Time-frequency analysis for cancer detection using proteomic MS-spectra

Abstract

Mass spectrum data is proven useful in cancer detection and biomarker discovery. Nevertheless, existing methods which analyze peaks of mass spectrum data still have some limitations, including variation in peak locations among individual samples, noisy data, irreproducibility of peak profiles, and computational burden. We introduce a simple algorithm in this paper which alleviate these drawbacks. Our approach is to analyze the mass spectrum data using time-frequency analysis. The data is transformed to features in the time-frequency domain. Informative features are then selected and subsequently used for detection or classification. To assess the efficacy of the proposed algorithm, we apply our algorithm to cancer detection problem. The performance of the algorithm is evaluated on real ovarian and prostate cancer datasets. The promising detection results with high sensitivity and specificity confirm the potential of our method in cancer detection. The algorithm is also applicable to multi-class classification and biomarker identification problems.

Evaluation of computer methods for biomarker discovery on computational grids

“…Samples are considered more similar on how close these factors are to each other (Lazar et al 2012). Limpiti et al (2012) made a frequency analysis on proteomic mass spectrometry data combining several statistical feature selection approaches, obtaining an accurate cancer detection method. A similar approach was used in Cheng et al (2011) analyzing HBV virus DNA sequences.…”