Dataset Information

Machine Learning of Human Pluripotent Stem Cell-Derived Engineered Cardiac Tissue Contractility for Automated Drug Classification.

ABSTRACT: Accurately predicting cardioactive effects of new molecular entities for therapeutics remains a daunting challenge. Immense research effort has been focused toward creating new screening platforms that utilize human pluripotent stem cell (hPSC)-derived cardiomyocytes and three-dimensional engineered cardiac tissue constructs to better recapitulate human heart function and drug responses. As these new platforms become increasingly sophisticated and high throughput, the drug screens result in larger multidimensional datasets. Improved automated analysis methods must therefore be developed in parallel to fully comprehend the cellular response across a multidimensional parameter space. Here, we describe the use of machine learning to comprehensively analyze 17 functional parameters derived from force readouts of hPSC-derived ventricular cardiac tissue strips (hvCTS) electrically paced at a range of frequencies and exposed to a library of compounds. A generated metric is effective for then determining the cardioactivity of a given drug. Furthermore, we demonstrate a classification model that can automatically predict the mechanistic action of an unknown cardioactive drug.

SUBMITTER: Lee EK

PROVIDER: S-EPMC5829317 | biostudies-literature | 2017 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning of Human Pluripotent Stem Cell-Derived Engineered Cardiac Tissue Contractility for Automated Drug Classification.

Lee Eugene K EK Tran David D DD Keung Wendy W Chan Patrick P Wong Gabriel G Chan Camie W CW Costa Kevin D KD Li Ronald A RA Khine Michelle M

Stem cell reports 20171012 5

Accurately predicting cardioactive effects of new molecular entities for therapeutics remains a daunting challenge. Immense research effort has been focused toward creating new screening platforms that utilize human pluripotent stem cell (hPSC)-derived cardiomyocytes and three-dimensional engineered cardiac tissue constructs to better recapitulate human heart function and drug responses. As these new platforms become increasingly sophisticated and high throughput, the drug screens result in larg ...[more]

PMID: 29033305

Similar Datasets

Project description:Introduction: Engineered heart tissues (EHTs) are three-dimensional culture platforms with cardiomyocytes differentiated from human pluripotent stem cells (hPSCs) and were designed for assaying cardiac contractility. For drug development applications, EHTs must have a stable function and provide reproducible results. We investigated these properties with EHTs made with different tissue casting batches and lines of differentiated hPSC-cardiomyocytes and analyzed them at different times after being fabricated. Methods: A video-optical assay was used for measuring EHT contractile outputs, and these results were compared with results from motion traction analysis of beating hPSC-cardiomyocytes cultured as monolayers in two-dimensional cultures. The reproducibility of induced contractile variations was tested using compounds with known mechanistic cardiac effects (isoproterenol, EMD-57033, omecamtiv mecarbil, verapamil, ranolazine, and mavacamten), or known to be clinically cardiotoxic (doxorubicin, sunitinib). These drug-induced variations were characterized at different electrical pacing rates and variations in intracellular calcium transients were also assessed in EHTs. Results: To ensure reproducibility in experiments, we established EHT quality control criteria based on excitation-contraction coupling and contractile sensitivity to extracellular calcium concentration. In summary, a baseline contractile force of 0.2 mN and excitation-contraction coupling of EHTs were used as quality control criteria to select suitable EHTs for analysis. Overall, drug-induced contractile responses were similar between monolayers and EHTs, where a close relationship was observed between contractile output and calcium kinetics. Contractile variations at multiple time points after adding cardiotoxic compounds were also detectable in EHTs. Discussion: Reproducibility of drug-induced effects in EHTs between experiments and relative to published work on these cellular models was generally observed. Future applications for EHTs may require additional mechanistic criteria related to drug effects and cardiac functional outputs to be measured in regard to specific contexts of use.

Project description:BackgroundFriedreich's ataxia (FRDA) is an autosomal recessive disease caused by a non-coding mutation in the first intron of the frataxin (FXN) gene that suppresses its expression. Compensatory hypertrophic cardiomyopathy, dilated cardiomyopathy, and conduction system abnormalities in FRDA lead to cardiomyocyte (CM) death and fibrosis, consequently resulting in heart failure and arrhythmias. Murine models have been developed to study disease pathology in the past two decades; however, differences between human and mouse physiology and metabolism have limited the relevance of animal studies in cardiac disease conditions. To bridge this gap, we aimed to generate species-specific, functional in vitro experimental models of FRDA using 2-dimensional (2D) and 3-dimensional (3D) engineered cardiac tissues from FXN-deficient human pluripotent stem cell-derived ventricular cardiomyocytes (hPSC-hvCMs) and to compare their contractile and electrophysiological properties with healthy tissue constructs.MethodsHealthy control and FRDA patient-specific hPSC-hvCMs were derived by directed differentiation using a small molecule-based protocol reported previously. We engineered the hvCMs into our established human ventricular cardiac tissue strip (hvCTS) and human ventricular cardiac anisotropic sheet (hvCAS) models, and functional assays were performed on days 7-17 post-tissue fabrication to assess the electrophysiology and contractility of FRDA patient-derived and FXN-knockdown engineered tissues, in comparison with healthy controls. To further validate the disease model, forced expression of FXN was induced in FXN-deficient tissues to test if disease phenotypes could be rescued.ResultsHere, we report for the first time the generation of human engineered tissue models of FRDA cardiomyopathy from hPSCs: FXN-deficient hvCTS displayed attenuated developed forces (by 70-80%) compared to healthy controls. High-resolution optical mapping of hvCAS with reduced FXN expression also revealed electrophysiological defects consistent with clinical observations, including action potential duration prolongation and maximum capture frequency reduction. Interestingly, a clear positive correlation between FXN expression and contractility was observed (ρ > 0.9), and restoration of FXN protein levels by lentiviral transduction rescued contractility defects in FXN-deficient hvCTS.ConclusionsWe conclude that human-based in vitro cardiac tissue models of FRDA provide a translational, disease-relevant biomimetic platform for the evaluation of novel therapeutics and to provide insight into FRDA disease progression.

Dataset Information

Machine Learning of Human Pluripotent Stem Cell-Derived Engineered Cardiac Tissue Contractility for Automated Drug Classification.

Publications

Machine Learning of Human Pluripotent Stem Cell-Derived Engineered Cardiac Tissue Contractility for Automated Drug Classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets