Decision tree supported substructure prediction of metabolites from GC-MS profiles

Abstract

Gas chromatography coupled to mass spectrometry (GC-MS) is one of the most widespread routine technologies applied to the large scale screening and discovery of novel metabolic biomarkers. However, currently the majority of mass spectral tags (MSTs) remains unidentified due to the lack of authenticated pure reference substances required for compound identification by GC-MS. Here, we accessed the information on reference compounds stored in the Golm Metabolome Database (GMD) to apply supervised machine learning approaches to the classification and identification of unidentified MSTs without relying on library searches. Non-annotated MSTs with mass spectral and retention index (RI) information together with data of already identified metabolites and reference substances have been archived in the GMD. Structural feature extraction was applied to sub-divide the metabolite space contained in the GMD and to define the prediction target classes. Decision tree (DT)-based prediction of the most frequent substructures based on mass spectral features and RI information is demonstrated to result in highly sensitive and specific detections of sub-structures contained in the compounds. The underlying set of DTs can be inspected by the user and are made available for batch processing via SOAP (Simple Object Access Protocol)-based web services. The GMD mass spectral library with the integrated DTs is freely accessible for non-commercial use at http://gmd.mpimp-golm.mpg.de/. All matching and structure search functionalities are available as SOAP-based web services. A XML + HTTP interface, which follows Representational State Transfer (REST) principles, facilitates read-only access to data base entities.

High specificity in plant leaf metabolic responses to arbuscular mycorrhiza

“…Moreover, metabolome responses only marginally reflected phylogeny within the dicotyledonous species, but some general The analytical platform used for quantification, chromatographic parameters (RI, Kováts 41 retention index; RT, retention time), and mass characteristics (qualifier masses and quantifier mass of MSRI libraries 44 (as m/z, mass to charge ratios) for GC-MS, accurate masses for uHPLC-ToF-MS) are given. It is indicated whether metabolites were identified via comparison of peak characteristics (RI/RT, mass spectra) with the Golm metabolome database (GMD) 42,43 or reference standards (Std.). Names of organic acids are given both in protonated form and as anions.…”

Comprehensive Dissection of Spatiotemporal Metabolic Shifts in Primary, Secondary, and Lipid Metabolism during Developmental Senescence in Arabidopsis

“…The chromatograms and mass spectra were evaluated using TagFinder software (Luedemann et al, 2008) and NIST05 software (http://www.nist.gov/srd/mslist.cfm). Metabolite identification was manually supervised using the mass spectral and retention index collection of the Golm Metabolome Database (Kopka et al, 2005;Hummel et al, 2010). Peak heights of the mass fragments were normalized on the basis of the fresh weight of the sample and the added amount of an internal standard (ribitol for the whole-plant experiment and [ 13 C 6 ]sorbitol for the singleleaf experiment).…”

Metabolic and Transcriptomic Phenotyping of Inorganic Carbon Acclimation in the Cyanobacterium Synechococcus elongatus PCC 7942

“…The GC-time of flight-MS chromatograms were processed by TagFinder software (Luedemann et al, 2008). Compounds were identified by comparison with a reference library of mass spectra and retention indices from the collection of the Golm Metabolome database (Hummel et al, 2010). The resulting data set of the identified metabolites may be found in Supplemental Table S1.…”