Key result
3D-SDAR neural network predicts drug-induced TdP risk with ~68% accuracy in external validation.
A 3D-SDAR neural network model can predict the torsadogenic potential of drug candidates with moderate accuracy on external validation, potentially aiding early preclinical screening.
Warrants caution for TdP risk prediction due to moderate accuracy; extends computational screening but leaves open prospective validation.
Blockage of some ion channels and in particular, the hERG (human Ether-a’-go-go-Related Gene) cardiac potassium channel delays cardiac repolarization and can induce arrhythmia. In some cases it leads to a potentially life-threatening arrhythmia known as Torsade de Pointes (TdP). Therefore recognizing drugs with TdP risk is essential. Candidate drugs that are determined not to cause cardiac ion channel blockage are more likely to pass successfully through clinical phases II and III trials (and preclinical work) and not be withdrawn even later from the marketplace due to cardiotoxic effects. The objective of the present study is to develop an SAR (Structure-Activity Relationship) model that can be used as an early screen for torsadogenic (causing TdP arrhythmias) potential in drug candidates. The method is performed using descriptors comprised of atomic NMR chemical shifts (13C and 15N NMR) and corresponding interatomic distances which are combined into a 3D abstract space matrix. The method is called 3D-SDAR (3-dimensional spectral data-activity relationship) and can be interrogated to identify molecular features responsible for the activity, which can in turn yield simplified hERG toxicophores. A dataset of 55 hERG potassium channel inhibitors collected from Kramer et al. consisting of 32 drugs with TdP risk and 23 with no TdP risk was used for training the 3D-SDAR model. An artificial neural network (ANN) with multilayer perceptron was used to define collinearities among the independent 3D-SDAR features. A composite model from 200 random iterations with 25% of the molecules in each case yielded the following figures of merit: training, 99.2%; internal test sets, 66.7%; external (blind validation) test set, 68.4%. In the external test set, 70.3% of positive TdP drugs were correctly predicted. Moreover, toxicophores were generated from TdP drugs. A 3D-SDAR was successfully used to build a predictive model for drug-induced torsadogenic and non-torsadogenic drugs based on 55 compounds. The model was tested in 38 external drugs.
No takes yet. Share an insight, caveat, or question.
Sharifi et al. (2017) studied Drug-induced Torsade de Pointes (TdP) arrhythmia (n=93). 3D-SDAR model using perceptron neural networks was evaluated on Prediction accuracy in external blind validation test set. A 3D-SDAR artificial neural network model predicted drug-induced Torsade de Pointes risk with 68.4% overall accuracy and correctly identified 70.3% of positive TdP drugs in an external test set.