DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction
Abstract
High-fidelity solubility prediction is fundamental to pharmaceutical development and environmental partitioning, where accurate modeling must couple molecular structure with thermodynamic behavior across diverse chemical environments. However, recent advancements have been dominated by deep learning architectures that often sacrifice physical interpretability for predictive power. We challenge this trend by showing that state-of-the-art performance does not require such non-transparent architectures. To address this, we introduce DISSOLVR, a transparent framework for molecular solubility prediction. In addition, we perform a comprehensive literature review and a benchmarking study against various methods. We show that DISSOLVR approaches the aleatoric limit of experimental uncertainty and achieves OOD generalization through structural invariance, derived by mapping molecules to physically-grounded descriptors. Then, we present an LLM-assisted post-hoc explanation pipeline that bridges the gap between symbolic model artifacts and chemically grounded narratives. Finally, a comparative benchmark of a survey involving 22 expert chemists reveals that expert evaluators provide deep insights.
Related
- AqSol-Blend: A CPU-Trained Descriptor Ensemble for Aqueous Solubility Prediction
- Hybrid-CatBoost: an empirical comparison of molecular representations for aqueous-solubility prediction on the TDC benchmark
- When Do Quantum-Chemical Descriptors Improve Aqueous Solubility Prediction? A Residual-Rescue Benchmark under Chemical Distribution Shift
- Explicitness in SMILES representation via ExACT: improved tokenization for aqueous solubility prediction.
- How Molecular Weight Shapes the Relative Importance of Chemical and Structural Descriptors for Aqueous Solubility
BibTeX
@misc{ramani2026dissolvr,
title = {{DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction}},
author = {Vansh Ramani and Har Ashish Arora and Dhairya Kuchhal and Sayan Ranu and Tarak Karmakar},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.02574},
eprint = {2610.02574},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.02574},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction
AU - Vansh Ramani
AU - Har Ashish Arora
AU - Dhairya Kuchhal
AU - Sayan Ranu
AU - Tarak Karmakar
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.02574
UR - https://arxiv.org/abs/2610.02574
AB - High-fidelity solubility prediction is fundamental to pharmaceutical development and environmental partitioning, where accurate modeling must couple molecular structure with thermodynamic behavior across diverse chemical environments. However, recent advancements have been dominated by deep learning architectures that often sacrifice physical interpretability for predictive power. We challenge this trend by showing that state-of-the-art performance does not require such non-transparent architectures. To address this, we introduce DISSOLVR, a transparent framework for molecular solubility prediction. In addition, we perform a comprehensive literature review and a benchmarking study against various methods. We show that DISSOLVR approaches the aleatoric limit of experimental uncertainty and achieves OOD generalization through structural invariance, derived by mapping molecules to physically-grounded descriptors. Then, we present an LLM-assisted post-hoc explanation pipeline that bridges the gap between symbolic model artifacts and chemically grounded narratives. Finally, a comparative benchmark of a survey involving 22 expert chemists reveals that expert evaluators provide deep insights.
ER -