Partial least squares discriminant analysis and bayesian networks for metabolomic prediction of childhood asthma

TY - JOUR

T1 - Partial least squares discriminant analysis and bayesian networks for metabolomic prediction of childhood asthma

AU - Kelly, Rachel S.

AU - McGeachie, Michael J.

AU - Lee-Sarwar, Kathleen A.

AU - Kachroo, Priyadarshini

AU - Chu, Su H.

AU - Virkud, Yamini V.

AU - Huang, Mengna

AU - Litonjua, Augusto A.

AU - Weiss, Scott T.

AU - Lasky-Su, Jessica

N1 - Publisher Copyright: © 2018 by the authors. Licensee MDPI, Basel, Switzerland.

PY - 2018/12

Y1 - 2018/12

N2 - 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.

AB - 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.

KW - Arginine metabolism

KW - Asthma

KW - Bayesian networks

KW - Overfitting

KW - Partial least-squares discriminant analysis

UR - https://www.scopus.com/pages/publications/85056078278

UR - https://www.scopus.com/pages/publications/85056078278#tab=citedBy

U2 - 10.3390/metabo8040068

DO - 10.3390/metabo8040068

M3 - Article

SN - 2218-1989

VL - 8

JO - Metabolites

JF - Metabolites

IS - 4

M1 - 68

ER -