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 whilst 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, 20253 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 3 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 package, and source code.

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 whilst 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, 20253 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 3 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 package, and source code.

Solvation Free Energy of Protonated Lysine: Molecular Dynamics Study

In the present work, we have used an alchemical approach for calculating solvation free energy of protonated lysine in water from molecular dynamics simulations. These approaches use a non-physical pathway between two end states in order to compute free energy difference from the set of simulations. The solute is modeled using bonded and non-bonded interactions described by OPLS-AA potential, while four different water models: TIP3P, SPC, SPC/E and TIP4P are used. The free energy of solvation of protonated lysine in water has been estimated using thermodynamic integration, free energy perturbation, and Bennett acceptance ratio methods at 310 K temperature. The contributions to the free energy due to van der Waals and electrostatics parameters are also separately computed. The estimated values of free energy of solvation using different methods are in well agreement with previously reported experimental value within 14 %.

MLSolvA: solvation free energy prediction from pairwise atomistic interactions by machine learning

Recent advances in machine learning technologies and their applications have led to the development of diverse structure–property relationship models for crucial chemical properties. The solvation free energy is one of them. Here, we introduce a novel ML-based solvation model, which calculates the solvation energy from pairwise atomistic interactions. The novelty of the proposed model consists of a simple architecture: two encoding functions extract atomic feature vectors from the given chemical structure, while the inner product between the two atomistic feature vectors calculates their interactions. The results of 6239 experimental measurements achieve outstanding performance and transferability for enlarging training data owing to its solvent-non-specific nature. An analysis of the interaction map shows that our model has significant potential for producing group contributions on the solvation energy, which indicates that the model provides not only predictions of target properties but also more detailed physicochemical insights.

Performance of molecular dynamics simulation for predicting of solvation free energy of neutral solutes in methanol

In this study, molecular dynamics simulation was applied for calculating solvation free energy of 16 solute molecules in methanol solvent. The thermodynamic integration method was used because it was possible to calculate the difference in free energy in any thermodynamic path. After comparing results for solvation free energy in different force fields, COMPASS force field was selected since it had the lowest error compared to experimental result. Group-based summation method was used to compute electrostatic and van der Waals forces at 298.15 K and 1 atm. The results of solvation free energy were obtained from molecular dynamics simulation and were compared to the results from Solvation Model Density (SMD) and Universal Continuum Solvation Model (denoted as SM8), which were obtained from other research works. Average square-root-error for molecular dynamics simulation, SMD and SM8 models were 0.096091, 0.595798, and 0.70649. Furthermore, the coefficient of determination (R 2) for molecular dynamics simulation was 0.9618, which shows higher accuracy of MD simulation for calculating solvation free energy comparing to two other models.

Improved prediction of solvation free energies by machine-learning polarizable continuum solvation model

Theoretical estimation of solvation free energy by continuum solvation models, as a standard approach in computational chemistry, is extensively applied by a broad range of scientific disciplines. Nevertheless, the current widely accepted solvation models are either inaccurate in reproducing experimentally determined solvation free energies or require a number of macroscopic observables which are not always readily available. In the present study, we develop and introduce the Machine-Learning Polarizable Continuum solvation Model (ML-PCM) for a substantial improvement of the predictability of solvation free energy. The performance and reliability of the developed models are validated through a rigorous and demanding validation procedure. The ML-PCM models developed in the present study improve the accuracy of widely accepted continuum solvation models by almost one order of magnitude with almost no additional computational costs. A freely available software is developed and provided for a straightforward implementation of the new approach.