| Abstract
| - Evaluation of the ALOGPS, ACD Labs LogD, andPALLAS PrologD suites to calculate the log D distributioncoefficient resulted in high root-mean-squared error (RMSE)of 1.0−1.5 log for two in-house Pfizer's log D data sets of 17 861and 640 compounds. Inaccuracy in log P prediction was thelimiting factor for the overall log D estimation by these algorithms. The self-learning feature of the ALOGPS (LIBRARYmode) remarkably improved the accuracy in log D prediction,and an rmse of 0.64−0.65 was calculated for both data sets.
|
