Piotr Setny

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 investigates how transmembrane domains (TMDs) of H1 and H3 hemagglutinin influence membrane fusion differently, showing TMD-lipid interactions drive fusion rather than direct FP:TMD complexing.

This paper introduces HydrAMP, a deep generative model for creating potent antimicrobial peptides, which outperforms existing methods and validates nine new peptides in lab tests.