ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915364502241280 |
|---|---|
| author | Chen, Kexin Du, Yuyang Li, Junyou Cao, Hanqun Guo, Menghao Dang, Xilin Li, Lanqing Qiu, Jiezhong Heng, Pheng Ann Chen, Guangyong |
| author_facet | Chen, Kexin Du, Yuyang Li, Junyou Cao, Hanqun Guo, Menghao Dang, Xilin Li, Lanqing Qiu, Jiezhong Heng, Pheng Ann Chen, Guangyong |
| contents | The development of AI-assisted chemical synthesis tools requires comprehensive datasets covering diverse reaction types, yet current high-throughput experimental (HTE) approaches are expensive and limited in scope. Chemical literature represents a vast, underexplored data source containing thousands of reactions published annually. However, extracting reaction information from literature faces significant challenges including varied writing styles, complex coreference relationships, and multimodal information presentation. This paper proposes ChemMiner, a novel end-to-end framework leveraging multiple agents powered by large language models (LLMs) to extract high-fidelity chemical data from literature. ChemMiner incorporates three specialized agents: a text analysis agent for coreference mapping, a multimodal agent for non-textual information extraction, and a synthesis analysis agent for data generation. Furthermore, we developed a comprehensive benchmark with expert-annotated chemical literature to evaluate both extraction efficiency and precision. Experimental results demonstrate reaction identification rates comparable to human chemists while significantly reducing processing time, with high accuracy, recall, and F1 scores. Our open-sourced benchmark facilitates future research in chemical literature data mining. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12993 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining Chen, Kexin Du, Yuyang Li, Junyou Cao, Hanqun Guo, Menghao Dang, Xilin Li, Lanqing Qiu, Jiezhong Heng, Pheng Ann Chen, Guangyong Information Retrieval Artificial Intelligence Machine Learning Quantitative Methods The development of AI-assisted chemical synthesis tools requires comprehensive datasets covering diverse reaction types, yet current high-throughput experimental (HTE) approaches are expensive and limited in scope. Chemical literature represents a vast, underexplored data source containing thousands of reactions published annually. However, extracting reaction information from literature faces significant challenges including varied writing styles, complex coreference relationships, and multimodal information presentation. This paper proposes ChemMiner, a novel end-to-end framework leveraging multiple agents powered by large language models (LLMs) to extract high-fidelity chemical data from literature. ChemMiner incorporates three specialized agents: a text analysis agent for coreference mapping, a multimodal agent for non-textual information extraction, and a synthesis analysis agent for data generation. Furthermore, we developed a comprehensive benchmark with expert-annotated chemical literature to evaluate both extraction efficiency and precision. Experimental results demonstrate reaction identification rates comparable to human chemists while significantly reducing processing time, with high accuracy, recall, and F1 scores. Our open-sourced benchmark facilitates future research in chemical literature data mining. |
| title | ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining |
| topic | Information Retrieval Artificial Intelligence Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2402.12993 |