ConSolv: Solvent-Conditional Machine Learning Implicit Solvent Potential
Abstract
Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulations. However, existing models have largely focused on aqueous environments, overlooking the diverse and important roles of non-aqueous solvents in areas such as organic synthesis and battery technology. Here, we present ConSolv, a solvent-conditional MLP architecture that explicitly incorporates solvent effects on solute interactions through an attention-based solvent-embedding block. By combining experimental solvation free energy data with ab initio data, we train a single implicit solvent MLP that is transferable across 66 common organic solvents. ConSolv outperforms classical explicit solvent methods and selected ab initio implicit solvent approaches across multiple solvation free energy benchmarks, and demonstrates generalization to unseen solvents. Beyond solvation free energies, the model shows close agreement with experimental nuclear magnetic resonance (NMR) data for γ-fluorohydrin molecules in chloroform. ConSolv's architecture is readily extensible to broader chemical spaces and alternative training strategies, while its attention-based design supports explainable artificial intelligence (AI) analysis that can help elucidate complex, solvent-dependent molecular interactions.
Related
- Generic aspects of neutral polymer brush bilayers immersed in an implicit solvent under steady-state shear
- IMPLICIT LEARNING: REACTION OUTCOME PREDICTION FROM POSITIVE-ONLY DATA
- Ensemble Molecular Surface Electrostatic Potential Descriptors as Informative Features for Active Learning
- Accuracy, Reliability, and Efficiency of a MACE Machine-Learning Interatomic Potential for Aspirin: A Reproducible Benchmark for Molecular Simulation
- A machine learning-based platform for predicting the potential energy of small molecules
BibTeX
@misc{zhang2026consolv,
title = {{ConSolv: Solvent-Conditional Machine Learning Implicit Solvent Potential}},
author = {Linying Zhang and Julija Zavadlav},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.24983},
eprint = {2606.24983},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.24983},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ConSolv: Solvent-Conditional Machine Learning Implicit Solvent Potential
AU - Linying Zhang
AU - Julija Zavadlav
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2606.24983
UR - https://arxiv.org/abs/2606.24983
AB - Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulations. However, existing models have largely focused on aqueous environments, overlooking the diverse and important roles of non-aqueous solvents in areas such as organic synthesis and battery technology. Here, we present ConSolv, a solvent-conditional MLP architecture that explicitly incorporates solvent effects on solute interactions through an attention-based solvent-embedding block. By combining experimental solvation free energy data with ab initio data, we train a single implicit solvent MLP that is transferable across 66 common organic solvents. ConSolv outperforms classical explicit solvent methods and selected ab initio implicit solvent approaches across multiple solvation free energy benchmarks, and demonstrates generalization to unseen solvents. Beyond solvation free energies, the model shows close agreement with experimental nuclear magnetic resonance (NMR) data for γ-fluorohydrin molecules in chloroform. ConSolv's architecture is readily extensible to broader chemical spaces and alternative training strategies, while its attention-based design supports explainable artificial intelligence (AI) analysis that can help elucidate complex, solvent-dependent molecular interactions.
ER -