Solubility is a fundamental physicochemical property of materials. Current solubility prediction models are often highly parameterized by existing data, leading to a serious issue of transferability; thus, it is still challenging to enhancing their accuracy and generalization-ability. In this study, we employ molecular dynamics (MD) simulations and some thermodynamic modeling methods (SMD, COSMO-RS, and COSMO-SAC) to predict the relative solubility of 1,1-diamino-2,2-dinitroethylene (FOX-7) in ten solvents. A meticulous comparison with experimental data reveals that the alchemical free energy approach based on MD simulations outperforms SMD, COSMO-RS and COSMO-SAC models in solubility prediction. Furthermore, we identify that the more negative solvation free energy corresponds to the higher solubility, and the stronger solute–solvent hydrogen bonding corresponds to the higher solubility for low polar solvents too. Finally, it is confirmed that the electrostatic attraction dominates the binding energy between solute and solvent molecules. This work transcends traditional solubility prediction by offering a robust theoretical framework and computational strategy, proving both economical and environmentally benign. It paves the way for the rational selection of solvents for FOX-7 crystallization and provides a versatile tool for predicting the solubility of organic compounds.
Read full abstract