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 2406.08075cs.LG
收藏

平衡分子信息与经验数据在物理化学性质预测中的应用

Balancing Molecular Information and Empirical Data in the Prediction of Physico-Chemical Properties

AI Center Tübingen(蒂宾根人工智能中心);University of Tübingen(蒂宾根大学);IMPRS-IS(国际马克斯·普朗克研究学院智能系统);RPTU Kaiserslautern(凯撒斯劳滕莱茵兰-普法尔茨技术大学)

Johannes Zenn, Dominik Gond, Fabian Jirasek, Robert Bamler

AI总结:

提出一种利用期望最大化算法结合分子描述符与表征学习的通用方法,以二元混合物活度系数预测为例,显著提升预测精度,优于现有方法。

摘要:

预测纯物质和混合物的物理化学性质是热力学中的核心任务。现有的预测方法涵盖多种类型:从完全基于物理的从头算(仅适用于极简单系统),到基于描述符的方法(利用待建模分子的部分信息与拟合模型参数,如定量结构-性质关系方法或经典基团贡献法),再到表征学习方法(极端情况下可完全忽略分子描述符,仅从待建模性质的现有数据外推,如矩阵补全方法)。在这项工作中,我们提出了一种利用概率机器学习文献中的期望最大化算法将分子描述符与表征学习相结合的通用方法,该方法使用不确定性估计在两种方法之间进行权衡。所提出的混合模型利用图神经网络提取化学结构信息,但它会自动检测基于结构的预测不可靠的情况,在这种情况下,它会通过更能专门处理异常情况的基于表征学习的预测来纠正它们。以二元混合物中活度系数的预测为例,证明了所提方法的有效性。结果令人信服,该方法显著提高了预测精度,优于当前最先进的方法,展示了其在推动物理化学性质预测方面的潜力。

英文摘要:

Predicting the physico-chemical properties of pure substances and mixtures is a central task in thermodynamics. Established prediction methods range from fully physics-based ab-initio calculations, which are only feasible for very simple systems, over descriptor-based methods that use some information on the molecules to be modeled together with fitted model parameters (e.g., quantitative-structure-property relationship methods or classical group contribution methods), to representation-learning methods, which may, in extreme cases, completely ignore molecular descriptors and extrapolate only from existing data on the property to be modeled (e.g., matrix completion methods). In this work, we propose a general method for combining molecular descriptors with representation learning using the so-called expectation maximization algorithm from the probabilistic machine learning literature, which uses uncertainty estimates to trade off between the two approaches. The proposed hybrid model exploits chemical structure information using graph neural networks, but it automatically detects cases where structure-based predictions are unreliable, in which case it corrects them by representation-learning based predictions that can better specialize to unusual cases. The effectiveness of the proposed method is demonstrated using the prediction of activity coefficients in binary mixtures as an example. The results are compelling, as the method significantly improves predictive accuracy over the current state of the art, showcasing its potential to advance the prediction of physico-chemical properties in general.

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。

↑