ChemReactSeek: an artificial intelligence-guided chemical reaction protocol design using retrieval-augmented large language models
We introduce ChemReactSeek, an advanced artificial intelligence platform that integrates retrieval-augmented generation using large language models (LLMs) to automate the design of chemical reaction protocols. The system employs DeepSeek-v3 to extract and structure data from scientific literature, enabling the construction of a specialized knowledge base focused on hydrogenation reactions. By combining FAISS-based semantic search with LLM-driven reasoning, ChemReactSeek generates executable reaction conditions, which we further validate through experiments on heterogeneous hydrogenation.
Authors
- Hongliang Duan (ORCID: https://orcid.org/0000-0002-9194-0115)
- Bin Shen (ORCID: https://orcid.org/0000-0002-2897-0047)
- Danyang Song (ORCID: https://orcid.org/0009-0005-6424-6610)
- Ziyang Gong (ORCID: https://orcid.org/0009-0006-5191-0380)
- An Su (ORCID: https://orcid.org/0000-0002-6544-3959)
- Wei Xia (ORCID: https://orcid.org/0000-0003-2108-0807)
- Chengwei Zhang (ORCID: https://orcid.org/0000-0002-5254-5403)
- Wei Ke Su
Institutions
- Macao Polytechnic University (MO)
- Zhejiang University of Technology (CN)
Publication Details
- Journal
- Chemical Communications
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5cc03155a
- Citations
- 2
- Primary Topic
- Asymmetric Hydrogenation and Catalysis
- Type
- article
- Field-Weighted Citation Impact
- 1.07
Funders
- National Natural Science Foundation of China
- Science and Technology Program of Zhejiang Province