Abstract
ABSTRACT
Background
Several omics studies have been completed in recent years, with the goal of identifying biomarkers of complex multifactorial diseases, such as bronchopulmonary dysplasia (BPD).
Objective
To evaluate the performance of 3 distinct omics platforms, using a machine learning pipeline with integration of sparse, reliable and adaptive biomarker identification (Stabl).
Methods
Using a well-characterized birth cohort, cord blood metabolomics, proteomics and adductomics data were integrated with Least Absolute Shrinkage and Selection Operator (LASSO) regression and Stabl, to evaluate predictive performance for BPD.
Results
Sparse multivariable modeling of 45,000 features measured in 217 infants (52 term, 165 extremely preterm ≤28 weeks; 82 with BPD and 35 with severe BPD/death) identified a perfect signature for preterm birth with both LASSO and Stabl (AUROC=1.0; p
Conclusions
The sparse machine learning pipeline is a complementary approach for identifying novel pathways and biomarkers of multifactorial BPD and its endotypes.
Impact Statement
Cord blood multi-omics provides a snapshot at birth of the complex interplay between the perinatal metabolome, proteome and exposome.
We leveraged novel machine learning approaches including integration of sparse, reliable and adaptive biomarker identification (Stabl) to identify novel cord blood biomarkers that elucidate perinatal pathways of BPD, mediated by preterm birth.
Biomarkers across 3 omics platforms revealed dysregulated pathways of innate/adaptive immune responses, metabolic programming and oxidative stress.
The sparse machine learning pipeline is a complementary approach for identifying novel biomarkers of multifactorial BPD and its endotypes.