Jacques Corbeil

QMAP evaluates antimicrobial peptide MIC and hemolytic activity prediction models using standardized, homology-constrained benchmarks, revealing limited progress and poor performance in high-potency predictions.

This study identifies pathogenic autoantibodies in EAE and demonstrates a therapeutic approach using a synthetic antibody to block their activity.

The paper introduces MOT, a deep learning model that classifies tumour types using multi-omics data, achieving high accuracy even with missing data.

The paper introduces kAAmer, a protein database engine that enables fast protein identification with complementary annotations through amino-acid k-mers.

This work proposes algorithms to correct variations between mass spectra, improving comparability across large datasets and enabling machine learning applications.

The paper develops interpretable genotype-to-phenotype classifiers with performance guarantees, validated on antimicrobial resistance prediction across 12 species and 56 antibiotics.

The paper performs a genome-wide screen in Candida albicans to identify genes critical for cell size homeostasis, finding both conserved regulators and novel genes, some of which are linked to pathogenicity.

This paper introduces a reference-free method for genomic biomarker discovery using k-mer representations and machine learning, validated on antibiotic resistance prediction in bacteria.