Feature selection for OPLS discriminant analysis of cancer tissue lipidomics data.

The mass spectrometry‐based molecular profiling can be used for better differentiation between normal and cancer tissues and for the detection of neoplastic transformation, which is of great importance for diagnostics of a pathology, prognosis of its evolution trend, and development of a treatment strategy. The aim of the present study is the evaluation of tissue classification approaches based on various data sets derived from the molecular profile of the organic solvent extracts of a tissue. A set of possibilities are considered for the orthogonal projections to latent structures discriminant analysis: all mass spectrometric peaks over 300 counts threshold, subset of peaks selected by ranking with support vector machine algorithm, peaks selected by random forest algorithm, peaks with the statistically significant difference of the intensity determined by the Mann‐Whitney U test, peaks identified as lipids, and both identified and significantly different peaks. The best predictive potential is obtained for OPLS‐DA model built on nonpolar glycerolipids (Q2 = 0.64, area under curve [AUC] = 0.95); the second one is OPLS‐DA model with lipid peaks selected by random forest algorithm (Q2 = 0.58, AUC = 0.87). Moreover, models based on particular molecular classes are more preferable from biological point of view, resulting in new explanatory mechanisms of pathophysiology and providing a pathway analysis. Another promising features for OPLS‐DA modeling are phosphatidylethanolamines (Q2 = 0.48, AUC = 0.86). [ABSTRACT FROM AUTHOR]