The present invention provides a method for predicting the treatment response of a human gastroesophageal cancer patient, the method comprising: a) measuring the gene expression of at least 3 of the following genes: CDH1, CDK6, COX2, ELOVL5, GATA4, EGFR, TBCEL, FGF7, CDH17, FNBP1, PIP5K1B, TWIST, CD44, MET, CEACAM1, TOX3, GLIPR2, GSTP1, RON, TMEM136, MYB, BRCA2, FGF1, POU5F1, EPR, DPYD, ABL2 and SH3RF1 in a sample obtained from the gastroesophageal tumour of the patient to obtain a sample gene expression profile of at least said genes; and b) making a prediction of the treatment response and/or prognosis of the patient based on the sample gene expression profile. Also provided are related computer-implemented methods and methods of treatment of gastroesophageal cancer.