Charge Prediction of Lipid Fragments in Mass Spectrometry

Author

Schrom, B. ; Kangas, L. ; Ginovska, B. ; Metz, T. ; Miller, J.

Author_Institution

Pacific Northwest Nat. Labratory, Richland, WA, USA

Volume

2

fYear

2011

fDate

18-21 Dec. 2011

Firstpage

186

Lastpage

188

Abstract

An artificial neural network is developed for predicting which fragment is charged and which fragment is neutral for lipid fragment pairs produced from a liquid chromatography tandem mass spectrometry simulation process. This charge predictor is integrated into software developed at PNNL for in silico spectra generation and identification of metabolites known as Met ISIS. To test the effect of including charge prediction in Met ISIS, 46 lipids are used which show a reduction in false positive identifications when the charge predictor is utilized.

Keywords

biology computing; chromatography; mass spectra; molecular biophysics; neural nets; software engineering; Met ISIS; PNNL; artificial neural network; charge prediction; charge predictor; false positive identifications; in silico spectra generation; lipid fragment pairs; lipid fragments; lipids; liquid chromatography tandem mass spectrometry simulation process; metabolites identification; Artificial neural networks; Atomic measurements; Databases; Lipidomics; Testing; Training; Vectors; artificial neural network; lipid; machine learning; mass spectrometry;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Applications and Workshops (ICMLA), 2011 10th International Conference on

Conference_Location

Honolulu, HI

Print_ISBN

978-1-4577-2134-2

Type

conf

DOI

10.1109/ICMLA.2011.45

Filename

6147670