Auto-deconvolution and molecular networking of gas chromatography–mass spectrometry data

We engineered a machine learning approach, MSHub, to enable auto-deconvolution of gas chromatography–mass spectrometry (GC–MS) data. We then designed workflows to enable the community to store, process, share, annotate, compare and perform molecular networking of GC–MS data within the Global Natural...

Full description

Saved in:

Bibliographic Details
Published in	Nature biotechnology Vol. 39; no. 2; pp. 169 - 173
Main Authors	Aksenov, Alexander A., Laponogov, Ivan, Zhang, Zheng, Doran, Sophie L. F., Belluomo, Ilaria, Veselkov, Dennis, Bittremieux, Wout, Nothias, Louis Felix, Nothias-Esposito, Mélissa, Maloney, Katherine N., Misra, Biswapriya B., Melnik, Alexey V., Smirnov, Aleksandr, Du, Xiuxia, Jones, Kenneth L., Dorrestein, Kathleen, Panitchpakdi, Morgan, Ernst, Madeleine, van der Hooft, Justin J. J., Gonzalez, Mabel, Carazzone, Chiara, Amézquita, Adolfo, Callewaert, Chris, Morton, James T., Quinn, Robert A., Bouslimani, Amina, Orio, Andrea Albarracín, Petras, Daniel, Smania, Andrea M., Couvillion, Sneha P., Burnet, Meagan C., Nicora, Carrie D., Zink, Erika, Metz, Thomas O., Artaev, Viatcheslav, Humston-Fulmer, Elizabeth, Gregor, Rachel, Meijler, Michael M., Mizrahi, Itzhak, Eyal, Stav, Anderson, Brooke, Dutton, Rachel, Lugan, Raphaël, Boulch, Pauline Le, Guitton, Yann, Prevost, Stephanie, Poirier, Audrey, Dervilly, Gaud, Le Bizec, Bruno, Fait, Aaron, Persi, Noga Sikron, Song, Chao, Gashu, Kelem, Coras, Roxana, Guma, Monica, Manasson, Julia, Scher, Jose U., Barupal, Dinesh Kumar, Alseekh, Saleh, Fernie, Alisdair R., Mirnezami, Reza, Vasiliou, Vasilis, Schmid, Robin, Borisov, Roman S., Kulikova, Larisa N., Knight, Rob, Wang, Mingxun, Hanna, George B., Dorrestein, Pieter C., Veselkov, Kirill
Format	Journal Article
Language	English
Published	New York Nature Publishing Group US 01.02.2021 Nature Publishing Group Springer Nature
Subjects	631/114/1314 639/638/11/296 Agriculture Algorithms Analysis Analytical chemistry Animals Anura Bioinformatics Biomedical and Life Sciences Biomedical Engineering/Biotechnology Biomedicine Biotechnology Brief Communication Chemical Sciences Chromatography Computer programs data processing Deconvolution Fragmentation Gas chromatography Gas Chromatography-Mass Spectrometry Humans Image processing Ions Learning algorithms Life Sciences Machine Learning Mass spectrometry Mass spectroscopy Metabolomics Methods Molecular simulation Natural products Networking Scientific imaging Social organization Spectroscopy Statistics Workflow United States France United Kingdom California Anura Metabolomics Animals Gas Chromatography-Mass Spectrometry Algorithms Humans
Online Access	Get full text
ISSN	1087-0156 1546-1696 1546-1696
DOI	10.1038/s41587-020-0700-3

Cover

More Information
Summary:	We engineered a machine learning approach, MSHub, to enable auto-deconvolution of gas chromatography–mass spectrometry (GC–MS) data. We then designed workflows to enable the community to store, process, share, annotate, compare and perform molecular networking of GC–MS data within the Global Natural Product Social (GNPS) Molecular Networking analysis platform. MSHub/GNPS performs auto-deconvolution of compound fragmentation patterns via unsupervised non-negative matrix factorization and quantifies the reproducibility of fragmentation patterns across samples. A machine learning workflow enables auto-deconvolution of gas chromatography–mass spectrometry data.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 PMCID: PMC7971188 European Research Council (ERC) AC05-76RL01830 PNNL-SA--150654 National Institutes of Health (NIH) USDOE Office of Science (SC), Biological and Environmental Research (BER) National Science Foundation RSB, LNK, MP, AAA assembled the initial version of the public reference spectra library AAA, AVM, MP, KJ, KD conducted 3D skin volatilome mapping studies AAA, RS, IB, AAO, AMS, BA, MG, KNM, RSB produced training videos MW, ZZ, AAA developed the workflows ZZ, AA, ME generated molecular network plots SD, IB, GH conducted oesophageal and gastric breath analysis cancers detection study AS, XD, AAA, BBM conducted comparative testing of MSHub with existing deconvolution tools PCD, AAA, WB, KV, RM, RK wrote the paper IL, DV, VV, KV developed the MSHub platform PCD, AAA, MW, LFN came up with the concept of GNPS for GC-MS data. AAA, AVM, SD, BBM, MG, CC, AA, JM, RQ, AB, AAO, DP, AMS, SPC, TOM, MCB, CDN, EZ, VA, EHF, RG, MMM, IM, SE, PLB, BA, RL, YG, SP, AP, GD, BLB, AF, NS, KG, CS, RC, MG, JM, JUS, DB, SA, AF generated GC-MS data MNE, AAA, MG, BBM, AS, LFN wrote and compiled tutorials and documentation WB generated plots for MSHub algorithm performance testing and benchmarking against existing deconvolution tools ME, JJJvdH adapted the MolNetEnhancer workflow for GC-MS Molecular Networks KV designed and supervised MSHub platform development AAA, ZZ, MW, BBM, RSB performed infrastructure testing and benchmarking RS created MZmine export module for GNPS GC-MS input files and RI markers file export Co-first author Author contributions AAA, ZZ assessed EI-based molecular networking AAA, ZZ, MP, MW converted and added public libraries to GNPS
ISSN:	1087-0156 1546-1696 1546-1696
DOI:	10.1038/s41587-020-0700-3