A brief introduction to high throughput technologies for measuring and analyzing gene expression is given. Various supervised and unsupervised data mining methods for analyzing the produced high-dimensional data are discussed. The main emphasis is on supervised machine learning methods for classification and prediction of tumor gene expression profiles. Furthermore, methods to rank the genes according to their importance for the classification are explored. The approaches are illustrated by exploratory studies using two examples of retrospective clinical data from routine tests; diagnostic prediction of small round blue cell tumors (SRBCT) of childhood and determining the estrogen receptor (ER) status of sporadic breast cancer. The classification performance is gauged using blind tests. These studies demonstrate the feasibility of machine learning-based molecular cancer classification.