Ligand-based prediction of hERG-mediated cardiotoxicity based on the integration of different machine learning techniques

Abstract

Drug-induced cardiotoxicity is a common side effect of drugs in clinical use or under postmarket surveillance and is commonly due to off-target interactions with the cardiac human-ether-a-go-go-related (hERG) potassium channel. Therefore, prioritizing drug candidates based on their hERG blocking potential is a mandatory step in the early preclinical stage of a drug discovery program. Herein, we trained and properly validated 30 ligand-based classifiers of hERG-related cardiotoxicity based on 7,963 curated compounds extracted by the freely accessible repository ChEMBL (version 25). Different machine learning algorithms were tested, namely, random forest, K-nearest neighbors, gradient boosting, extreme gradient boosting, multilayer perceptron, and support vector machine. The application of 1) the best practices for data curation, 2) the feature selection method VSURF, and 3) the synthetic minority oversampling technique (SMOTE) to properly handle the unbalanced data, allowed for the development of highly predictive models (BAMAX = 0.91, AUCMAX = 0.95). Remarkably, the undertaken temporal validation approach not only supported the predictivity of the herein presented classifiers but also suggested their ability to outperform those models commonly used in the literature. From a more methodological point of view, the study put forward a new computational workflow, freely available in the GitHub repository (https://github.com/PDelre93/hERG-QSAR), as valuable for building highly predictive models of hERG-mediated cardiotoxicity.

AMALPHI: A Machine Learning Platform for Predicting Drug-Induced PhospholIpidosis

“…We extracted 851 entries from ChEMBL v30 according to the Target ID (CHEMBL1626541) assigned to the PLD phenotype. Following an approach described elsewhere, , we checked the validity of each SMILES string using an in-house semiautomated procedure implemented in the KNIME platform. In particular, this procedure allows for the removal of organometallic and inorganic compounds, chemicals characterized by unusual elements and mixtures, neutralizing salts, and stereochemistry.…”

Endocannabinoid Degradation Enzyme Inhibitors as Potential Antipsychotics: A Medicinal Chemistry Perspective

“…To have an overview of the safety of the clinically relevant compounds chosen as candidates for repositioning, we started our analysis with cardiotoxicity (hERG liability), probably the worst early adverse reaction studied during clinical trials focused on acute toxicity [118,119]. To this aim, we employed a recently published ligand-based classifier based on the application of different machine learning algorithms and proved to outperform many predictors commonly used in the literature [120]. More specifically, the model has been developed by using an IC 50 value equal to 10 µM as the threshold for discerning blockers from non-blockers and applies a consensus strategy based on two different algorithms, namely SVM (Support Vector Machine) and BRF (Balanced Random Forest), to provide the requested predictions.…”

“…Results returned by the ligand-based classifier recently published by Delre et al[120]. Notice that an IC 50 = 10 µM was used as the threshold.…”

On QSAR-based cardiotoxicity modeling with the expressiveness-enhanced graph learning model and dual-threshold scheme

“… Chavan et al. (2016) tried to use a consensus model based on the k-nearest neighbor model (KNN) input with eight types of fingerprints to predict the cardiotoxicity for a dataset of 172 compounds, and a careful comparison of different models, including random forest and SVM, was conducted by Delre et al. (2022) to extract the best pipeline of cardiotoxicity modeling.…”