Housekeeping Gene Expression Normalization in Transcriptomics Mitigates Data Leakage in Machine Learning Models
Guilherme Taborda Ribas, Cristian V. Riella, Dieval Guizelini, Mauricio Menegatti Rigo, Leonardo V. Riella, Thiago J. Borges
The paper identifies stable housekeeping genes to improve machine learning model performance by reducing data leakage in transcriptomic data from kidney transplant recipients.
bioRxiv · Apr 24, 2026 · PreprintBioinformatics