Predicting CO 2 Absorption in Ionic Liquids with Molecular Descriptors and Explainable Graph Neural Networks

作者：Yue Jian, Yuyang Wang, Amir Barati Farimani · 发表于：ACS Sustainable Chemistry & Engineering · 年份：2022 · DOI：10.1021/acssuschemeng.2c05985 · 被引用次数：62 · 研究领域：Ionic liquids properties and applications、Carbon dioxide utilization in catalysis、CO2 Reduction Techniques and Catalysts

Ionic liquids (ILs) provide a promising solution for CO 2 capture and storage to mitigate global warming. However, identifying and designing the high-capacity IL from the giant chemical space require expensive and exhaustive simulations and experiments. Machine learning (ML) can accelerate the process of searching for desirable ionic molecules through accurate and efficient property predictions in a data-driven manner. However, existing descriptors and ML models for the ionic molecule suffer from the inefficient adaptation of molecular graph structure. Besides, few works have investigated the explainability of ML models to help understand the learned features that can guide the design of efficient ionic molecules. In this work, we develop both fingerprint-based ML models and graph neural networks (GNNs) to predict the CO 2 absorption in ILs. Fingerprint works on graph structure at the feature extraction stage, while GNNs directly handle molecule structure in both the feature extraction and model prediction stage. We show that our method outperforms previous ML models by reaching a high accuracy (MAE of 0.0137, R 2 of 0.9884). Furthermore, we take the advantage of GNN representation and develop a substructure-based explanation method that provides insight into how each chemical fragment within IL molecules contributes to the CO 2 absorption prediction of ML models. We also show that our result agrees with some ground truth on functional group importance from the theoretical un...