arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.09612cs.AIcs.LGphysics.chem-ph
收藏

自动化分子概念生成与标注:基于大语言模型的方法

Automated Molecular Concept Generation and Labeling with Large Language Models

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California Los Angeles(加利福尼亚大学洛杉矶分校);California Institute of Technology(加州理工学院);Harvard University(哈佛大学)

Zimin Zhang, Qianli Wu, Botao Xia, Fang Sun, Ziniu Hu, Yizhou Sun, Shichang Zhang

AI总结:

本文提出AutoMolCo框架,利用大语言模型自动生成和标注分子概念,通过迭代精炼使线性模型超越GNN和LLM,无需人工知识,保持可解释性,并在MoleculeNet和HTE数据集上验证其有效性。

摘要:

人工智能(AI)正在变革科学研究,基于概念的可解释AI方法(如概念模型,CMs)在新发现方面展现出潜力。然而,在分子科学中,由于概念模型需要预定义概念和手动标注,其应用不如图神经网络(GNNs)等黑盒模型普遍。本文提出了自动化分子概念(AutoMolCo)框架,利用大语言模型(LLMs)自动生成和标注预测性分子概念。通过迭代概念精炼,AutoMolCo使简单的线性模型在多个基准上超越GNNs和LLM上下文学习。该框架无需人类知识输入,克服了现有概念模型的局限性,同时保持可解释性并允许轻松干预。在MoleculeNet和高通量实验(HTE)数据集上的实验表明,AutoMolCo诱导的可解释概念模型对分子科学研究有益。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑