Integrated modeling of metabolome, proteome, and immunome trajectories predicts labor onset

To predict labor onset, a longitudinal study was conducted in 63 women who went into labor spontaneously. More than 7000 plasma analytes and peripheral immune cell responses were analyzed using untargeted mass spectrometry for metabolomics, aptamer-based proteomic technology, and single-cell mass cytometry in serial blood samples collected during the last 100 days of pregnancy. A stacked generalization algorithm to the multiomic dataset was applied to build and independently validate an integrated predition model. The model with the top 45 features resulted in the prediction in Pearson R=0.85 ( training set) and 0.81 (test set), respectively. The study found the surge in steroid hormone metabolites 2 to 4 weeks before labor coincided with dynamic changes in plasma protein concentrations and immune cell responses.