A Unified Approach to Inferring Chemical Compounds with the Desired Aqueous Solubility

TL;DR

This paper introduces a unified, efficient method combining graph-theoretic descriptors, regression, and optimization to accurately predict and infer chemical compounds with specific aqueous solubility, simplifying existing complex models.

Contribution

The authors develop a novel approach that uses simple descriptors and linear models to predict and infer compounds with desired solubility, reducing computational complexity and increasing interpretability.

Findings

Achieved high prediction accuracy with simple models (0.7191 to 0.9377) across diverse datasets.

Successfully inferred optimal compounds with up to 50 non-hydrogen atoms within seconds to minutes.

Demonstrated strong correlation between simple descriptors and aqueous solubility, enabling deeper understanding.

Abstract

Aqueous solubility (AS) is a key physiochemical property that plays a crucial role in drug discovery and material design. We report a novel unified approach to predict and infer chemical compounds with the desired AS based on simple deterministic graph-theoretic descriptors, multiple linear regression (MLR) and mixed integer linear programming (MILP). Selected descriptors based on a forward stepwise procedure enabled the simplest regression model, MLR, to achieve significantly good prediction accuracy compared to the existing approaches, achieving the accuracy in the range [0.7191, 0.9377] for 29 diverse datasets. By simulating these descriptors and learning models as MILPs, we inferred mathematically exact and optimal compounds with the desired AS, prescribed structures, and up to 50 non-hydrogen atoms in a reasonable time range [6, 1204] seconds. These findings indicate a strong correlation between the simple graph-theoretic descriptors and the AS of compounds, potentially leading to a deeper understanding of their AS without relying on widely used complicated chemical descriptors and complex machine learning models that are computationally expensive, and therefore difficult to use for inference. An implementation of the proposed approach is available at https://github.com/ku-dml/mol-infer/tree/master/AqSol.