Harnessing generative AI for predicting and optimizing antimicrobial peptides against drug-resistant infections
Sandra Clemens, Hannah Franziska Löchel, Nico Häußer, Felix Wannemacher, Wilhelm Bertrams, Bernd Schmeck, Dominik Heider · 2026
Read Harnessing generative AI for predicting and optimizing antimicrobial peptides against drug-resistant infections by Sandra Clemens, Hannah Franziska Löchel, Nico Häußer, Felix Wannemacher, Wilhelm Bertrams, Bernd Schmeck, Dominik Heider (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13230547.txt.
Description
Sandra Clemens and six co-authors use generative AI to design germ-killing peptides. Their 2026 study fights antimicrobial resistance, the spread of infections that shrug off standard drugs. Short protein chains called antimicrobial peptides kill broadly and rarely breed resistance. The team built both a data trove and a peptide-writing model.
The trove, COMPASS, gathers over seventy-five thousand unique peptide sequences from nine sources. The model, AmpGPT2, learned natural peptide patterns without a narrow target. Over ninety-five percent of its drafts were judged real peptides by a checker tool. Its peptides matched natural ones in length and chemistry. In lab tests, one of five drafts killed two tough hospital germs in a dose-linked way.
Catalog record
| CREATOR | Sandra Clemens, Hannah Franziska Löchel, Nico Häußer, Felix Wannemacher, Wilhelm Bertrams, Bernd Schmeck, Dominik Heider |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |