Pharmacokinetic parameter prediction from drug structure using artificial neural networks

• Published in: International journal of pharmaceutics Vol. 270; no. 1; pp. 209 - 219
• Main Authors: Turner, Joseph V, Maddalena, Desmond J, Cutler, David J
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 11-02-2004; Elsevier
• Subjects: ANN; Biological and medical sciences; Drug Design; General pharmacology; Humans; Medical sciences; Models, Molecular; Molecular Structure; Neural networks; Neural Networks (Computer); Pharmaceutical Preparations - chemistry; Pharmacokinetics; Pharmacokinetics. Pharmacogenetics. Drug-receptor interactions; Pharmacology. Drug treatments; QSPkR; QSPR; Structure-Activity Relationship; Technology, Pharmaceutical; Theoretical descriptors; ANN; Theoretical descriptors; QSPkR; QSPR; Neural networks; Drug; Pharmaceutical technology; Prediction; Theoretical study; Neural network; Parameter; Property structure relationship; Pharmacokinetics
• ISSN: 0378-5173; 1873-3476
• DOI: 10.1016/j.ijpharm.2003.10.011

Simple methods for determining the human pharmacokinetics of known and unknown drug-like compounds is a much sought-after goal in the pharmaceutical industry. The current study made use of artificial neural networks (ANNs) for the prediction of clearances, fraction bound to plasma proteins, and volume of distribution of a series of structurally diverse compounds. A number of theoretical descriptors were generated from the drug structures and both automated and manual pruning were used to derive optimal subsets of descriptors for quantitative structure-pharmacokinetic relationship models. Models were trained on one set of compounds and validated with another. Absolute predicted ability was evaluated using a further independent test set of compounds. Correlations for test compounds ranged from 0.855 to 0.992. Predicted values agreed closely with experimental values for total clearance, renal clearance, and volume of distribution, while predictions for protein binding were encouraging. The combination of descriptor generation, ANNs, and the speed and success of this technique compared with conventional methods shows strong potential for use in pharmaceutical product development.