Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.01444 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915381388509184 |
|---|---|
| author | Zhang, Yueqing Liu, Wentao Zhang, Yan Xiong, Danyang Zhai, Jihang Hao, Hao Gu, YuCheng Yang, HaiBo Gao, Shuanhu Hu, Lianrui Zhou, Aimin He, Xiao |
| author_facet | Zhang, Yueqing Liu, Wentao Zhang, Yan Xiong, Danyang Zhai, Jihang Hao, Hao Gu, YuCheng Yang, HaiBo Gao, Shuanhu Hu, Lianrui Zhou, Aimin He, Xiao |
| contents | Large language models (LLM) have achieved impressive progress across a broad range of general-purpose tasks, but their effectiveness in chemistry remains limited due to scarce domain-specific datasets and the demand for precise symbolic and structural reasoning. Here we introduce ECNU-ChemGPT(name after East China Normal University), a chemistry-specialized LLM engineered for deep chemical knowledge understanding and accurate retrosynthetic route planning. Our approach is distinguished by four key strategies: structured prompt-based knowledge distillation from authoritative chemistry textbooks to construct a high-quality question-answering dataset; domain-specific prompt engineering using curated chemical keywords, combined with LLMs APIs for data derivation and knowledge distillation; large-scale fine-tuning on a meticulously cleaned and enriched Pistachio reaction dataset to enhance retrosynthesis prediction accuracy; and integration of BrainGPT, a dynamic multi-model scheduling framework that enables task-specific invocation of multiple specialized models trained for diverse chemistry-related tasks. ECNU-ChemGPT exhibits superior performance on chemistry question-answering and retrosynthetic planning benchmarks, outperforming leading general-purpose models-including Deepseek-R1, Qwen-2.5, and GPT-4o. In retrosynthesis, it achieves a Top-1 accuracy of 68.3% on the USPTO_50K dataset and successfully reconstructed 13 complete experimental pathways for real-world drug molecules from medicinal chemistry journals. These results underscore the effectiveness of domain-adapted fine-tuning combined with dynamic multi-model task scheduling, providing a scalable and robust solution for chemical knowledge question answering and retrosynthetic planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01444 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Large Language Model for Chemistry and Retrosynthesis Predictions Zhang, Yueqing Liu, Wentao Zhang, Yan Xiong, Danyang Zhai, Jihang Hao, Hao Gu, YuCheng Yang, HaiBo Gao, Shuanhu Hu, Lianrui Zhou, Aimin He, Xiao Chemical Physics Large language models (LLM) have achieved impressive progress across a broad range of general-purpose tasks, but their effectiveness in chemistry remains limited due to scarce domain-specific datasets and the demand for precise symbolic and structural reasoning. Here we introduce ECNU-ChemGPT(name after East China Normal University), a chemistry-specialized LLM engineered for deep chemical knowledge understanding and accurate retrosynthetic route planning. Our approach is distinguished by four key strategies: structured prompt-based knowledge distillation from authoritative chemistry textbooks to construct a high-quality question-answering dataset; domain-specific prompt engineering using curated chemical keywords, combined with LLMs APIs for data derivation and knowledge distillation; large-scale fine-tuning on a meticulously cleaned and enriched Pistachio reaction dataset to enhance retrosynthesis prediction accuracy; and integration of BrainGPT, a dynamic multi-model scheduling framework that enables task-specific invocation of multiple specialized models trained for diverse chemistry-related tasks. ECNU-ChemGPT exhibits superior performance on chemistry question-answering and retrosynthetic planning benchmarks, outperforming leading general-purpose models-including Deepseek-R1, Qwen-2.5, and GPT-4o. In retrosynthesis, it achieves a Top-1 accuracy of 68.3% on the USPTO_50K dataset and successfully reconstructed 13 complete experimental pathways for real-world drug molecules from medicinal chemistry journals. These results underscore the effectiveness of domain-adapted fine-tuning combined with dynamic multi-model task scheduling, providing a scalable and robust solution for chemical knowledge question answering and retrosynthetic planning. |
| title | A Large Language Model for Chemistry and Retrosynthesis Predictions |
| topic | Chemical Physics |
| url | https://arxiv.org/abs/2507.01444 |