Quantitative structure–property relationship of distribution coefficients of organic compounds

ABSTRACT

The n-octanol/buffer solution distribution coefficient (or n-octanol/water partition coefficient) is of critical importance for measuring lipophilicity of drug candidates. After 4885 molecular descriptor generation, 15 molecular descriptors were selected to develop quantitative structure–property relationship (QSPR) models for distribution coefficients at pH 7.4 (log D_7.4) of a large data set consisting of 1043 organic compounds, which was divided into a training set (600 compounds) and a test set (443 compounds). Support vector machine (SVM) based on genetic algorithm was used to develop a model for log D_7.4 that has coefficient of determination r² of 0.919 for the training set and 0.893 for the test set. The results suggest that the SVM model is accurate in predicting log D_7.4.

KEYWORDS:

• Distribution coefficient
• genetic algorithm
• lipophilicity
• structure–property relationship
• SVM

Disclosure statement

No potential conflict of interest was reported by the authors.

Supplementary material

Supplemental data for this article can be accessed at: https://doi.org/10.1080/1062936X.2020.1782468.

Additional information

Funding

This project was supported by the Innovation Platform Opening Fund Project of Colleges and Universities in Hunan Province (16K023); the Hunan Provincial Natural Science Foundation (2018JJ4049) of China and the Open Project Program of Hunan Provincial Key Laboratory of Environmental Catalysis & Waste Regeneration (No. 2018KF11).