In Silico Binary Classification QSAR Models Based on 4D-Fingerprints and MOE Descriptors for Prediction of hERG Blockage

Abstract

Blockage of the human ether-a-go-go related gene (hERG) potassium ion channel is a major factor related to cardiotoxicity. Hence, drugs binding to this channel have become an important biological end point in side effects screening. A set of 250 structurally diverse compounds screened for hERG activity from the literature was assembled using a set of reliability filters. This data set was used to construct a set of two-state hERG QSAR models. The descriptor pool used to construct the models consisted of 4D-fingerprints generated from the thermodynamic distribution of conformer states available to a molecule, 204 traditional 2D descriptors and 76 3D VolSurf-like descriptors computed using the Molecular Operating Environment (MOE) software. One model is a continuous partial least-squares (PLS) QSAR hERG binding model. Another related model is an optimized binary classification QSAR model that classifies compounds as active or inactive. This binary model achieves 91% accuracy over a large range of molecular diversity spanning the training set. Two external test sets were constructed. One test set is the condensed PubChem bioassay database containing 876 compounds, and the other test set consists of 106 additional compounds found in the literature. Both of the test sets were used to validate the binary QSAR model. The binary QSAR model permits a structural interpretation of possible sources for hERG activity. In particular, the presence of a polar negative group at a distance of 6-8 A from a hydrogen bond donor in a compound is predicted to be a quite structure-specific pharmacophore that increases hERG blockage. Since a data set of high chemical diversity was used to construct the binary model, it is applicable for performing general virtual hERG screening.

A human ether-á-go-go-related (hERG) ion channel atomistic model generated by long supercomputer molecular dynamics simulations and its use in predicting drug cardiotoxicity

“…Most of the previously available hERG computational models are ligand-based but since these rely mainly on the existence of structural similarities between the tested drug candidate and previously reported known hERG blockers, these models have limited value in the frequent case of a novel drug structure (Aronov and Goldman, 2004;Coi et al, 2006;Du-Cuny et al, 2011;Ekins et al, 2002;Keseru, 2003;Song and Clark, 2006;Su et al, 2010;Yoshida and Niwa, 2006). Producing a reliable hERG ion channel structure-based model to directly test drug binding (Broccatelli et al, 2012;Du-Cuny et al, 2011) has therefore been of high priority but in the absence of a hERG crystal structure, this has been limited to creating homology models that have excluded a large portion of the hERG channel and which display very limited conformational flexibility (Boukharta et al, 2011;Di Martino et al, 2013;Farid et al, 2006;Osterberg and Aqvist, 2005).…”

hERG K+Channels: Structure, Function, and Clinical Significance

“…In contrast, molecular features that in general negatively correlate with block include the presence of polar entities (156,447,569,638,703) and hydrophilic groups close to hydrophobic regions of the drug (562,569). On this note, distances between features (such as proximity between nonpolar atoms or between hydrogen bond donors and polar groups) may also be significant factors (569,599).…”

The great descriptor melting pot: mixing descriptors for the common good of QSAR models

“…Recently we have shown that merging 1D through 4D molecular descriptor sets into a single trial descriptor pool leads to multi-class continuous and classification QSAR models that are superior for the prediction of hERG cardiotoxicity when compared to models from the corresponding segregated descriptor sets. [36,37] The transport of organic compounds through lipid assemblies of the stratum corneum for transdermal drug delivery applications has also been modeled using multiple classes of descriptors. [38] The trial descriptor pool consisted of intermolecular interactions between a membrane (monolayer of DMPC) and the penetrant as well as intramolecular (1D and 2D molecular descriptors; classic descriptors) features of only the penetrant.…”