Machine learning plus optical flow: A simple and sensitive method to detect cardioactive drugs

Eugene K. Lee, Yosuke K. Kurokawa, Robin Tu, Steven George, Michelle Khine

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Current preclinical screening methods do not adequately detect cardiotoxicity. Using human induced pluripotent stem cell-derived cardiomyocytes (iPS-CMs), more physiologically relevant preclinical or patient-specific screening to detect potential cardiotoxic effects of drug candidates may be possible. However, one of the persistent challenges for developing a high-throughput drug screening platform using iPS-CMs is the need to develop a simple and reliable method to measure key electrophysiological and contractile parameters. To address this need, we have developed a platform that combines machine learning paired with brightfield optical flow as a simple and robust tool that can automate the detection of cardiomyocyte drug effects. Using three cardioactive drugs of different mechanisms, including those with primarily electrophysiological effects, we demonstrate the general applicability of this screening method to detect subtle changes in cardiomyocyte contraction. Requiring only brightfield images of cardiomyocyte contractions, we detect changes in cardiomyocyte contraction comparable to - and even superior to - fluorescence readouts. This automated method serves as a widely applicable screening tool to characterize the effects of drugs on cardiomyocyte function.

Original languageEnglish (US)
Article number11817
JournalScientific Reports
Volume5
DOIs
StatePublished - Jul 3 2015
Externally publishedYes

Fingerprint

Cardiac Myocytes
Pharmaceutical Preparations
Induced Pluripotent Stem Cells
Preclinical Drug Evaluations
Machine Learning
Fluorescence

ASJC Scopus subject areas

  • General

Cite this

Machine learning plus optical flow : A simple and sensitive method to detect cardioactive drugs. / Lee, Eugene K.; Kurokawa, Yosuke K.; Tu, Robin; George, Steven; Khine, Michelle.

In: Scientific Reports, Vol. 5, 11817, 03.07.2015.

Research output: Contribution to journalArticle

Lee, Eugene K. ; Kurokawa, Yosuke K. ; Tu, Robin ; George, Steven ; Khine, Michelle. / Machine learning plus optical flow : A simple and sensitive method to detect cardioactive drugs. In: Scientific Reports. 2015 ; Vol. 5.
@article{c841c44ebcc24ad58547710b190d91ef,
title = "Machine learning plus optical flow: A simple and sensitive method to detect cardioactive drugs",
abstract = "Current preclinical screening methods do not adequately detect cardiotoxicity. Using human induced pluripotent stem cell-derived cardiomyocytes (iPS-CMs), more physiologically relevant preclinical or patient-specific screening to detect potential cardiotoxic effects of drug candidates may be possible. However, one of the persistent challenges for developing a high-throughput drug screening platform using iPS-CMs is the need to develop a simple and reliable method to measure key electrophysiological and contractile parameters. To address this need, we have developed a platform that combines machine learning paired with brightfield optical flow as a simple and robust tool that can automate the detection of cardiomyocyte drug effects. Using three cardioactive drugs of different mechanisms, including those with primarily electrophysiological effects, we demonstrate the general applicability of this screening method to detect subtle changes in cardiomyocyte contraction. Requiring only brightfield images of cardiomyocyte contractions, we detect changes in cardiomyocyte contraction comparable to - and even superior to - fluorescence readouts. This automated method serves as a widely applicable screening tool to characterize the effects of drugs on cardiomyocyte function.",
author = "Lee, {Eugene K.} and Kurokawa, {Yosuke K.} and Robin Tu and Steven George and Michelle Khine",
year = "2015",
month = "7",
day = "3",
doi = "10.1038/srep11817",
language = "English (US)",
volume = "5",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Machine learning plus optical flow

T2 - A simple and sensitive method to detect cardioactive drugs

AU - Lee, Eugene K.

AU - Kurokawa, Yosuke K.

AU - Tu, Robin

AU - George, Steven

AU - Khine, Michelle

PY - 2015/7/3

Y1 - 2015/7/3

N2 - Current preclinical screening methods do not adequately detect cardiotoxicity. Using human induced pluripotent stem cell-derived cardiomyocytes (iPS-CMs), more physiologically relevant preclinical or patient-specific screening to detect potential cardiotoxic effects of drug candidates may be possible. However, one of the persistent challenges for developing a high-throughput drug screening platform using iPS-CMs is the need to develop a simple and reliable method to measure key electrophysiological and contractile parameters. To address this need, we have developed a platform that combines machine learning paired with brightfield optical flow as a simple and robust tool that can automate the detection of cardiomyocyte drug effects. Using three cardioactive drugs of different mechanisms, including those with primarily electrophysiological effects, we demonstrate the general applicability of this screening method to detect subtle changes in cardiomyocyte contraction. Requiring only brightfield images of cardiomyocyte contractions, we detect changes in cardiomyocyte contraction comparable to - and even superior to - fluorescence readouts. This automated method serves as a widely applicable screening tool to characterize the effects of drugs on cardiomyocyte function.

AB - Current preclinical screening methods do not adequately detect cardiotoxicity. Using human induced pluripotent stem cell-derived cardiomyocytes (iPS-CMs), more physiologically relevant preclinical or patient-specific screening to detect potential cardiotoxic effects of drug candidates may be possible. However, one of the persistent challenges for developing a high-throughput drug screening platform using iPS-CMs is the need to develop a simple and reliable method to measure key electrophysiological and contractile parameters. To address this need, we have developed a platform that combines machine learning paired with brightfield optical flow as a simple and robust tool that can automate the detection of cardiomyocyte drug effects. Using three cardioactive drugs of different mechanisms, including those with primarily electrophysiological effects, we demonstrate the general applicability of this screening method to detect subtle changes in cardiomyocyte contraction. Requiring only brightfield images of cardiomyocyte contractions, we detect changes in cardiomyocyte contraction comparable to - and even superior to - fluorescence readouts. This automated method serves as a widely applicable screening tool to characterize the effects of drugs on cardiomyocyte function.

UR - http://www.scopus.com/inward/record.url?scp=84953888876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953888876&partnerID=8YFLogxK

U2 - 10.1038/srep11817

DO - 10.1038/srep11817

M3 - Article

C2 - 26139150

AN - SCOPUS:84953888876

VL - 5

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 11817

ER -