文献类型： 会议论文

第一作者： Mathias Hilfiker

作者： Mathias Hilfiker ¹ ; Leonardo Medrano Sandonas ² ; Marco Klahn ³ ; Ola Engkvist ³ ; Alexandre Tkatchenko ¹ ;

作者机构： 1.Department of Physics and Materials Science, University of Luxembourg

2.Institute for Materials Science and Max Bergmann Center of Biomaterials, TU Dresden

3.Molecular AI, Discovery Sciences, R&D, AstraZeneca

关键词： Drug-like molecules;Quantum-mechanical properties;Solvent effects;Property prediction

会议名称：

主办单位：

页码： 47-57

摘要： Understanding how solvation affects structure-property and property-property relationships of drug-like molecules is crucial for de novo design, as most relevant reactions occur in aqueous environments. We have thus performed an exhaustive analysis of the recently proposed Aquamarine dataset to gain insights into the effect of solvent-molecule interaction on the quantum-mechanical (QM) properties of large druglike molecules. Our results show that the inclusion of an implicit solvent model of water changes the values of (extensive and intensive) QM properties but it does not alter the correlations among them. Moreover, we have found that solvation can limit the identification of unique molecular conformations, with variations in specific properties being rationalized by the extent of structural changes. Δ-learning approach was used to predict solvent effects on the dipole moment μ and the many-body dispersion energy E_(MBD), resulting in more accurate and scalable predictive models compared to these directly trained on solvated properties. Hence, our work provides valuable insights into the effect of solvent-molecule interaction on physicochemical properties, which could assist in the development of machine-learning models for designing solvated molecules of pharmaceutical and biological relevance.

分类号： tp18-53