ROOFS: RObust biOmarker Feature Selection

Feature selection (FS) is essential for biomarker discovery and clinical predictive modeling. Over the past decades, the methodological literature on FS has become rich and mature, offering a wide spectrum of algorithmic approaches. However, much of this methodological progress has not been fully adopted in applied biomedical research. To bridge this gap, we propose ROOFS (RObust biOmarker Feature Selection), a Python package designed to help researchers in the choice of the FS method most adapted to their problem. Currently supporting classification tasks, ROOFS benchmarks multiple FS methods on the user’s data and generates reports summarizing a comprehensive set of evaluation metrics, including downstream predictive performance estimated using optimism correction, stability, robustness of individual features, and true positive and false positive rates assessed on semi-synthetic data with a simulated outcome. We demonstrate the utility of ROOFS on data from the PIONeeR biomarker study, aimed at identifying predictors of resistance to anti-PD-(L)1 immunotherapy in lung cancer. Comprehensive benchmarking with ROOFS has the potential to improve the reproducibility of FS discoveries and increase the translational value of clinical models. ROOFS is available at https://gitlab.inria.fr/compo/roofs .