Modeling and estimation of physiochemical properties of cancer drugs using entropy measures

Abstract

Hyaluronic acid-paclitaxel conjugate is a nanoparticle-based drug delivery system that combines hyaluronic acid with paclitaxel, enhancing its solubility, stability, and targeting specificity. This conjugate shows promise in treating breast, lung, and ovarian cancers with reduced side effects. Entropy measures are used to predict physical and chemical properties of drugs. In this paper, we compute entropy measures for the hyaluronic acid-paclitaxel conjugate using the edge/connectivity partition approach. We establish a quantitative structure-property relationship using reverse entropy measures to predict physical properties of cancer drugs. Multiple linear, Ridge, Lasso, ElasticNet, and Support Vector regression models are employed using Python software. Our results show that reverse entropy measures exhibit high predictive capability for physical properties, based on the highest coefficient of determination and lowest mean squared error. We conclude that physical properties, including boiling point, enthalpy of vaporization, flash point, molar refractivity, molar volume, polarization, molecular weight, monoisotopic mass, topological polar surface area, and complexity, can be predicted using reverse entropy measures. We propose models for each relationship, including only the most significant models for estimating uncalculated physical properties.