Maternal plasma lipids are involved in the pathogenesis of preterm birth

Abstract

Background: Preterm birth is defined by the onset of labor at a gestational age shorter than 37 weeks, and it can lead to premature birth and impose a threat to newborns' health. The Puerto Rico PROTECT cohort is a well-characterized prospective birth cohort that was designed to investigate environmental and social contributors to preterm birth in Puerto Rico, where preterm birth rates have been elevated in recent decades. To elucidate possible relationships between metabolites and preterm birth in this cohort, we conducted a nested case-control study to conduct untargeted metabolomic characterization of maternal plasma of 31 women who experienced preterm birth and 69 controls who underwent full-term labor at 24-28 gestational weeks.

Results: A total of 333 metabolites were identified and annotated with liquid chromatography/mass spectrometry. Subsequent weighted gene correlation network analysis shows that the fatty acid and carene-enriched module has a significant positive association (P = 8e-04, FDR = 0.006) with preterm birth. After controlling for potential clinical confounders, a total of 38 metabolites demonstrated significant changes uniquely associated with preterm birth, where 17 of them were preterm biomarkers. Among 7 machine-learning classifiers, the application of random forest achieved a highly accurate and specific prediction (AUC = 0.92) for preterm birth in testing data, demonstrating their strong potential as biomarkers for preterm births. The 17 preterm biomarkers are involved in cell signaling, lipid metabolism, and lipid peroxidation functions. Additional modeling using only the 19 spontaneous preterm births (sPTB) and controls identifies 16 sPTB markers, with an AUC of 0.89 in testing data. Half of the sPTB overlap with those markers for preterm births. Further causality analysis infers that suberic acid upregulates several fatty acids to promote preterm birth.

Conclusions: Altogether, this study demonstrates the involvement of lipids, particularly fatty acids, in the pathogenesis of preterm birth.

Keywords: biomarkers; fatty acid; lipid; metabolic pathway; metabolomics; network; preterm.

Figure 1:

(A) Correlation matrix of the 10 phenotypic variables on the 100 samples (69 controls vs 31 preterm cases). (B) Partial least squares–discriminant analysis (PLS-DA) plot of the 100 samples using 333 metabolites. (C) Source of variation (SOV) analysis using 100 samples; 333 metabolites are used in the ANOVA model. (D) Heat map of correlations between 333 metabolites and 11 confounding factors. The rows represent the clinical factors, and the columns represent metabolites (point-biserial correlation for continuous and binary covariates; Pearson correlation for continuous covariates; Spearman correlation for continuous and ordinal covariates).

Figure 2:

WGCNA network in all samples. (A) WGCNA network modules of metabolomics data from both preterm and control samples. Each node represents a lipid. Node color represents a module. (B) Module-trait associations.

Figure 3:

Metabolites show significantly different levels in preterm and control samples. (A) Heat map of the 38 metabolites with a significant difference exclusively between preterm and control samples (P < 0.05). (B) Bar plots on the averaged normalized intensities in cases vs controls. (C) Bipartite graph of the significantly differentiated metabolites and the significantly altered metabolic pathways with which they are associated. Five pathways with a significant difference between preterm and control samples (P < 0.05) and 33 significantly differentiated metabolites engaged in these pathways are shown. Elliptical nodes: metabolites. Rectangular nodes: pathways from HMDB, PubChem, and KEGG databases. Node color: red, upregulated; blue, down-regulated. Node size: the absolute value of log fold change (logFC).

Figure 4:

Classification model for preterm birth. (A) Comparison of 7 classification models using 17 metabolites on the hold-out testing. The dataset was randomly split into training data (80%) and testing data (20%) 10 times. The mean value (bars) and standard error (error bars) of the 10 repeats are shown for 3 performance metrics of the area under the receiver operating curve (AUC), F1 statistic, and balanced accuracy. The winning method RF in training data (left) was then applied to the testing data (right). (B) The heat map of correlation coefficients between the 17 metabolites and clinical variables. (C) The precision-recall curves of the RF model from (A) on classifying preterm, LGA (large for gestational age), income, and maternal age (≥35 y or not), respectively, using the same set of testing data as in (A). (D) Normalized variable importance scores for the 17 lipid markers in the RF model. The normalization is done on R by making the sum of importance scores be 100.

Figure 5:

Predicted significant (P < 0.01) causality interactions between the 17 metabolites and preterm birth. Arrow indicates the causality interaction. Blue and red nodes are down- and upregulated metabolites, while the center one is preterm.

Figure 6:

A proposed model of metabolite changes affecting preterm birth.