Phospholipid fatty acid biomarkers in a freshwater periphyton community exposed to uranium: discovery by non-linear statistical learning

Abstract

Phospholipid fatty acids (PLFA) have been widely used to characterize environmental microbial communities, generating community profiles that can distinguish phylogenetic or functional groups within the community. The poor specificity of organism groups with fatty acid biomarkers in the classic PLFA-microorganism associations is a confounding factor in many of the statistical classification/clustering approaches traditionally used to interpret PLFA profiles. In this paper we demonstrate that non-linear statistical learning methods, such as a support vector machine (SVM), can more accurately find patterns related to uranyl nitrate exposure in a freshwater periphyton community than linear methods, such as partial least squares discriminant analysis. In addition, probabilistic models of exposure can be derived from the identified lipid biomarkers to demonstrate the potential model-based approach that could be used in remediation. The SVM probability model separates dose groups at accuracies of ∼87.0%, ∼71.4%, ∼87.5%, and 100% for the four groups; Control (non-amended system), low dose (amended at 10 μg U L −1), medium dose (amended at 100 μg U L −1), and high dose (500 μg U L −1). The SVM model achieved an overall cross-validated classification accuracy of ∼87% in contrast to ∼59% for the best linear classifier.