Developing a Quantum Physics-Inspired Machine Learning Model for Partition Coefficient Prediction and Comparing Its Performance with Empirical Descriptors and Molecular Graph-Based Models
- 1Indraprastha Institute of Information Technology Delhi , , Okhla Industrial Estate, Phase III , , ,
- 2Indian Institute of Technology Hyderabad , , Kandi , , ,
Abstract
Predicting the partition coefficient (logP) is critical in pharmaceutical research for assessing the bioavailability of small molecules. We present a novel quantum physics-inspired machine learning model (QM-ML) for predicting logP and compare its performance with an empirical descriptor-based model and a graph neural network (GNN) model. For all the models investigated, feature selection was conducted to refine the high-dimensional descriptor space and identify critical determinants of lipophilicity or logP. Quantum mechanical descriptors, in particular frontier orbital energies derived, such as chemical potential, hardness, electrophilicity, electronegativity, and dipole moment, transfer energy, and quantum mechanical polar surface area (QMPSA), were extracted to construct QM-ML mod. The results indicate that the hybrid model achieved the highest predictive accuracy, yielding an R2 of 0.9248, a mean absolute error (MAE) of 0.3511, and a root mean square error (RMSE) of 0.4981. The ExtraTrees regressor, utilizing empirical classical Mordred descriptors, demonstrated comparable performance with an R2 of 0.9141. While models relying exclusively on frontier orbital energies showed limited accuracy (R2 = 0.4349), the inclusion of explicit solvation energy (ΔG) and QMPSA significantly improved the physics-based model performance (R2 = 0.8132). The DeepChem-based GCN model also achieved an R2 of 0.8936. Notably, the explainability analysis showed that certain QM descriptors, such as solvation energy (ΔG) and non-polar QMPSA, contributed significantly to the model performance. The hybrid model outperformed all the physics-based and baseline Mordred models with large-scale descriptor sets and showed the importance of certain QM descriptors, such as solvation transfer energy and QM-PSA. These findings highlight the potential of a hybrid data-driven model involving physics-based descriptors to capture complex molecular interactions and underscore the importance of targeted feature engineering in quantitative structure–property relationship modeling.
Related
- A Machine Learning Approach to logBB Prediction Combining Molecular Docking and Quantum-Chemical Descriptors
- Charge-Transfer-State Descriptors from Donor–Acceptor Interfaces Enable Improved Prediction of Indoor Organic Photovoltaic Efficiency
- Rotamer-Dependent Amino Acid Descriptors as Protein and Peptide Representation for Reactivity and Property Prediction
- Machine learning prediction of DFT-derived electrical conductivity in perovskite and double perovskite materials using physically motivated descriptors
- Microstate-Aware Excited-State Descriptors Improve Scaffold-Robust Prediction of Drug Phototoxicity
BibTeX
@article{tripathi2026developing,
title = {{Developing a Quantum Physics-Inspired Machine Learning Model for Partition Coefficient Prediction and Comparing Its Performance with Empirical Descriptors and Molecular Graph-Based Models}},
author = {Abhishek Tripathi and Riya Rajput and Mohammad Seraj and G. Narahari Sastry and N. Arul Murugan},
journal = {ACS Omega},
year = {2026},
month = nov,
doi = {10.1021/acsomega.6c10110},
url = {https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c10110/5464047/Developing-a-Quantum-Physics-Inspired-Machine},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Developing a Quantum Physics-Inspired Machine Learning Model for Partition Coefficient Prediction and Comparing Its Performance with Empirical Descriptors and Molecular Graph-Based Models
AU - Abhishek Tripathi
AU - Riya Rajput
AU - Mohammad Seraj
AU - G. Narahari Sastry
AU - N. Arul Murugan
PY - 2026
DA - 2026/11/04
JO - ACS Omega
DO - 10.1021/acsomega.6c10110
UR - https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c10110/5464047/Developing-a-Quantum-Physics-Inspired-Machine
AB - Predicting the partition coefficient (logP) is critical in pharmaceutical research for assessing the bioavailability of small molecules. We present a novel quantum physics-inspired machine learning model (QM-ML) for predicting logP and compare its performance with an empirical descriptor-based model and a graph neural network (GNN) model. For all the models investigated, feature selection was conducted to refine the high-dimensional descriptor space and identify critical determinants of lipophilicity or logP. Quantum mechanical descriptors, in particular frontier orbital energies derived, such as chemical potential, hardness, electrophilicity, electronegativity, and dipole moment, transfer energy, and quantum mechanical polar surface area (QMPSA), were extracted to construct QM-ML mod. The results indicate that the hybrid model achieved the highest predictive accuracy, yielding an R2 of 0.9248, a mean absolute error (MAE) of 0.3511, and a root mean square error (RMSE) of 0.4981. The ExtraTrees regressor, utilizing empirical classical Mordred descriptors, demonstrated comparable performance with an R2 of 0.9141. While models relying exclusively on frontier orbital energies showed limited accuracy (R2 = 0.4349), the inclusion of explicit solvation energy (ΔG) and QMPSA significantly improved the physics-based model performance (R2 = 0.8132). The DeepChem-based GCN model also achieved an R2 of 0.8936. Notably, the explainability analysis showed that certain QM descriptors, such as solvation energy (ΔG) and non-polar QMPSA, contributed significantly to the model performance. The hybrid model outperformed all the physics-based and baseline Mordred models with large-scale descriptor sets and showed the importance of certain QM descriptors, such as solvation transfer energy and QM-PSA. These findings highlight the potential of a hybrid data-driven model involving physics-based descriptors to capture complex molecular interactions and underscore the importance of targeted feature engineering in quantitative structure–property relationship modeling.
SN - 2470-1343
ER -