Identification of Markers by Simultaneous Tests in a Set of Quantifying Dependences

Abstract

In this paper we describe the algorithm of identification of markers by simultaneous tests in a set of quantifying dependences. The algorithm is based on the application of special simultaneous tests. The basic algorithmic construction of the tests used has already been described in this journal. It is the “Test of the Hypothesis That One group of Dependences is Consistent with Another Group of Dependences” for the case in which the error disturbances of the data have normal distribution. Possible efficiency of the algorithm of marker identification was verified on a solution of renal cell carcinoma biomarker identification in mass spectra (MS). The proposed algorithm is generally applicable for an arbitrary problem of marker identification by simultaneous tests in a set of quantifying dependences.