Paul Dufossé

Anastasiia Bakhmach, Paul Dufossé, Andrea Vaglio et al.

Feature selection (FS) is essential for biomarker discovery and clinical predictive modeling. Over the past decades, methodological literature on FS has become rich and mature, offering a wide spectrum of algorithmic approaches. However, much of this methodological progress has not fully translated into applied biomedical research. Moreover, challenges inherent in biomedical data, such as high-dimensional feature space, low sample size, multicollinearity, and missing values, make FS non-trivial. To help bridge this gap between methodological development and practical application, we propose ROOFS (RObust biOmarker Feature Selection), a Python package available at https://gitlab.inria.fr/compo/roofs, designed to help researchers in the choice of FS method adapted to their problem. 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 clinical trial, aimed at identifying predictors of resistance to anti-PD-(L)1 immunotherapy in lung cancer. Of the 34 FS methods gathered in ROOFS, we evaluated 23 in combination with 11 classifiers (253 models) and identified a filter based on the union of Benjamini-Hochberg false discovery rate-adjusted p-values from t-test and logistic regression as the optimal approach, outperforming other methods including widely used LASSO. We conclude that comprehensive benchmarking with ROOFS has the potential to improve the reproducibility of FS discoveries and increase the translational value of clinical models.

Paul Dufossé, Sébastien Benzekry

Survival analysis is an essential tool for the study of health data. An inherent component of such data is the presence of missing values. In recent years, researchers proposed new learning algorithms for survival tasks based on neural networks. Here, we studied the predictive performance of such algorithms coupled with different methods for handling missing values on simulated data that reflect a realistic situation, i.e., when individuals belong to unobserved clusters. We investigated different patterns of missing data. The results show that, without further feature engineering, no single imputation method is better than the others in all cases. The proposed methodology can be used to compare other missing data patterns and/or survival models. The Python code is accessible via the package survivalsim. -- L'analyse de survie est un outil essentiel pour l'étude des données de santé. Une composante inhérente à ces données est la présence de valeurs manquantes. Ces dernières années, de nouveaux algorithmes d'apprentissage pour la survie, basés sur les réseaux de neurones, ont été conçus. L'objectif de ce travail est d'étudier la performance en prédiction de ces algorithmes couplés à différentes méthodes pour gérer les valeurs manquantes, sur des données simulées qui reflètent une situation rencontrée en pratique, c'est-à dire lorsque les individus peuvent être groupés selon leurs covariables. Différents schémas de données manquantes sont étudiés. Les résultats montrent que, sans l'ajout de variables supplémentaires, aucune méthode d'imputation n'est meilleure que les autres dans tous les cas. La méthodologie proposée peut être utilisée pour comparer d'autres modèles de survie. Le code en Python est accessible via le package survivalsim.

Paul Dufossé, Cyrille Enderli

In this paper we consider the problem of finding Pulse Repetition Intervals allowing the best compromises mitigating range and Doppler ambiguities in a Pulsed-Doppler radar system. We revisit a problem that was proposed to the Evolutionary Computation community as a real-world case to test Many-objective Optimization algorithms. We use it as a baseline to compare several Evolutionary Algorithms for black-box optimization with different metrics. Resulting data is aggregated to build a reference set of Pareto optimal points and is the starting point for further analysis and operational use by the radar designer.