Machine learning-driven identification of key chemical determinants of tobacco leaf sensory irritation
Wenting Li, Xuehui Sun, Zhe Jin, Bin Peng, Jizhao Guo, Ran Wan, Song Yang, Junwei Guo, Hongbo Wang, Meijuan Fan, Feng Li, Cong Nie, Le Zhao, Chao Wang · 2026
Read Machine learning-driven identification of key chemical determinants of tobacco leaf sensory irritation by Wenting Li, Xuehui Sun, Zhe Jin, Bin Peng, Jizhao Guo, Ran Wan, Song Yang, Junwei Guo, Hongbo Wang, Meijuan Fan, Feng Li, Cong Nie, Le Zhao, Chao Wang (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/PMC13469580.txt.
Description
Li and a large team built a machine learning model in this 2026 study to predict how irritating a tobacco leaf feels when smoked, using chemistry instead of human tasters. They measured 78 chemical components in 353 leaf samples and paired each sample with sensory scores that split leaves into high-irritation and low-irritation groups.
After cleaning outliers and narrowing the data to 33 core features, their random forest model with 60 decision trees classified an independent test set with 84.38 percent accuracy, beating support vector machine and nearest-neighbor models in the same comparison. Eight chemicals mattered most, including total nitrogen, total alkaloids, and reducing sugar. Higher nitrogen compounds tracked with stronger irritation, while sugars and certain organic acids tracked with milder leaves, giving growers targets for breeding and blending.
Catalog record
| CREATOR | Wenting Li, Xuehui Sun, Zhe Jin, Bin Peng, Jizhao Guo, Ran Wan, Song Yang, Junwei Guo, Hongbo Wang, Meijuan Fan, Feng Li, Cong Nie, Le Zhao, Chao Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |