Anna Gambin

BATTLE-AMP benchmarks antimicrobial peptide predictors using MIC data, showing that models trained on MIC data outperform binary classifiers and highlighting limitations in distinguishing active from inactive peptides.

The paper identifies methodological errors in epitope discovery that inflate in silico benchmarks and introduces a model trained on clean data that outperforms existing methods.

The paper introduces a linear deconvolution method using optimal transport to improve accuracy in mass spectrometry by reducing sensitivity to measurement inaccuracies.