Deep learning reveals antimicrobial peptides within prions.
Deep learning just cracked open a new source of antimicrobial peptides—inside prions. Researchers at the University of Pennsylvania ran 19.3 million fragments from almost 3,000 prion-related proteins through advanced AI models. The result: 1,179 new candidates, now dubbed “prionins.” Forget what you thought about prions as just troublemakers in neurodegeneration. These sequences may have a positive role in host defense.
Nat Microbiol
by Torres MDT, Wan F, de la Fuente-Nunez C
“Deep learning reveals antimicrobial peptides within prions. Torres MDT(#)(1)(2)(3)(4), Wan F(#)(1)(2)(3)(4), de la Fuente-Nunez C(5)(6)(7)(8). Author information: (1)Machine Biology Group, Departments of Psychiatry and Microbiology, Institute for Biomedical Informatics, Institute for Translational Medicine and Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA. (2)Departments of Bioengineering and Chemical and Biomolecular Engineering, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA. (3)Department of Chemistry, School of Arts and Sciences, University of Pennsylvania, Philadelphia, PA, USA. (4)Penn Institute for Computational Science, University of Pennsylvania, Philadelphia, PA, USA. (5)Machine Biology Group, Departments of Psychiatry and Microbiology, Institute for Biomedical Informatics, Institute for Translational Medicine and Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA. cfuente@upenn.edu. (6)Departments of Bioengineering and Chemical and Biomolecular Engineering, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA. cfuente@upenn.edu. (7)Department of Chemistry, School of Arts and Sciences, University of Pennsylvania, Philadelphia, PA, USA. cfuente@upenn.edu. (8)Penn Institute for Computational Science, University of Pennsylvania, Philadelphia, PA, USA. cfuente@upenn.edu. (#)Contributed equally Prion and prion-like proteins are classically associated with protein misfolding, but amyloidogenic sequences can also participate in host defence. Here, using deep learning, we screened 19.3 million fragments from 2,897 curated prion-related proteins and identified 1,179 candidate antimicrobial peptides, which we term prionins. Among 75 synthesized prionins, 59 inhibited bacterial pathogens, 53 perturbed membranes and 2 reduced Acinetobacter baumannii infection burden in mice. © 2026. The Author(s). Conflict of interest statement: Competing interests: C.d.l.F.-N. is a co-founder of and scientific advisor to Peptaris, Inc.; provides consulting services to Invaio Sciences; and serves on the Scientific Advisory Boards of Intera Bio, Nowture S.L., Peptidus, European Biotech Venture Builder, the Peptide Drug Hunting Consortium (PDHC), ePhective Therapeutics, Inc., and Phare Bio. M.D.T.T. is a co-founder and scientific advisor to Peptaris, Inc. The other author declares no competing interests.”
Here’s why this matters. Prion and prion-like proteins have always been linked to protein misfolding diseases. But the team’s machine learning approach highlights a hidden reservoir of antimicrobial activity. Of 75 prionins synthesized, 59 knocked out bacterial pathogens in lab tests. Fifty-three of those also disrupted bacterial membranes. That’s serious hit rate territory for a first pass. Two prionins even reduced infection burden in a mouse model of Acinetobacter baumannii, a notoriously tough bug.
Key takeaway: AI-driven discovery is turbocharging peptide research. The days of slow, trial-and-error peptide prospecting are fading fast.
Prionins expand the definition of antimicrobial peptides
Prion-related proteins are now a legitimate source for new research compounds
Machine learning is finding bioactivity where no one thought to look
For researchers, this opens up a new class of peptides to explore. The full list of prionins—and the approach behind their discovery—could spark a wave of follow-up studies. If you want the big picture on what’s happening with peptide discovery, check out the peptide research index.
AI is pulling peptides out of the shadows. The research community is just getting started.
Related Reading
The STRIDE Trial and Semaglutide: Implications for Clinical Vascular Practice.
News · J Med ChemStructure-Based Adaptation of a SARS-CoV-2 Neutralizing Peptide to New Virus Variants.
News · J Nucl MedCombining an α(v)β(6)-Targeted (177)Lu-Based Peptide Receptor Radionuclide Therapy with Olaparib to Boost Therapeutic Efficacy in Pancreatic Cancer.
For Research Use Only
All content published on Pushing Peptides is intended for educational and informational purposes only. The information provided is not intended as medical advice, diagnosis, or treatment. Peptides discussed in this article are research compounds and are not approved for human therapeutic use by the FDA or any other regulatory agency. All studies referenced involve animal models or in vitro research unless otherwise stated. Consult a qualified healthcare professional before making any decisions related to your health. Pushing Peptides does not sell peptides — we are a vendor directory and educational resource.