Smart molecular design of NIR‐II organic fluorophores through self‐driven iterative evolution, deep learning, and fragment‐based assembly
Yu Zhang, Zhubin Hu, Xinyuan Wang, Zhenrong Sun, Yongye Liang, Cheng Zhong, Haitao Sun · 2026
Read Smart molecular design of NIR‐II organic fluorophores through self‐driven iterative evolution, deep learning, and fragment‐based assembly by Yu Zhang, Zhubin Hu, Xinyuan Wang, Zhenrong Sun, Yongye Liang, Cheng Zhong, Haitao Sun (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/PMC13398758.txt.
Description
Yu Zhang and colleagues let an AI evolve dye molecules that glow in the second near-infrared window. Their 2026 study builds the AI4NIR-II pipeline, joining quantum chemistry calculations, transformer prediction models and generative design. Such dyes (glowing between 1,000 and 1,700 nm) pierce tissue deeply with little background haze, prized for imaging and light therapy, but finding them by hand is slow trial and error.
Starting from two fragment families, the model trained on about 16,000 molecules with computed absorption and emission values. It then proposed, scored and refined new candidates in rounds, a self-driven loop needing far less bench work. The authors present the loop as a template for smart molecule hunting generally.
Catalog record
| CREATOR | Yu Zhang, Zhubin Hu, Xinyuan Wang, Zhenrong Sun, Yongye Liang, Cheng Zhong, Haitao Sun |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33724 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |