Closed-Loop Multi-Objective Optimization for Receptor-Selective Cell-Penetrating Peptide Design
Iori Yamahata, Hidetomo Yokoo, Yosuke Demizu, Teppei Shimamura, Shuto Hayashi · 2026
Read Closed-Loop Multi-Objective Optimization for Receptor-Selective Cell-Penetrating Peptide Design by Iori Yamahata, Hidetomo Yokoo, Yosuke Demizu, Teppei Shimamura, Shuto Hayashi (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-13625959.txt.
Description
Iori Yamahata and co-authors built a computer loop that designs cell-entering peptides choosy about which receptor they touch, in a study published in 2026. Such peptides ferry cargo into cells, but tuning them to favor one surface receptor over another is hard. Their loop starts by generating peptide candidates with a model trained on known examples. Each one is scored by docking and physics simulations against each receptor.
An optimizer then balances the competing scores and proposes the next round of candidates. Aimed at favoring the CXCR4 receptor over NRP1, the loop found peptides with the wanted profile. Of ten candidates tested in cells, four gathered more strongly where CXCR4 sits than where NRP1 sits. The authors present the loop as a practical design route for such peptides. Lab proof, they note, still decides which candidates truly work.
Catalog record
| CREATOR | Iori Yamahata, Hidetomo Yokoo, Yosuke Demizu, Teppei Shimamura, Shuto Hayashi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |