AI-designed peptide guides enable mammalian protein screens
AllThingsApx · x · 2026-08-27
Researchers from the University of Pennsylvania and others have developed a mammalian high-throughput screening method using AI-designed peptide guides. Analogous to how CRISPR made gene editing programmable, this approach uses language models to design peptide guides to screen protein "knockdowns" across disease targets. This technique provides a new tool for therapeutic protein degradation.
More from Research
- GLM-5.3-Flash Released: 1M Context & Open Weights — qinzytech · 2026-08-27
- Research predicts optimal model size and data allocation for pre-training — yoavgo · 2026-08-27
- Experts debate if RMSNorm helps interpret neural network black boxes — CFGeek · 2026-08-27
- ARC-AGI-3 learnings: Key designs for self-learning AI agents — GregKamradt · 2026-08-27
- Recommended Reads: Poggio on Minds & Machines, Welling on GenAI Thermodynamics — neurovium · 2026-08-27
- Category Theory Master: AI Expands Mathematical Truth but Doesn't Change Core — begusgasper · 2026-08-27