One of the major challenges in cancer diagnosis from microarray data is to develop highly accurate and robust classification models which are independent of the analysis techniques used and can combine data from different laboratories. We present a novel, robust meta-classification scheme originally developed for phenotype identification from mass spectrometry data. The method uses a robust multivariate gene selection procedure and combines the results of several machine learning tools trained on raw and pattern data to produce an accurate meta-classifier. We illustrate and validate our method by applying it to distinguish prostate cancer patients from controls on a mass spectrometry dataset and also to distinguish diffuse large B-cell lymphoma from follicular lymphoma on two independent gene expression datasets.