XLSTM-AmPEP60: An xLSTM Model for the Minimum Inhibitory Concentrations Prediction of Antimicrobial Peptides

Antimicrobial peptides (AMPs) represent a promising alternative to combat escalating bacterial drug resistance. While pretrained protein language models (PLMs) have demonstrated success in identifying AMPs from sequence data, overfitting remains a major challenge. This issue is mainly caused by the high complexity of PLMs and limited availability of data. To address this, we proposed xLSTM-AmPEP60, a deep learning method based on an extended Long Short-Term Memory (xLSTM) architecture. This model used lightweight parameters to derive embedding features from peptide sequences, enabling the quantitative prediction of minimum inhibitory concentrations (MICs) of the common bacterial species Escherichia coli (E. coli). In five independent experiments, with 10% leave-out sequences as test sets, xLSTM-AmPEP60 outperformed state-of-the-art regression methods, achieving a mean squared error of 0.2349 (log μ M). These results demonstrate that lightweight xLSTM architectures can accurately assess AMP activity against E. coli.