Application of ALOGPS to predict 1‐octanol/water distribution coefficients, logP, and logD, of AstraZeneca in‐house database

• Published in: Journal of pharmaceutical sciences Vol. 93; no. 12; pp. 3103 - 3110
• Main Authors: Tetko, Igor V., Bruneau, Pierre
• Format: Journal Article
• Language: English
• Published: Hoboken Elsevier Inc 01.12.2004; Wiley Subscription Services, Inc., A Wiley Company; Wiley; American Pharmaceutical Association
• Subjects: 1-Octanol - chemistry; 1-Octanol - metabolism; associative neural network; Biological and medical sciences; computational ADME; Databases, Factual - statistics & numerical data; drug design; Drug Industry - methods; Drug Industry - statistics & numerical data; drug-like properties; General pharmacology; logD; logP; Medical sciences; Pharmaceutical technology. Pharmaceutical industry; Pharmacology. Drug treatments; Predictive Value of Tests; QSAR; QSPR; Software; Water - chemistry; Water - metabolism; drug‐like properties; logD; QSPR; drug design; QSAR; computational ADME; associative neural network; logP; Water; Drug; Pharmaceutical technology; Octanol; drug-like properties; Neural network; Design; Structure activity relation; Distribution; Database; Pharmacokinetics
• ISSN: 0022-3549; 1520-6017
• DOI: 10.1002/jps.20217

The ALOGPS 2.1 was developed to predict 1‐octanol/water partition coefficients, logP, and aqueous solubility of neutral compounds. An exclusive feature of this program is its ability to incorporate new user‐provided data by means of self‐learning properties of Associative Neural Networks. Using this feature, it calculated a similar performance, RMSE = 0.7 and mean average error 0.5, for 2569 neutral logP, and 8122 pH‐dependent logD7.4, distribution coefficients from the AstraZeneca “in‐house” database. The high performance of the program for the logD7.4 prediction looks surprising, because this property also depends on ionization constants pKa. Therefore, logD7.4 is considered to be more difficult to predict than its neutral analog. We explain and illustrate this result and, moreover, discuss a possible application of the approach to calculate other pharmacokinetic and biological activities of chemicals important for drug development. © 2004 Wiley‐Liss, Inc. and the American Pharmacists Association J Pharm Sci 93:3103–3110, 2004