Descriptors for Pentane-2,4-dione and Its Derivatives

Group Contribution and Machine Learning Approaches to Predict Abraham Solute Parameters, Solvation Free Energy, and Solvation Enthalpy

We present a group contribution method (SoluteGC) and a machine learning model (SoluteML) to predict the Abraham solute parameters, as well as a machine learning model (DirectML) to predict solvation free energy and enthalpy at 298 K. The proposed group contribution method uses atom-centered functional groups with corrections for ring and polycyclic strain while the machine learning models adopt a directed message passing neural network. The solute parameters predicted from SoluteGC and SoluteML are used to calculate solvation energy and enthalpy via linear free energy relationships. Extensive data sets containing 8366 solute parameters, 20,253 solvation free energies, and 6322 solvation enthalpies are compiled in this work to train the models. The three models are each evaluated on the same test sets using both random and substructure-based solute splits for solvation energy and enthalpy predictions. The results show that the DirectML model is superior to the SoluteML and SoluteGC models for both predictions and can provide accuracy comparable to that of advanced quantum chemistry methods. Yet, even though the DirectML model performs better in general, all three models are useful for various purposes. Uncertain predicted values can be identified by comparing the three models, and when the 3 models are combined together, they can provide even more accurate predictions than any one of them individually. Finally, we present our compiled solute parameter, solvation energy, and solvation enthalpy databases (SoluteDB, dGsolvDBx, dHsolvDB) and provide public access to our final prediction models through a simple web-based tool, software packages, and source code.

Externally predictive quantum-mechanical models for the adsorption of aromatic organic compounds by graphene-oxide nanomaterials

Graphene oxide is most often chosen as an alternative to graphene in the applications of carbon-based nanomaterials where adsorption is the primary process. However, its adsorption properties are poorly understood. The existing reports on the adsorption mechanism of graphene oxide rely on the linear free-energy/solvation-energy relationship (LFER/LSER) models. This computational work explores the role of quantum mechanical descriptors in the adsorption of aromatic organic compounds by graphene-oxide. For this, externally predictive quantitative models based on quantum-mechanical descriptors are developed and compared with the existing LSERs for the prediction of adsorption coefficients of organic compounds at three different adsorbate concentrations. The predictivity of the models is assessed using an external prediction set of compounds not used for developing the models. Notably, the mean polarizability, but originating from the quantum mechanical exchange interactions (between electrons of parallel spin), is found to be the most significant factor in driving the adsorption on graphene oxide. The present work also proposes quantum-mechanical-LSER models based on a combination of quantum-mechanical and LSER descriptors, which are in fact found to be equally predictive as the existing LSERs. The quantum-mechanical models proposed in this work are further utilized for the prediction of adsorption coefficients of aliphatic compounds.