Deep learning-driven integrated pipeline for de novo design and synthesis of antimicrobial peptides
Jiahui Liu, Yun Chen, Jian Tang, Xupu Xing, Jin-Shun Lin, Juping Sun, Xin-Hui Xing, Juan Li, Can Yang Zhang · 2026
Read Deep learning-driven integrated pipeline for de novo design and synthesis of antimicrobial peptides by Jiahui Liu, Yun Chen, Jian Tang, Xupu Xing, Jin-Shun Lin, Juping Sun, Xin-Hui Xing, Juan Li, Can Yang Zhang (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-13267055.txt.
Description
Jiahui Liu and co-authors build an end-to-end pipeline that designs brand-new antimicrobial peptides with deep learning, then makes and tests them. Such peptides could stand in for antibiotics, but screening finds them slowly, and computer designs often trade strength for sameness. Their pipeline runs in three stages: generate, evaluate, validate.
A tuned language model drafts candidate peptides with fresh structures. An ensemble model then votes on which candidates look strongest, and lab tests check the top picks against bacteria. Of nine candidates tested, four showed real antimicrobial activity. The loop shows machine design can deliver working molecules, not just plausible ones.
Catalog record
| CREATOR | Jiahui Liu, Yun Chen, Jian Tang, Xupu Xing, Jin-Shun Lin, Juping Sun, Xin-Hui Xing, Juan Li, Can Yang Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |