Next Article in Journal
Evidence That Parietal Lobe Fatty Acids May Be More Profoundly Affected in Moderate Alzheimer’s Disease (AD) Pathology Than in Severe AD Pathology
Previous Article in Journal
Current Applications of Metabolomics in Cirrhosis
Article

Partial Least Squares Discriminant Analysis and Bayesian Networks for Metabolomic Prediction of Childhood Asthma

1
Channing Division of Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA
2
Harvard Medical School, Boston, MA 02115, USA
3
Division of Rheumatology, Immunology and Allergy, Brigham and Women’s Hospital, Boston, MA 02115, USA
4
Department of Pediatrics, Massachusetts General Hospital for Children, Boston, MA 02114, USA
5
Division of Pediatric Pulmonary Medicine, Department of Pediatrics, University of Rochester Medical Center, Rochester, NY 14642, USA
*
Author to whom correspondence should be addressed.
These authors contribute equally.
Metabolites 2018, 8(4), 68; https://doi.org/10.3390/metabo8040068
Received: 4 September 2018 / Revised: 18 October 2018 / Accepted: 18 October 2018 / Published: 23 October 2018
To explore novel methods for the analysis of metabolomics data, we compared the ability of Partial Least Squares Discriminant Analysis (PLS-DA) and Bayesian networks (BN) to build predictive plasma metabolite models of age three asthma status in 411 three year olds (n = 59 cases and 352 controls) from the Vitamin D Antenatal Asthma Reduction Trial (VDAART) study. The standard PLS-DA approach had impressive accuracy for the prediction of age three asthma with an Area Under the Curve Convex Hull (AUCCH) of 81%. However, a permutation test indicated the possibility of overfitting. In contrast, a predictive Bayesian network including 42 metabolites had a significantly higher AUCCH of 92.1% (p for difference < 0.001), with no evidence that this accuracy was due to overfitting. Both models provided biologically informative insights into asthma; in particular, a role for dysregulated arginine metabolism and several exogenous metabolites that deserve further investigation as potential causative agents. As the BN model outperformed the PLS-DA model in both accuracy and decreased risk of overfitting, it may therefore represent a viable alternative to typical analytical approaches for the investigation of metabolomics data. View Full-Text
Keywords: Partial Least-Squares Discriminant analysis; Bayesian networks; asthma; arginine metabolism; overfitting Partial Least-Squares Discriminant analysis; Bayesian networks; asthma; arginine metabolism; overfitting
Show Figures

Figure 1

MDPI and ACS Style

Kelly, R.S.; McGeachie, M.J.; Lee-Sarwar, K.A.; Kachroo, P.; Chu, S.H.; Virkud, Y.V.; Huang, M.; Litonjua, A.A.; Weiss, S.T.; Lasky-Su, J. Partial Least Squares Discriminant Analysis and Bayesian Networks for Metabolomic Prediction of Childhood Asthma. Metabolites 2018, 8, 68. https://doi.org/10.3390/metabo8040068

AMA Style

Kelly RS, McGeachie MJ, Lee-Sarwar KA, Kachroo P, Chu SH, Virkud YV, Huang M, Litonjua AA, Weiss ST, Lasky-Su J. Partial Least Squares Discriminant Analysis and Bayesian Networks for Metabolomic Prediction of Childhood Asthma. Metabolites. 2018; 8(4):68. https://doi.org/10.3390/metabo8040068

Chicago/Turabian Style

Kelly, Rachel S., Michael J. McGeachie, Kathleen A. Lee-Sarwar, Priyadarshini Kachroo, Su H. Chu, Yamini V. Virkud, Mengna Huang, Augusto A. Litonjua, Scott T. Weiss, and Jessica Lasky-Su. 2018. "Partial Least Squares Discriminant Analysis and Bayesian Networks for Metabolomic Prediction of Childhood Asthma" Metabolites 8, no. 4: 68. https://doi.org/10.3390/metabo8040068

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop