Major Source of Error in QSPR Prediction of Intrinsic Thermodynamic Solubility of Drugs: Solid vs Nonsolid State Contributions?

The
main purpose of this study is to define the major limiting
factor in the accuracy of the quantitative structure–property
relationship (QSPR) models of the thermodynamic intrinsic aqueous
solubility of the drug-like compounds. For doing this, the thermodynamic
intrinsic aqueous solubility property was suggested to be indirectly
“measured” from the contributions of solid state, ΔGfus, and nonsolid state, ΔGmix, properties, which are
estimated by the corresponding QSPR models. The QSPR models of ΔGfus and ΔGmix properties were built based on a
set of drug-like compounds with available accurate measurements of
fusion and thermodynamic solubility properties. For consistency ΔGfus and ΔGmix models were developed using similar algorithms
and descriptor sets, and validated against the similar test compounds.
Analysis of the relative performances of these two QSPR models clearly
demonstrates that it is the solid state contribution which is the
limiting factor in the accuracy and predictive power of the QSPR models
of the thermodynamic intrinsic solubility. The performed analysis
outlines a necessity of development of new descriptor sets for an
accurate description of the long-range order (periodicity) phenomenon
in the crystalline state. The proposed approach to the analysis of
limitations and suggestions for improvement of QSPR-type models may
be generalized to other applications in the pharmaceutical industry.