Alteration of gene expression profiles during chemotherapy may predict response to neoadjuvant chemotherapy (NAC) in breast cancer patients. In a prospective cohort study of 32 women with primary invasive breast cancer, we obtained tumor specimens before and after 4 cycles of NAC with epirubicine 90 mg/m2 and cyclophosphamide 600 mg/m2, followed by 4 cycles of docetaxel 100 mg/m2. Total-RNA was extracted from tumor specimens and the whole transcriptome was analyzed with Agilent's 44K single color microarray. Data analysis was performed by GeneSpring v.11 and IBM SPSS v.18. Ten tumors were classified as basal-like and 22 tumors were classified as non-basal-like. Gene expression-based molecular subtype (basal-like vs. non-basal-like) (P=0.003), but not tumor grade (P=0.07), estrogen receptor (P=0.1), progesterone receptor (P=0.6) and HER2 status (P=0.4) predicted pathological complete response to NAC. Specifically, 7/10 basal-like tumors responded to NAC, whereas 19/22 non-basal-like tumors did not respond. Comparing gene expression signatures before and after 4 cycles of NAC, we found that all patients with an initial non-basal-like tumor retained this tumor type, whereas 5/7 basal-like tumors, including all responders, lost this molecular subtype. Complete prediction of response to NAC was achieved with a 21 gene list (P=0.000008). Of note, both the expression and up-regulation of a single gene, i.e. HER4, predicted the response to NAC in 26/32 (81%; P=0.002) and in 23/25 (92%; P<0.001) patients, respectively. These preliminary data indicate that therapy-induced HER4 gene up-regulation may be associated with response to NAC with epirubicine, cyclophosphamide and docetaxel.