Artificial intelligence–powered biofoundries for protein engineering and metabolic engineering
Junyu Chen, Nilmani Singh, Jingxia Lu, Stephan Lane, Huimin Zhao
Why it has this license class
AChecked 30 Sept 2026. Non-commercial or no-derivatives license: full text kept internally; only metadata and abstract are indexed and used.
| Source | License | Open-access status | Read as |
|---|---|---|---|
| openalex | cc-by-nc-nd | hybrid | Yellow |
| crossref | http://creativecommons.org/licenses/by-nc-nd/4.0/ | — | Yellow |
| unpaywall | cc-by-nc-nd | hybrid | Yellow |
Abstract
BSynthetic biology is rapidly evolving through the integration of artificial intelligence (AI) and automated biofoundries. This convergence accelerates the design–build–test–learn cycle, shifting protein engineering and metabolic engineering from labor-intensive manual experimentation to autonomous experimentation. This review summarizes recent advances in workflow development, AI models, and their integration with biofoundries for automated or autonomous protein engineering and metabolic engineering. Particularly, we highlight the potential of AI-powered biofoundries for accelerated scientific discovery and innovation in synthetic biology. • AI-driven biofoundries accelerate the design–build–test–learn cycle. • Language models, generative AI, and active learning drive protein engineering. • AI-guided metabolic engineering optimizes complex pathways and strains. • Emerging foundational biological models enable multiscale design from DNA to cells. • Cloud biofoundries and multi-AI agents advance self-driving labs via collaboration.
Claims built on this paper
DNone yet.