Advancing energy storage through solubility prediction: leveraging the potential of deep learning

Chaka, Mesfin Diro; Mekonnen, Yedilfana Setarge; Wu, Qin; Geffe, Chernet Amente

doi:10.1039/d3cp03992g

Cited by 1 publication

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…24 A molecular graph attention architecture named MolGAT has also been developed to predict solubility and provide insights in energy storage. 25 Further, Cui et al adopted a residual convolutional neural network architecture comprising approximately 20 layers, for predicting the water solubility of compounds. 26 Panapitiya et al evaluated various DL approaches, including SchNet based on 3D atomic coordinates, long short-term memory neural networks taking SMILES strings as inputs, graph neural networks (GNNs) with graph convolutions, and models based on molecular descriptors.…”

Section: ■ Introductionmentioning

confidence: 99%

“…Francoeur and Koes developed a solubility prediction framework called SolTranNet that is based on the molecule attention transformer . A molecular graph attention architecture named MolGAT has also been developed to predict solubility and provide insights in energy storage . Further, Cui et al adopted a residual convolutional neural network architecture comprising approximately 20 layers, for predicting the water solubility of compounds .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Revisiting the Application of Machine Learning Approaches in Predicting Aqueous Solubility

Zheng,

Mitchell,

Dobson

2024

ACS Omega

View full text Add to dashboard Cite

The solubility of chemical substances in water is a critical parameter in pharmaceutical development, environmental chemistry, agrochemistry, and other fields; however, accurately predicting it remains a challenge. This study aims to evaluate and compare the effectiveness of some of the most popular machine learning modeling methods and molecular featurization techniques in predicting aqueous solubility. Although these methods were not implemented in a competitive environment, some of their performance surpassed previous benchmarks, offering gradual but significant improvements. Our results show that methods based on graph convolution and graph attention mechanisms demonstrated exceptional predictive abilities with high-quality data sets, albeit with a sensitivity to data noise and errors. In contrast, models leveraging molecular descriptors not only provided better interpretability but also showed more resilience when dealing with inherent noise and errors in data. Our analysis of over 4000 molecular descriptors used in various models identified that approximately 800 of these descriptors make a significant contribution to solubility prediction. These insights offer guidance and direction for future developments in solubility prediction.

show abstract

Section: ■ Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Revisiting the Application of Machine Learning Approaches in Predicting Aqueous Solubility

Zheng,

Mitchell,

Dobson

2024

ACS Omega

View full text Add to dashboard Cite

show abstract

Advancing energy storage through solubility prediction: leveraging the potential of deep learning

Abstract: Solubility prediction plays a crucial role in energy storage applications, such as redox flow batteries, because it directly affects the efficiency and reliability.

Cited by 1 publication

References 47 publications

Revisiting the Application of Machine Learning Approaches in Predicting Aqueous Solubility

Revisiting the Application of Machine Learning Approaches in Predicting Aqueous Solubility

Contact Info

Product

Resources

About