AI discovers antimicrobial peptides encoded in ancient human mitochondrial genomes
NikoMcCarty · x · 2026-08-22
Researchers at UPenn used AI to mine over 2,000 ancient human mitochondrial genomes, identifying hidden peptide sequences with antibacterial potential named 'Mitochondrins'.
- Hypothesis: As descendants of bacteria, mitochondrial genomes may retain fragments capable of engaging bacterial physiology.
- Findings: AI identified several peptides active against clinically relevant bacteria, including drug-resistant strains, with distinct mechanisms of action.
- Validation: A representative peptide reduced A. baumannii burden in a mouse infection model.
- Implication: Several active sequences are perfectly conserved in modern human mitochondrial DNA, suggesting a role in host defense.
More from Research
- Sim data can't cover the humanoid long tail: the sim2real debate, mapped — herbiebradley · 2026-10-16
- SJTU AutoLab releases Drive3R, a streaming geometric foundation model for long-horizon driving 3D reconstruction — AutoLab-SJTU · 2026-10-16
- Cortex A/B-tests coding-agent skills and rules by replaying developer corrections before keeping them — Samuele Giampieri · 2026-10-16
- Zero-latency lab-in-the-loop tests whether drug-discovery agents cheat via memorization — niloofar_mire · 2026-10-16
- 260M-parameter looped diffusion transformer beats 6x larger baselines with 5x less compute — burkov · 2026-10-16
- Stanford's Next-Concept Modeling sketches text first, 21x faster generation on one H100 — lmoroney · 2026-10-16