Melpomeni Kasapi

This study profiles the duodenal microbiome after meals with different structures, showing how food structure affects bacterial composition and links to metabolites and gut hormones.

The paper introduces a directional feature importance metric for decision tree classifiers and evaluates its performance on cancer proteomics data using multiple algorithms.

LAVASET improves feature importance estimation in correlated datasets by incorporating correlation factors, achieving non-inferior prediction accuracy compared to Random Forests.