Recent advances in high-resolution mass spectrometry have benefited many fields with an abundance of data, which include exposomics and metabolomics. However, a major bottleneck exists in the processing and review of experimental data. Samples under investigation in non-targeted analysis experiments may have upwards of thousands of compounds, some of which are not present in any available mass spectrometry library and require characterization. With a lack of automated high-throughput screening methods available, tradeoffs must be made in regard to which samples can be investigated using a non-targeted based workflow, resulting in varying degrees of uncertainty.  Furthermore, while sample analysis via non-targeted analysis methods typically employs gas- and liquid-chromatography based methods, the majority of studies have been performed using the latter. To address this gap in available high-throughput screening technologies for gas-chromatography-based non-targeted analysis methods, we present a supervised learning-based method for high-throughput screening of two dimensional gas chromatography mass spectrometry data for non-targeted analysis workflows. The supervised learning method was employed on high-quality, well curated data, and couples spectra data with metadata to assess spectra quality in order to provide decision support to analysts. Using this high-throughput screening method, analysts are able to spend less time on mundane spectral quality review. This increase in freedom provides more time to focus on the important task at hand: the characterization of unknowns and the assessment of suspect screening matches in a given sample, many of which may pose a hazard exposure risk.  Furthermore, this tool has the potential to be adapted to other workflows, including liquid-chromatography.

Improvements in gas chromatography mass spectrometry-based non-targeted analysis workflows through integration of supervised learning techniques for signal quality assessment

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.