Advancing Peptide Toxicity Prediction with tAMPer

We are pleased to announce the publication of tAMPer, a new deep learning model for predicting peptide toxicity. Published under “Structure-aware deep learning model for peptide toxicity prediction,” in the journal Protein Science, tAMPer integrates amino acid sequence composition with ColabFold-predicted peptide structures using graph and recurrent neural networks. tAMPer aims to expedite AMP discovery by reducing reliance on costly toxicity screening experiments and is set to catalyze antimicrobial research and accelerate the discovery and development of new peptide/protein-based biologics in our global fight against multi-drug resistant pathogens. Explore the full potential of tAMPer and its impact on antimicrobial research by visiting our tAMPer GitHub software project page and reading the tAMPer manuscript!