INTRODUCTION:We hypothesised that gene expression in histologically normal (HN) epithelium (NlEpi) would differ between breast cancer patients and usual-risk controls undergoing reduction mammoplasty (RM), and that gene expression in NlEpi from cancer-free prophylactic mastectomy (PM) samples from high-risk women would resemble HN gene expression. METHODS: We analysed gene expression in 73 NlEpi samples microdissected from frozen tissue. In 42 samples, we used microarrays to compare gene expression between 18 RM patients and 18 age-matched HN (9 oestrogen receptor (ER) þ , 9 ERÀ) and 6 PM patients. Data were analysed using a Bayesian approach (BADGE), and validated with quantitative real-time PCR (qPCR) in 31 independent NlEpi samples from 8 RM, 17 HN, and 6 PM patients. RESULTS: A total of 98 probe sets (86 genes) were differentially expressed between RM and HN samples. Performing hierarchical analysis with these 98 probe sets, PM and HN samples clustered together, away from RM samples. qPCR validation of independent samples was high (84%) and uniform in RM compared with HN patients, and lower (58%), but more heterogeneous, in RM compared with PM patients. The 86 genes were implicated in many processes including transcription and the MAPK pathway. CONCLUSION: Gene expression differs between the NlEpi of breast cancer cases and controls. The profile of cancer cases can be discerned in high-risk NlEpi from cancer-free breasts. This suggests that the profile is not an effect of the tumour, but may mark increased risk and reveal the earliest genomic changes of breast cancer.