Application of proteomics coupled with pattern classification techniques to discover novel biomarkers that can be used for the predictive diagnoses of several cancer diseases. However, for effective classification, the extraction of good features that can represent the identities of different classes plays the frontal critical factor for any classification problems. In addition, another major problem associated with pattern recognition is how to effectively handle a large number of features. This paper address these two frontal issues for mass spectrometry (MS) classification. We apply the theory of linear predictive coding to extract features and vector quantization to reduce the storage of the large feature space of MS data. The proposed methodology was tested using two MS-based cancer datasets and the results are promising.