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

Eugene K. Lee, David D. Tran, Wendy Keung, Patrick Chan, Gabriel Wong, Camie W. Chan, Kevin D. Costa, Ronald A. Li, Michelle Khine

Research output: Contribution to journalArticlepeer-review

49 Scopus citations

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. Analysis methods must be improved in parallel with advancements in drug screening platforms. Machine learning principles are used here to analyze multidimensional datasets to determine cardioactivity of unknown drugs. Furthermore, this study describes the use of multiclassification algorithms to classify unknown drugs based on their mechanistic action and compare their potency with related drugs.

Original languageEnglish
Pages (from-to)1560-1572
Number of pages13
JournalStem Cell Reports
Volume9
Issue number5
DOIs
StatePublished - 14 Nov 2017

Keywords

  • drug classification library
  • drug-induced cardiotoxicity
  • human engineered cardiac tissue
  • human pluripotent stem cell-derived cardiomyocytes
  • machine learning

Fingerprint

Dive into the research topics of 'Machine Learning of Human Pluripotent Stem Cell-Derived Engineered Cardiac Tissue Contractility for Automated Drug Classification'. Together they form a unique fingerprint.

Cite this