markus Ringnér, Bo Baldetorp, Gunilla Chebil, Åke Borg, Mårten Fernö, Carsten Peterson and Paul S. Meltzer Predicting Continuous Values of Prognostic Markers in Breast Cancer from Microarray Gene Expression Profiles Molecular Cancer Therapeutics 3, 161-168 (2004) Abstract: The prognostic and treatment predictive markers currently in use for breast cancer are commonly based on the protein levels of individual genes (e.g. steroid receptors), or aspects of the tumor phenotype such as histological grade and percent of cells in the DNA synthesis phase of the cell cycle. Microarrays have previously been used to classify binary classes in breast cancer such as estrogen receptor alpha (ER) status. To test whether the properties and specific values of conventional prognostic markers are encoded within tumor gene expression profiles, we have analyzed 48 well-characterized primary tumors from lymph node-negative breast cancer patients using 6728-element cDNA microarrays. In the present study we show that artificial neural networks fed with tumor gene expression data can be used to predict the ER protein values on a continuous scale. Furthermore, we determined a gene expression profile-directed threshold for ER protein level to redefine the cut-off between ER-positive and ER-negative classes that may be more biologically relevant. With a similar approach, we studied the prediction of other prognostic parameters such as percent cells in the S-phase of the cell cycle, histological grade, DNA ploidy status, and progesterone receptor status. This and similar studies may be used to increase our understanding of the biology underlying these markers as well as to improve the currently available prognostic markers for breast cancer. LU TP 02-42