Can large language models predict antimicrobial peptide activity and toxicity?

Orsi, Markus; Reymond, Jean-Louis (2024). Can large language models predict antimicrobial peptide activity and toxicity? RSC Medicinal Chemistry, 15(6), pp. 2030-2036. Royal Society of Chemistry 10.1039/d4md00159a

Preview

Text d4md00159a.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (1MB) | Preview

Antimicrobial peptides (AMPs) are naturally occurring or designed peptides up to a few tens of amino acids which may help address the antimicrobial resistance crisis. However, their clinical development is limited by toxicity to human cells, a parameter which is very difficult to control. Given the similarity between peptide sequences and words, large language models (LLMs) might be able to predict AMP activity and toxicity. To test this hypothesis, we fine-tuned LLMs using data from the Database of Antimicrobial Activity and Structure of Peptides (DBAASP). GPT-3 performed well but not reproducibly for activity prediction and hemolysis, taken as a proxy for toxicity. The later GPT-3.5 performed more poorly and was surpassed by recurrent neural networks (RNN) trained on sequence-activity data or support vector machines (SVM) trained on MAP4C molecular fingerprint-activity data. These simpler models are therefore recommended, although the rapid evolution of LLMs warrants future re-evaluation of their prediction abilities.

Interest & Impact

Downloads

12 since deposited on 26 Jun 2024
12 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item