Antoine Passemiers

The paper identifies how batch correction methods can distort gene-gene correlations and introduces a metric to quantify this issue.

geneRNIB provides a benchmark for gene regulatory network inference, showing simpler models often outperform complex ones in perturbation-informed metrics.

This paper identifies critical methodological flaws in the CellOracle approach for gene regulatory network inference and perturbation analysis.

MetDecode uses methylation patterns to estimate tumor proportion and identify tissue origin in cell-free DNA samples from cancer patients.

This paper introduces an optimal transport-based domain adaptation method to correct technical biases in cfDNA sequencing data, improving cancer detection and enabling cohort integration.