ADME Evaluation in Drug Discovery. 4. Prediction of Aqueous Solubility Based on Atom Contribution Approach

A novel method for the estimation of aqueous solubility was solely based on simple atom contribution.
Each atom in a molecule has its own contribution to aqueous solubility and was developed. Altogether 76
atom types were used to classify atoms with different chemical environments. Moreover, two correction
factors, including hydrophobic carbon and square of molecular weight, were used to account for the inter-/intramolecular hydrophobic interactions and bulkiness effect. The contribution coefficients of different atom
types and correction factors were generated based on a multiple linear regression using a learning set consisting
of 1290 organic compounds. The obtained linear regression model possesses good statistical significance
with an overall correlation coefficient (r) of 0.96, a standard deviation (s) of 0.61, and an unsigned mean
error (UME) of 0.48. The actual prediction potential of the model was validated through an external test set
with 21 pharmaceutically and environmentally interesting compounds. For the test set, a predictive r =
0.94, s = 0.84, and UME = 0.52 were achieved. Comparisons among eight procedures of solubility calculation
for those 21 molecules demonstrate that our model bears very good accuracy and is comparable to or even
better than most reported techniques based on molecular descriptors. Moreover, we compared the performance
of our model to a test set of 120 molecules with a popular group contribution method developed by Klopman
et al. For this test set, our model gives a very effective prediction (r = 0.96, s = 0.79, UME = 0.57), which
is obviously superior to the predicted results (r = 0.96, s = 0.84, UME = 0.70) given by the Klopman's
group contribution approach. Because of the adoption of atoms as the basic units, our addition model does
not contain a “missing fragment” problem and thus may be more simple and universal than the group
contribution models and can give predictions for any organic molecules. A program, drug-LOGS, had been
developed to identify the occurrence of atom types and estimate the aqueous solubility of a molecule.