Systematic classification of unknown metabolites using high-resolution fragmentation mass spectra

By Kai Dührkop, Louis-Félix Nothias, Markus Fleischauer, R. Reher, M. Ludwig, Martin A. Hoffmann, D. Petráš, W. Gerwick, Juho Rousu, Pieter C. Dorrestein and 1 more. Nature Biotechnology, 2020

678 citations recorded by the source corpus.

Metabolomics using nontargeted tandem mass spectrometry can detect thousands of molecules in a biological sample. However, structural molecule annotation is limited to structures present in libraries or databases, restricting analysis and interpretation of experimental data. Here we describe CANOPUS (class assignment and ontology prediction using mass spectrometry), a computational tool for systematic compound class annotation. CANOPUS uses a deep neural network to predict 2,497 compound classes from fragmentation spectra, including all biologically relevant classes. CANOPUS explicitly targets compounds for which neither spectral nor structural reference data are available and predicts classes lacking tandem mass spectrometry training data. In evaluation using reference data, CANOPUS reached very high prediction performance (average accuracy of 99.7% in cross-validation) and outperformed four baseline methods. We demonstrate the broad utility of CANOPUS by investigating the effect of microbial colonization in the mouse digestive system, through analysis of the chemodiversity of different Euphorbia plants and regarding the discovery of a marine natural product, revealing biological insights at the compound class level. Unknown metabolites are classified from mass spectrometry data.

Subfields: Molecular Biology, Pharmacology, Spectroscopy

View Paper: https://www.semanticscholar.org/paper/99d560df65eca2974bd6e0542bcad0503e5bcd79

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

1. Kai Blin
2. Philippe Schwaller
3. Marnix H. Medema
4. Nadine Ziemert
5. Maria Sorokina
6. Marwin H. S. Segler
7. Djork-Arné Clevert
8. Marcy J. Balunas

In Pharmacology

1. Kai Blin
2. Marnix H. Medema
3. Nadine Ziemert
4. Maria Sorokina
5. Marcy J. Balunas
6. Andrea Volkamer

In Spectroscopy

1. Philippe Schwaller
2. Marwin H. S. Segler
3. Andrea Volkamer
4. Nadine Ziemert

Citations in the corpus

• Artificial Intelligence For Natural Product Drug Discovery (2023, methodology): “Therefore, AI has been leveraged to target common challenges in MS-based metabolome mining 23 , including library matching and searching using mass spectral similarity metrics 24,25 , molecular formula annotation 26,27 , molecular class annotation 28,29 and retention time prediction 30 .”