Deriving Lipid Classification Based on Molecular Formulas
Open Access
- 24 March 2020
- journal article
- research article
- Published by MDPI AG in Metabolites
- Vol. 10 (3) , 122
Abstract
Despite instrument and algorithmic improvements, the untargeted and accurate assignment of metabolites remains an unsolved problem in metabolomics. New assignment methods such as our SMIRFE algorithm can assign elemental molecular formulas to observed spectral features in a highly untargeted manner without orthogonal information from tandem MS or chromatography. However, for many lipidomics applications, it is necessary to know at least the lipid category or class that is associated with a detected spectral feature to derive a biochemical interpretation. Our goal is to develop a method for robustly classifying elemental molecular formula assignments into lipid categories for an application to SMIRFE-generated assignments. Using a Random Forest machine learning approach, we developed a method that can predict lipid category and class from SMIRFE non-adducted molecular formula assignments. Our methods achieve high average predictive accuracy (>90%) and precision (>83%) across all eight of the lipid categories in the LIPIDMAPS database. Classification performance was evaluated using sets of theoretical, data-derived, and artifactual molecular formulas. Our methods enable the lipid classification of non-adducted molecular formula assignments generated by SMIRFE without orthogonal information, facilitating the biochemical interpretation of untargeted lipidomics experiments. This lipid classification appears insufficient for validating single-spectrum assignments, but could be useful in cross-spectrum assignment validation.Keywords
Funding Information
- National Institutes of Health (UL1TR001998-01)
- National Science Foundation (1419282)
This publication has 62 references indexed in Scilit:
- LipidHome: A Database of Theoretical Lipids Optimized for High Throughput Mass Spectrometry LipidomicsPLOS ONE, 2013
- Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker SelectionEvidence-Based Complementary and Alternative Medicine, 2013
- ERROR ANALYSIS AND PROPAGATION IN METABOLOMICS DATA ANALYSISComputational and Structural Biotechnology Journal, 2013
- Novel biomarkers for pre‐diabetes identified by metabolomicsMolecular Systems Biology, 2012
- FAT SIGNALS - Lipases and Lipolysis in Lipid Metabolism and SignalingCell Metabolism, 2012
- Mass Spectrometry Based Lipidomics: An Overview of Technological PlatformsMetabolites, 2012
- High sensitivity quantitative lipidomics analysis of fatty acids in biological samples by gas chromatography–mass spectrometryBiochimica et Biophysica Acta (BBA) - Molecular and Cell Biology of Lipids, 2011
- Isotopomer analysis of lipid biosynthesis by high resolution mass spectrometry and NMRAnalytica Chimica Acta, 2009
- Lipidomic analysis of twenty‐seven prostanoids and isoprostanes by liquid chromatography/electrospray tandem mass spectrometryRapid Communications in Mass Spectrometry, 2006
- Mass spectrometry‐based metabolomicsMass Spectrometry Reviews, 2006