Efficient Quantum-Chemical Calculations of Acid Dissociation Constants from Free-Energy Relationships

The calculation of
acid dissociation constants (pKa) is an
important task in computational chemistry and
chemoinformatics. Theoretically and with minimal empiricism, this
is possible from computed acid dissociation free energies via so-called
linear free-energy relationships. In this study some modifications
are introduced to the latter, providing a straightforward, broadly
applicable protocol with an adjustable degree of sophistication for
quantum chemistry-based calculations of pKa in water. It targets a wide pKa range
(∼70 units) and medium-sized, flexible molecules. Herein, a
focus is set on the recently published r2SCAN-3c and related
efficient composite density functionals and the semiempirical GFN2–xTB
method, including a newly introduced energy correction for heterolytic
dissociation, both in combination with implicit solvation models.
The performance is evaluated in comparison with experimental data,
showing mean errors often smaller than a targeted 1 pKa unit accuracy. Larger deviations are observed only upon
inclusion of challenging highly negative (<−5) or positive
(>15) pKa values. Among all those tested,
it is found that B97-3c is the best performing functional, although
rather independently of the density functional theory (DFT) method
used; low root-mean-square errors of 0.8–1.0 pKa units for typical drugs are obtained. For optimal performance,
it is recommended to employ DFT functional specific free-energy relationship
parameters. Additionally, a significant conformational dependence
of the pKa values is revealed and quantified
for some nonrigid drug molecules.