Back

Longitudinal Urine Metabolic Profiling and Gestational Age Prediction in Pregnancy

Chen, S.; Shen, X.; Liang, L.; Avina, M.; Zackriah, H.; Jelliffe-Pawlowski, L.; Rand, L.; Snyder, M.

2022-07-10 systems biology
10.1101/2022.07.10.499478 bioRxiv
Show abstract

Pregnancy is a critical time that has long-term impacts on both maternal and fetal health. During pregnancy, the maternal metabolome undergoes dramatic systemic changes, although correlating longitudinal changes in maternal urine remain largely unexplored. We applied an LCMS-based untargeted metabolomics profiling approach to analyze 346 longitudinal maternal urine samples collected throughout pregnancy for 36 women from diverse ethnic backgrounds with differing clinical characteristics. We detected 20,314 metabolic peaks and annotated 875 metabolites. Altered metabolites include a broad panel of glucocorticoids, lipids, and amino acid derivatives, which revealed systematic pathway alterations during pregnancy. We also developed a machine-learning model to precisely predict gestational age (GA) at time of sampling using urine metabolites that provides a non-invasive method for pregnancy dating. This longitudinal maternal urine study demonstrates the clinical utility of using untargeted metabolomics in obstetric settings. One Sentence SummaryMachine-learning based gestational age and due date using longitudinal urine samples of pregnancy.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.