Philippe J. Dufresne

This study uses population genomics and machine learning to identify genetic markers predictive of antifungal resistance in Candida albicans, highlighting the need for expanded resistance catalogues.

This paper trains a machine learning model to predict antifolate resistance mutations in Pneumocystis jirovecii using experimental data and computational modeling, finding mutations that confer resistance to trimethoprim-sulfamethoxazole.

This study establishes CLSI-endorsed epidemiological cutoff values (ECVs) for antifungal susceptibility in clinically relevant Sporothrix species using broth microdilution data from 19 laboratories.

The paper curates AMR mutations in fungi to create FungAMR, identifies universal resistance mutations, and provides a tool to screen genomes for AMR mutations.