Prostate cancer biomarker identification using MALDI-MS DATA: Initial results

We present a computational framework to identify prostate specific cancer biomarkers using matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) tissue imaging data collected at the Eastern Virginia Medical School (EVMS). Protein profiles of a tumor and its surrounding area from one prostate tissue sample were analyzed. The data contain 974 spectra (27 cancer, 947 normal). We proposed a pipeline to configure our previously developed feature selection and classification algorithms for biomarker identification. We also compared our algorithms with other popular computational models. Our feature selection algorithm identified three peaks (proteins) which obtained high sensitivities and specificities in a five-fold cross validation experiment.