Premium
Probing genetic algorithms for feature selection in comprehensive metabolic profiling approach
Author(s) -
Zou Wei,
Tolstikov Vladimir V.
Publication year - 2008
Publication title -
rapid communications in mass spectrometry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.528
H-Index - 136
eISSN - 1097-0231
pISSN - 0951-4198
DOI - 10.1002/rcm.3507
Subject(s) - chemistry , feature selection , metabolomics , biomarker discovery , cluster analysis , chromatography , artificial intelligence , profiling (computer programming) , mass spectrometry , discriminative model , pattern recognition (psychology) , chemometrics , random forest , machine learning , computational biology , proteomics , computer science , biochemistry , biology , gene , operating system
Six different clones of 1‐year‐old loblolly pine ( Pinus taeda L.) seedlings grown under standardized conditions in a green house were used for sample preparation and further analysis. Three independent and complementary analytical techniques for metabolic profiling were applied in the present study: hydrophilic interaction chromatography (HILIC‐LC/ESI‐MS), reversed‐phase liquid chromatography (RP‐LC/ESI‐MS), and gas chromatography all coupled to mass spectrometry (GC/TOF‐MS). Unsupervised methods, such as principle component analysis (PCA) and clustering, and supervised methods, such as classification, were used for data mining. Genetic algorithms (GA), a multivariate approach, was probed for selection of the smallest subsets of potentially discriminative classifiers. From more than 2000 peaks found in total, small subsets were selected by GA as highly potential classifiers allowing discrimination among six investigated genotypes. Annotated GC/TOF‐MS data allowed the generation of a small subset of identified metabolites. LC/ESI‐MS data and small subsets require further annotation. The present study demonstrated that combination of comprehensive metabolic profiling and advanced data mining techniques provides a powerful metabolomic approach for biomarker discovery among small molecules. Utilizing GA for feature selection allowed the generation of small subsets of potent classifiers. Copyright © 2008 John Wiley & Sons, Ltd.