A k-nearest neighbor classification of hERG K(+) channel blockers.

Swapnil Chavan,Jesper G Wiklander,Ahmed Abdelaziz,Ian A Nicholls

doi:10.1007/s10822-016-9898-z

Swapnil Chavan, Jesper G Wiklander + Show 2 more

Open Access

https://doi.org/10.1007/s10822-016-9898-z

Copy DOI

Abstract

A series of 172 molecular structures that block the hERG K+ channel were used to develop a classification model where, initially, eight types of PaDEL fingerprints were used for k-nearest neighbor model development. A consensus model constructed using Extended-CDK, PubChem and Substructure count fingerprint-based models was found to be a robust predictor of hERG activity. This consensus model demonstrated sensitivity and specificity values of 0.78 and 0.61 for the internal dataset compounds and 0.63 and 0.54 for the external (PubChem) dataset compounds, respectively. This model has identified the highest number of true positives (i.e. 140) from the PubChem dataset so far, as compared to other published models, and can potentially serve as a basis for the prediction of hERG active compounds. Validating this model against FDA-withdrawn substances indicated that it may even be useful for differentiating between mechanisms underlying QT prolongation.Electronic supplementary materialThe online version of this article (doi:10.1007/s10822-016-9898-z) contains supplementary material, which is available to authorized users.

Highlights

The human ether-a-go-go related gene encodes for a voltage dependent K? ion channel (Kv11.1)
The k-nearest neighbor (k-NN) classification method was employed to construct classification models using each of the eight PaDEL fingerprints
Employing the k-NN algorithm requires that the optimal value of k is determined [34]

Summary

Introduction

The human ether-a-go-go related gene (hERG, KCNH2) encodes for a voltage dependent K? ion channel (Kv11.1). The human ether-a-go-go related gene (hERG, KCNH2) encodes for a voltage dependent K? Blocking of this channel has been associated with potential severe heart arrhythmia, and because of this, several drugs have been withdrawn from the market [1,2,3,4,5,6]. The drug-induced long QT syndrome may cause avoidable sudden cardiac arrest [3, 4]. With the intention of protecting clinical trial participants and patients, the International Conference of Harmonization published a guideline (S7B) recommending that ‘‘all new drugs’’ should be tested pre-clinically for hERG sensitivity and cardiac safety before submitting an application to regulatory reviews [7]. The early assessment of hERG-related cardiotoxicity has become a common practice in drug discovery.

Methods

Results

Conclusion