Automated Molecular Concept Generation and Labeling with Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916522459398144 |
|---|---|
| author | Zhang, Zimin Wu, Qianli Xia, Botao Sun, Fang Hu, Ziniu Sun, Yizhou Zhang, Shichang |
| author_facet | Zhang, Zimin Wu, Qianli Xia, Botao Sun, Fang Hu, Ziniu Sun, Yizhou Zhang, Shichang |
| contents | Artificial intelligence (AI) is transforming scientific research, with explainable AI methods like concept-based models (CMs) showing promise for new discoveries. However, in molecular science, CMs are less common than black-box models like Graph Neural Networks (GNNs), due to their need for predefined concepts and manual labeling. This paper introduces the Automated Molecular Concept (AutoMolCo) framework, which leverages Large Language Models (LLMs) to automatically generate and label predictive molecular concepts. Through iterative concept refinement, AutoMolCo enables simple linear models to outperform GNNs and LLM in-context learning on several benchmarks. The framework operates without human knowledge input, overcoming limitations of existing CMs while maintaining explainability and allowing easy intervention. Experiments on MoleculeNet and High-Throughput Experimentation (HTE) datasets demonstrate that AutoMolCo-induced explainable CMs are beneficial for molecular science research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09612 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automated Molecular Concept Generation and Labeling with Large Language Models Zhang, Zimin Wu, Qianli Xia, Botao Sun, Fang Hu, Ziniu Sun, Yizhou Zhang, Shichang Artificial Intelligence Machine Learning Chemical Physics Artificial intelligence (AI) is transforming scientific research, with explainable AI methods like concept-based models (CMs) showing promise for new discoveries. However, in molecular science, CMs are less common than black-box models like Graph Neural Networks (GNNs), due to their need for predefined concepts and manual labeling. This paper introduces the Automated Molecular Concept (AutoMolCo) framework, which leverages Large Language Models (LLMs) to automatically generate and label predictive molecular concepts. Through iterative concept refinement, AutoMolCo enables simple linear models to outperform GNNs and LLM in-context learning on several benchmarks. The framework operates without human knowledge input, overcoming limitations of existing CMs while maintaining explainability and allowing easy intervention. Experiments on MoleculeNet and High-Throughput Experimentation (HTE) datasets demonstrate that AutoMolCo-induced explainable CMs are beneficial for molecular science research. |
| title | Automated Molecular Concept Generation and Labeling with Large Language Models |
| topic | Artificial Intelligence Machine Learning Chemical Physics |
| url | https://arxiv.org/abs/2406.09612 |