Intelligent Molecular Identification Approach to High-Efficiency Solvents for Organosulfide Capture Using the Active Machine Learning Framework

Yuxiang Chen, Chuanlei Liu, Yang An, Yue Lou, Yang Zhao, Qian Cheng, Hao Jiang, Kongguo Wu, Boxiong Shen, Xianghui Zhang, Fahai Cao, Di Wu, Hui SunEnergy 2023 · DOI

Abstract

There is increasing interest in the development of intelligent strategies for rational design and/or identification of promising solvent compounds for volatile, environmentally unfriendly compound capture. However, typical computer-aided methods require huge datasets and/or suffer from accumulated prediction bias. Here, we constructed a computational framework by introducing a stepwise screen approach for molecular descriptors and molecular active selection machine learning to modify the adequate chemical space iteratively. This framework identifies the optimal solvent candidates by molecular similarity search and iterative molecular addition to the training dataset. In a virtual screening of 126,068 compounds, 2443 solvent candidates were successfully identified for the capture of methyl mercaptan (MeSH), one of the major organosulfides in fossil gases.
BibTeX
@inproceedings{chen2023intelligent,
  author = {Yuxiang Chen and Chuanlei Liu and Yang An and Yue Lou and Yang Zhao and Qian Cheng and Hao Jiang and Kongguo Wu and Boxiong Shen and Xianghui Zhang and Fahai Cao and Di Wu and Hui Sun},
  title = {{Intelligent Molecular Identification Approach to High-Efficiency Solvents for Organosulfide Capture Using the Active Machine Learning Framework}},
  booktitle = {Energy},
  year = {2023},
  doi = {10.1021/acs.energyfuels.3c01525},
}

Loading related content...

Figure