Large language model for knowledge synthesis and AI-enhanced biomanufacturing.

Area of Science:

• Synthetic Biology
• Artificial Intelligence
• Biomanufacturing

Background:

• Large language models (LLMs) are increasingly impacting scientific research and education.
• Synthetic biology (SynBio) is a rapidly evolving field with complex data and knowledge requirements.

Purpose of the Study:

• To review the advancements and potential impacts of LLMs in synthetic biology education and biomanufacturing.
• To compare LLM capabilities in addressing fundamental SynBio questions.
• To explore the future role of LLMs in revolutionizing biomanufacturing processes.

Main Methods:

• Literature review of recent developments in LLMs and their applications in SynBio.
• Comparative analysis of US and Chinese LLMs for SynBio tasks.
• Discussion of LLM applications including information extraction, knowledge graph construction, and retrieval-augmented generation.
• Anticipation of LLM integration into the design-build-test-learn (DBTL) cycle and self-driving laboratories.

Main Results:

• LLMs show significant potential in extracting SynBio information from unstructured data.
• LLMs can facilitate knowledge graph construction and retrieval-augmented generation for SynBio.
• LLMs are poised to revolutionize metabolic modeling, engineering, and enable automated laboratories in biomanufacturing.

Conclusions:

• LLMs offer transformative potential for synthetic biology education and biomanufacturing.
• Establishing benchmarks, ensuring trustworthy knowledge synthesis, and developing biosecurity frameworks are crucial.
• Interdisciplinary collaboration between AI scientists, SynBio researchers, and bioprocess engineers is essential for realizing LLM potential.