Predictions of the ADMET Properties of Candidate Drug Molecules Utilizing Different QSAR/QSPR Modelling Approaches

Title: Predictions of the ADMET Properties of Candidate Drug Molecules Utilizing Different QSAR/QSPR Modelling Approaches

Volume: 11 Issue: 4

Author(s): Mahmud Tareq Hassan Khan

Affiliation:

Keywords: ADMET, drugability, molecular descriptor, QSAR modeling, logP, logD, artificial neural network, PSA, multiple linear regressions, machine learning, support vector machine, inductive logic programming

Abstract: The integration of early ADMET (absorption, distribution, metabolism, excretion and toxicity) profiling, or simply prediction, of lead molecules to speed-up the lead selection further for phase-I trial without losing large amount of revenue. The ADMET profiling and prediction is mostly dependent of a number of molecular descriptors, for example, Lipinskis Rule of 5 (Ro5). Recently a large number of articles have been reporting that it possible to do some prediction of the ADMET properties using the structural features of the molecules, utilizing several and multiple approaches. One of the most important approaches is the QSAR/QSPR modelling of the data derived from their activity profiles and their different structural features (i.e., quantitative molecular descriptors).

Cite this article as:

Tareq Hassan Khan Mahmud, Predictions of the ADMET Properties of Candidate Drug Molecules Utilizing Different QSAR/QSPR Modelling Approaches, Current Drug Metabolism 2010; 11 (4) . https://dx.doi.org/10.2174/138920010791514306