Machine learning plus optical flow: a simple and sensitive method to detect cardioactive drugs
Machine learning plus optical flow: a simple and sensitive method to detect cardioactive drugs
复制标题
DOI：
10.1038/srep11817
复制
发表时间：
2015-07-03
影响因子：
4.6
通讯作者：
Khine, Michelle
中科院分区：
文献类型：
--
作者：
Lee, Eugene K.;Kurokawa, Yosuke K.;Khine, Michelle
目前的临床前筛查方法不能充分检测心脏毒性。使用人诱导多能干细胞来源的心肌细胞(iPS-CMS)，可能会有更多生理上相关的临床前或患者特异性筛选，以检测候选药物的潜在心脏毒性作用。然而，使用iPS-CMS开发高通量药物筛选平台的长期挑战之一是需要开发一种简单可靠的方法来测量关键的电生理和收缩参数。为了满足这一需求，我们开发了一个结合了机器学习和Brightfield光流的平台，作为一种简单而强大的工具，可以自动检测心肌细胞药物的效果。使用三种不同机制的心脏活性药物，包括那些主要具有电生理效应的药物，我们证明了这种筛选方法在检测心肌细胞收缩的细微变化方面的普遍适用性。只需要心肌细胞收缩的明场图像，我们就可以检测到与荧光读数相当甚至更好的心肌细胞收缩变化。这种自动化的方法是一种广泛应用的筛选工具，可以用来表征药物对心肌细胞功能的影响。
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.