Dataset Information

Capsule Networks Showed Excellent Performance in the Classification of hERG Blockers/Nonblockers.

ABSTRACT: Capsule networks (CapsNets), a new class of deep neural network architectures proposed recently by Hinton et al., have shown a great performance in many fields, particularly in image recognition and natural language processing. However, CapsNets have not yet been applied to drug discovery-related studies. As the first attempt, we in this investigation adopted CapsNets to develop classification models of hERG blockers/nonblockers; drugs with hERG blockade activity are thought to have a potential risk of cardiotoxicity. Two capsule network architectures were established: convolution-capsule network (Conv-CapsNet) and restricted Boltzmann machine-capsule networks (RBM-CapsNet), in which convolution and a restricted Boltzmann machine (RBM) were used as feature extractors, respectively. Two prediction models of hERG blockers/nonblockers were then developed by Conv-CapsNet and RBM-CapsNet with the Doddareddy's training set composed of 2,389 compounds. The established models showed excellent performance in an independent test set comprising 255 compounds, with prediction accuracies of 91.8 and 92.2% for Conv-CapsNet and RBM-CapsNet models, respectively. Various comparisons were also made between our models and those developed by other machine learning methods including deep belief network (DBN), convolutional neural network (CNN), multilayer perceptron (MLP), support vector machine (SVM), k-nearest neighbors (kNN), logistic regression (LR), and LightGBM, and with different training sets. All the results showed that the models by Conv-CapsNet and RBM-CapsNet are among the best classification models. Overall, the excellent performance of capsule networks achieved in this investigation highlights their potential in drug discovery-related studies.

SUBMITTER: Wang Y

PROVIDER: S-EPMC6997788 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Drug-induced block of the cardiac rapid delayed rectifying potassium current (I Kr), carried by the human ether-a-go-go-related gene (hERG) channel, is the most common cause of acquired long QT syndrome. Indeed, some, but not all, drugs that block hERG channels cause fatal cardiac arrhythmias. However, there is no clear method to distinguish between drugs that cause deadly arrhythmias and those that are clinically safe. Here we propose a mechanism that could explain why certain clinically used hERG blockers are less proarrhythmic than others. We demonstrate that several drugs that block hERG channels, but have favorable cardiac safety profiles, also evoke another effect; they facilitate the hERG current amplitude in response to low-voltage depolarization. To investigate how hERG facilitation impacts cardiac safety, we develop computational models of I Kr block with and without this facilitation. We constrain the models using data from voltage clamp recordings of hERG block and facilitation by nifekalant, a safe class III antiarrhythmic agent. Human ventricular action potential simulations demonstrate the ability of nifekalant to suppress ectopic excitations, with or without facilitation. Without facilitation, excessive I Kr block evokes early afterdepolarizations, which cause lethal arrhythmias. When facilitation is introduced, early afterdepolarizations are prevented at the same degree of block. Facilitation appears to prevent early afterdepolarizations by increasing I Kr during the repolarization phase of action potentials. We empirically test this prediction in isolated rabbit ventricular myocytes and find that action potential prolongation with nifekalant is less likely to induce early afterdepolarization than action potential prolongation with dofetilide, a hERG channel blocker that does not induce facilitation. Our data suggest that hERG channel blockers that induce facilitation increase the repolarization reserve of cardiac myocytes, rendering them less likely to trigger lethal ventricular arrhythmias.

Project description:Drug-induced cardiotoxicity represents one of the most critical safety concerns in the early stages of drug development. The blockade of the human ether-à-go-go-related potassium channel (hERG) is the most frequent cause of cardiotoxicity, as it is associated to long QT syndrome which can lead to fatal arrhythmias. Therefore, assessing hERG liability of new drugs candidates is crucial to avoid undesired cardiotoxic effects. In this scenario, computational approaches have emerged as useful tools for the development of predictive models able to identify potential hERG blockers. In the last years, several efforts have been addressed to generate ligand-based (LB) models due to the lack of experimental structural information about hERG channel. However, these methods rely on the structural features of the molecules used to generate the model and often fail in correctly predicting new chemical scaffolds. Recently, the 3D structure of hERG channel has been experimentally solved enabling the use of structure-based (SB) strategies which may overcome the limitations of the LB approaches. In this study, we compared the performances achieved by both LB and SB classifiers for hERG-related cardiotoxicity developed by using Random Forest algorithm and employing a training set containing 12789 hERG binders. The SB models were trained on a set of scoring functions computed by docking and rescoring calculations, while the LB classifiers were built on a set of physicochemical descriptors and fingerprints. Furthermore, models combining the LB and SB features were developed as well. All the generated models were internally validated by ten-fold cross-validation on the TS and further verified on an external test set. The former revealed that the best performance was achieved by the LB model, while the model combining the LB and the SB attributes displayed the best results when applied on the external test set highlighting the usefulness of the integration of LB and SB features in correctly predicting unseen molecules. Overall, our predictive models showed satisfactory performances providing new useful tools to filter out potential cardiotoxic drug candidates in the early phase of drug discovery.

Dataset Information

Capsule Networks Showed Excellent Performance in the Classification of hERG Blockers/Nonblockers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets