The abstract is read at the publisher; the summary is JClub's.
Hierarchical interactome representation learning linked HELLP syndrome to both late-onset and early-onset preeclampsia, while chorioamnionitis was linked only to late-onset disease.
- Why it matters: Distinct biological mechanisms for early- versus late-onset preeclampsia remain unclear, limiting subtype-specific, explainable models of pathogenesis.
- What they did: Using 19 prior gene sets, the study trained and validated explainable AI interactome models (n=177 develop; n=352 validate) with a deep-insight visible neural network, gradient-weighted class activation mapping, and a large language model.
- The result: Novel genes were highlighted for LOPE (ANKRD13A, SLA) and HELLP (PDE5A), and for EOPE (SWAP70, GREM2, GPR146, PIP5K1B, EZR), enabling subtype-specific mechanistic hypotheses.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.