Premium
Comprehensive feature analysis for sample classification with comprehensive two‐dimensional LC
Author(s) -
Reichenbach Stephen E.,
Tian Xue,
Tao Qingping,
Stoll Dwight R.,
Carr Peter W.
Publication year - 2010
Publication title -
journal of separation science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.72
H-Index - 102
eISSN - 1615-9314
pISSN - 1615-9306
DOI - 10.1002/jssc.200900859
Subject(s) - chromatography , replicate , sample (material) , sample preparation , pattern recognition (psychology) , support vector machine , set (abstract data type) , feature (linguistics) , artificial intelligence , chemistry , computer science , data mining , mathematics , statistics , programming language , linguistics , philosophy
Comprehensive two‐dimensional LC (LC×LC) is a powerful tool for analysis of complex biological samples. With its multidimensional separation power and increased peak capacity, LC×LC generates information‐rich, but complex, chromatograms, which require advanced data analysis to produce useful information. An important analytical challenge is to classify samples on the basis of chromatographic features, e.g. , to extract and utilize biomarkers indicative of health conditions, such as disease or response to therapy. This study presents a new approach to extract comprehensive non‐target chromatographic features from a set of LC×LC chromatograms for sample classification. Experimental results with urine samples indicate that the chromatographic features generated by this approach can be used to effectively classify samples. Based on the extracted features, a support vector machine successfully classified urine samples by individual, before/after procedure, and concentration with leave‐one‐out and replicate K ‐fold cross‐validation. The new method for comprehensive chromatographic feature analysis of LC×LC separations provides a potentially powerful tool for classifying complex biological samples.