Longitudinal metabolomics of human plasma reveals prognostic markers of COVID-19 disease severity

  1. Miriam Sindelar
  2. Ethan Stancliffe
  3. Michaela Schwaiger-Haber
  4. Dhanalakshmi S. Anbukumar
  5. Kayla Adkins-Travis
  6. Charles W. Goss
  7. Jane A. O’Halloran
  8. Philip A. Mudd
  9. Wen-Chun Liu
  10. Randy A. Albrecht
  11. Adolfo García-Sastre
  12. Leah P. Shriver
  13. Gary J. Patti

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

No abstract available

Article activity feed

  1. Version published to 10.1016/j.xcrm.2021.100369
  2. ScreenIT

    SciScore for 10.1101/2021.02.05.21251173: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    Data preprocessing and normalization: Polar metabolite identifications were supported by matching the retention time, accurate mass, and MS/MS fragmentation data to our in-house retention time and MS/MS library created from authentic reference standards (Mass Spectrometry Metabolite Library supplied by IROA Technologies, Millipore Sigma, St. Louis, MO, USA) and online MS/MS libraries (Human Metabolome Database (HMDB, https://hmdb.ca, (Wishart et al., 2018)), Mass Bank of North America (MoNA, https://mona.fiehnlab.ucdavis.edu/, (Horai et al., 2010)), and mzCloud (https://mzcloud.org).
    https://mona.fiehnlab.ucdavis.edu/
    suggested: (MassBank of North America, RRID:SCR_015536)
    mzCloud
    suggested: (mzCloud, RRID:SCR_014669)
    Lipid iterative MS/MS data were annotated with the Agilent Lipid Annotator software.
    Agilent Lipid Annotator
    suggested: None
    ComBat correction outperformed the other batch correction approaches tested using this metric.
    ComBat
    suggested: (ComBat, RRID:SCR_010974)
    All ML analyses were carried out using Python (v3.7) with extensive use of the packages SciPy (v1.4.1) (Virtanen et al., 2020a) and Scikit-learn (v0.23.1) (Pedregosa et al., 2011).
    Python
    suggested: (IPython, RRID:SCR_001658)
    SciPy
    suggested: (SciPy, RRID:SCR_008058)
    Scikit-learn
    suggested: (scikit-learn, RRID:SCR_002577)

    Results from OddPub: Thank you for sharing your code and data.

    Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:
    A limitation of the ElasticNet approach is that it is a linear model and most biological systems are innately non-linear. Other studies have used non-linear ML models such as RF to predict disease severity from metabolomics, lipidomics, and/or proteomics profiles (Fraser et al., 2020; Shen et al., 2020). Although these studies found higher AUC scores than that of our model, they used considerably smaller patient cohorts than what our model was trained and evaluated on. When we tested non-linear models (RF and SVM), we found worse cross-validated performance than ElasticNet (see Figure S3a). Another challenge we faced in building a model of disease severity is that the size of our study required normalizing metabolic profiles acquired in multiple batches. We demonstrated that ComBat normalization was able to remove the variance resulting from these batch effects. In removing this variance, however, true biological variation was undoubtedly removed. Despite these limitations, our model still accurately predicted patient disease severity. Interpretation of our model led us to identify 25 robust predictor metabolites whose identities were rigorously confirmed. Using this reduced predictor set, we were able to retrain our model and found similarly strong predictive ability. Our large sample size that included longitudinal measurements of patient plasma and collection of patient metadata (laboratory values, comorbidities, and demographics) allowed us to uniquely validate the relati...

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  3. Version published to 10.1101/2021.02.05.21251173 on medRxiv