Lars J. Kangas, Thomas O. Metz, Giorgis Isaac, Brian T. Schrom, Bojana Ginovska-Pangovska, Luning Wang, Li Tan, Robert R. Lewis and John H. Miller. In Bioinformatics. Vol. 28 no. 13. Oxford Press. 2012.
Motivation: Liquid chromatography–mass spectrometry-based metabolomics has gained importance in the life sciences, yet it is not supported by software tools for high throughput identification of metabolites based on their fragmentation spectra. An algorithm (ISIS: in silico identification software) and its implementation are presented and show great promise in generating in silico spectra of lipids for the purpose of structural identification. Instead of using chemical reaction rate equations or rules-based fragmentation libraries, the algorithm uses machine learning to find accurate bond cleavage rates in a mass spectrometer employing collision-induced dissociation tandem mass spectrometry.
Results: A preliminary test of the algorithm with 45 lipids from a subset of lipid classes shows both high sensitivity and specificity.