A discriminant model constructed by the support vector machine method for HERG potassium channel inhibitors

• Published in: Bioorganic & medicinal chemistry letters Vol. 15; no. 11; pp. 2886 - 2890
• Main Authors: Tobita, Motoi, Nishikawa, Tetsuo, Nagashima, Renpei
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 02.06.2005; Elsevier
• Subjects: Animals; Biological and medical sciences; CHO Cells; Cricetinae; Discriminant Analysis; Drug toxicity and drugs side effects treatment; ERG1 Potassium Channel; Ether-A-Go-Go Potassium Channels; HERG; Humans; In silico; Medical sciences; Pharmacology. Drug treatments; Potassium Channel Blockers - pharmacology; Potassium Channels, Voltage-Gated - antagonists & inhibitors; Prediction; SVM; Toxicity: cardiovascular system; In silico; Discriminant analysis; HERG; SVM; Prediction; Drug; Wave burst; Arrhythmia; Potassium channel antagonist; Toxicity; Cardiovascular disease; Support vector machine; Classification; Inhibition; Chemometrics
• ISSN: 0960-894X; 1464-3405
• DOI: 10.1016/j.bmcl.2005.03.080

Constructed models achieved 95% and 90% accuracy in classifying HERG actives and inactives as a result of 10-fold cross validation. The two test sets consist of 73 diverse drugs. HERG attracts attention as a risk factor for arrhythmia, which might trigger torsade de pointes. A highly accurate classifier of chemical compounds for inhibition of the HERG potassium channel is constructed using support vector machine. For two test sets, our discriminant models achieved 90% and 95% accuracy, respectively. The classifier is even applied for the prediction of cardio vascular adverse effects to achieve about 70% accuracy. While modest inhibitors are partly characterized by properties linked to global structure of a molecule including hydrophobicity and diameter, strong inhibitors are exclusively characterized by properties linked to substructures of a molecule.