Data-driven multi-objective molecular design of ionic liquid with high generation efficiency on small dataset

Abstract

Ionic liquids (ILs) are promising electrolytes or solvents for numerous applications owing to their unique properties. However, it is a challenge to design the ideal IL with the required properties. Variational autoencoders (VAEs) trained by significantly large datasets have shown good performance in drug discovery. However, low generation efficiency and small sparse datasets prevent their application on IL. In this work, we propose a high generation efficiency molecular design model for IL, which realizes multi-objective optimization on a small dataset. The model combines VAE, multilayer perceptron, and particle swarm optimization for property prediction and molecule optimization. The thermal conductivity and heat capacity of the ILs are chosen as a case to verify the advantages of our model. The results shows that by setting molecular validity judgments to optimization target, 98% output of our method are valid molecules. Besides, the heat capacity and thermal conductivity are improved by 39% and 15%, respectively. Our model improves the applicability to small sparse datasets and the generation efficiency of VAE-like generation model. By multi-objective design ILs for given properties, our model can provide guidance for the design and application of ILs.

Keywords

• Machine learning
• Ionic liquid
• Molecular design
• Generative model