Premium
Classification Models for hERG Inhibitors by Counter‐Propagation Neural Networks
Author(s) -
Thai KhacMinh,
Ecker Gerhard F.
Publication year - 2008
Publication title -
chemical biology and drug design
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.59
H-Index - 77
eISSN - 1747-0285
pISSN - 1747-0277
DOI - 10.1111/j.1747-0285.2008.00705.x
Subject(s) - herg , test set , artificial neural network , artificial intelligence , training set , quantitative structure–activity relationship , set (abstract data type) , computer science , class (philosophy) , pattern recognition (psychology) , data set , potassium channel , machine learning , biological system , chemistry , biology , biophysics , programming language
Counter‐propagation neural networks were used to develop computational models for classification and prediction of human ether‐a‐go‐go‐related‐gene (hERG) potassium channel blockers. The data set used includes 285 compounds taken from literature sources and two sets of 2D molecular descriptors, one is based on 32 P_VSA descriptors derived from moe and the other comprises 11 descriptors retrieved by a feature selection method. The counter‐propagation neural networks with a 3‐dimensional output layer combined with a set of 11 hERG relevant descriptors showed best performance, especially in classifying compounds in the middle‐activity class (hERG IC 50 = 1–10 μ m ). The total accuracy values obtained for training and test sets are 0.93–0.95 and 0.83–0.85, respectively. In each activity class (low, medium, high), ‘Goodness of Hit lists’ GH scores archived range from 0.89 to 0.97 for the training set and from 0.74 to 0.87 for the test set. This model thus provides possible strategies for improving the performance of predicting and classifying compounds having hERG IC 50 in the range of 1–10 μ m .