Related Experiment Video
Updated: Sep 13, 2025
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
ChemReactSeek: an artificial intelligence-guided chemical reaction protocol design using retrieval-augmented large
Ziyang Gong1, Chengwei Zhang2, Danyang Song2
1Key Laboratory of Pharmaceutical Engineering of Zhejiang Province, National Engineering Research Center for Process Development of Active Pharmaceutical Ingredients, Collaborative Innovation Center of Yangtze River Delta Region Green Pharmaceuticals, Zhejiang University of Technology, Hangzhou, 310014, P. R. China.
ChemReactSeek automates chemical reaction protocol design using artificial intelligence and large language models (LLMs). This platform extracts data from literature to generate and experimentally validate hydrogenation reaction conditions.
Area of Science:
- Chemical synthesis
- Artificial intelligence in chemistry
- Reaction engineering
Background:
- Designing chemical reaction protocols is complex and time-consuming.
- Automating protocol design can accelerate chemical research and development.
Purpose of the Study:
- To introduce ChemReactSeek, an AI platform for automating chemical reaction protocol design.
- To leverage retrieval-augmented generation with large language models (LLMs) for this purpose.
Main Methods:
- Utilizing DeepSeek-v3 for data extraction and structuring from scientific literature.
- Building a specialized knowledge base for hydrogenation reactions.
- Employing FAISS-based semantic search and LLM-driven reasoning.
- Experimental validation of generated protocols for heterogeneous hydrogenation.
Main Results:
- ChemReactSeek successfully extracts and structures relevant chemical reaction data.
- The platform generates executable reaction conditions for hydrogenation.
- Experimental validation confirms the efficacy of the designed protocols.
Conclusions:
- ChemReactSeek demonstrates a novel approach to automating chemical reaction protocol design.
- The integration of LLMs and semantic search offers a powerful tool for synthetic chemists.
- This AI-driven platform has the potential to significantly expedite chemical synthesis research.
