The abstract is read at the publisher; the summary is JClub's.
CATEomics provides a standardized, reproducible workflow to select and ensemble CATE estimators for high-dimensional omics data using out-of-fold proxy losses.
- Why it matters: High-dimensional omics studies often cannot directly assess CATE estimation error from observed outcomes, leaving no consistent way to choose among competing estimators.
- What they did: The R package takes a SummarizedExperiment, applies shared preprocessing and data partitions across R and Python estimators, then compares out-of-fold CATE estimates via proxy losses for model selection and ensembling.
- The result: It outputs CATE estimates back into the original object for downstream omics analysis, enabling practical, reproducible CATE estimation workflows.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.