Leveraging large language models for metabolic engineering design
Journal article, 2026
Establishing efficient cell factories involves a continuous process of trial and error due to metabolic complexity. This complexity makes predicting effective engineering targets a challenging task. Therefore, successful previous designs are vital for future cell factory development. In this study, we developed a method using large language models to extract metabolic engineering strategies from research articles. We created a database containing over 29 006 metabolic engineering entries, 1210 products, and 751 organisms. Using this database, we trained a deep learning model to predict engineering targets for cell factories. Our model outperformed traditional algorithms, demonstrated strong generalization to unseen products and multigene combinations, and was experimentally validated with geraniol overproduction in yeast, leading to the identification of several novel targets. Our study provides a valuable dataset, a chatbot, and an engineering target prediction model for the metabolic engineering field and exemplifies an efficient method for leveraging existing knowledge for future predictions.
cell factory
deep learning
database
metabolic engineering
Author
Xiongwen Li
Tsinghua University
Zhetao Guo
Tsinghua University
Yi Li
Sun Yat-Sen University
Zhu Liang
Wuhan University
Ziyi Liu
Tsinghua University
Ke Wu
Tsinghua University
Jiahao Luo
Tsinghua University
Yuesheng Zhang
Novo Nordisk Foundation
Lizheng Liu
Tsinghua University
Manda Sun
Tsinghua University
Yuanyuan Huang
Shenzhen Institute of Advanced Technology
Yu Chen
Shenzhen Institute of Advanced Technology
Tao Yu
Shenzhen Institute of Advanced Technology
Jens B Nielsen
BioInnovation Institute
Chalmers, Life Sciences, Systems and Synthetic Biology
H. T. Tang
Sun Yat-Sen University
Feiran Li
Tsinghua University
Trends in Biotechnology
0167-7799 (ISSN) 18793096 (eISSN)
Vol. 44 10 3104-3125Subject Categories (SSIF 2025)
Bioinformatics (Computational Biology)
Bioinformatics and Computational Biology
Artificial Intelligence
DOI
10.1016/j.tibtech.2026.03.026
PubMed
42031622