Mining UniProtKB/Swiss-Prot for Antimicrobial Peptides with AMPlify

We are excited to share our latest publication in Protein Science, featuring AMPlify, a machine learning-based tool developed at Birol Lab to identify antimicrobial peptides (AMPs).

Antimicrobial resistance is a growing global threat, and AMPs offer a promising alternative to conventional antibiotics, yet their discovery remains a challenge. In Li et al. (2025), we leveraged AMPlify to mine the UniProtKB/Swiss-Prot database, identifying 8008 novel putative AMPs. Of these, 13 showed antimicrobial activity against Escherichia coli and/or Staphylococcus aureus. This study highlights the power of deep learning in accelerating AMP discovery for real-world applications. By integrating sequence features and deep learning, AMPlify enables scalable and accurate AMP discovery, paving the way for novel antimicrobial therapeutics.

Read the full publication

Explore AMPlify on GitHub