PeakDecoder enables machine learning-based metabolite annotation and accurate profiling in multidimensional mass spectrometry measurements

• Published in: Nature communications Vol. 14; no. 1; p. 2461
• Main Authors: Bilbao, Aivett, Munoz, Nathalie, Kim, Joonhoon, Orton, Daniel J., Gao, Yuqian, Poorey, Kunal, Pomraning, Kyle R., Weitz, Karl, Burnet, Meagan, Nicora, Carrie D., Wilton, Rosemarie, Deng, Shuang, Dai, Ziyu, Oksen, Ethan, Gee, Aaron, Fasani, Rick A., Tsalenko, Anya, Tanjore, Deepti, Gardner, James, Smith, Richard D., Michener, Joshua K., Gladden, John M., Baker, Erin S., Petzold, Christopher J., Kim, Young-Mo, Apffel, Alex, Magnuson, Jon K., Burnum-Johnson, Kristin E.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 28.04.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 49/47; 631/114/1305; 631/114/1314; 631/1647/296; 631/45/320; 82/16; 82/58; Algorithms; Annotations; BASIC BIOLOGICAL SCIENCES; Biological activity; Chemical reactions; Chromatography; Chromatography, Liquid - methods; Construction standards; Gas chromatography; Humanities and Social Sciences; Ion Mobility Spectrometry; Ionic mobility; Ions; Learning algorithms; Libraries; Liquid chromatography; Machine learning; Mass spectrometry; Mass Spectrometry - methods; Mass spectroscopy; Metabolites; Metabolomics; Metabolomics - methods; Microorganisms; Mobility; multidisciplinary; Pseudomonas putida; Science; Science (multidisciplinary); Scientific imaging; Sensitivity analysis; Workflow
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-37031-9

Multidimensional measurements using state-of-the-art separations and mass spectrometry provide advantages in untargeted metabolomics analyses for studying biological and environmental bio-chemical processes. However, the lack of rapid analytical methods and robust algorithms for these heterogeneous data has limited its application. Here, we develop and evaluate a sensitive and high-throughput analytical and computational workflow to enable accurate metabolite profiling. Our workflow combines liquid chromatography, ion mobility spectrometry and data-independent acquisition mass spectrometry with PeakDecoder, a machine learning-based algorithm that learns to distinguish true co-elution and co-mobility from raw data and calculates metabolite identification error rates. We apply PeakDecoder for metabolite profiling of various engineered strains of Aspergillus pseudoterreus, Aspergillus niger, Pseudomonas putida and Rhodosporidium toruloides . Results, validated manually and against selected reaction monitoring and gas-chromatography platforms, show that 2683 features could be confidently annotated and quantified across 116 microbial sample runs using a library built from 64 standards. Alternative algorithms exploiting advantages of multidimensional mass spectrometry in untargeted metabolomics are needed. Here, the authors develop and demonstrate PeakDecoder for confident and accurate metabolite profiling in 116 microbial sample runs and using a library built from 64 standards.