Enhanced drug classification using machine learning with multiplexed cardiac contractility assays

• Published in: Pharmacological research Vol. 209; p. 107459
• Main Authors: Aghavali, Reza, Roberts, Erin G., Kurokawa, Yosuke K., Mak, Erica, Chan, Martin Y.C., Wong, Andy O.T., Li, Ronald A., Costa, Kevin D.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Ltd 01-11-2024; Elsevier
• Subjects: Cardiac contractility; Cardiac tissue engineering; Drug discovery; Electrophysiology; In vitro screening; Pharmaceutical compound testing; Electrophysiology; Drug discovery; Pharmaceutical compound testing; Cardiac contractility; In vitro screening; Cardiac tissue engineering
• ISSN: 1043-6618; 1096-1186; 1096-1186
• DOI: 10.1016/j.phrs.2024.107459

Cardiac screening of newly discovered drugs remains a longstanding challenge for the pharmaceutical industry. While therapeutic efficacy and cardiotoxicity are evaluated through preclinical biochemical and animal testing, 90 % of lead compounds fail to meet safety and efficacy benchmarks during human clinical trials. A preclinical model more representative of the human cardiac response is needed; heart tissue engineered from human pluripotent stem cell derived cardiomyocytes offers such a platform. In this study, three functionally distinct and independently validated engineered cardiac tissue assays are exposed to increasing concentrations of known compounds representing 5 classes of mechanistic action, creating a robust electrophysiology and contractility dataset. Combining results from six individual models, the resulting ensemble algorithm can classify the mechanistic action of unknown compounds with 86.2 % predictive accuracy. This outperforms single-assay models and offers a strategy to enhance future clinical trial success aligned with the recent FDA Modernization Act 2.0.
[Display omitted]