Related Experiment Video
Updated: Dec 15, 2025
Semi-automated Production of Hepatocyte Like Cells from Pluripotent Stem Cells
Published on: July 27, 2018
Quantifying drug-induced structural toxicity in hepatocytes and cardiomyocytes derived from hiPSCs using a deep
Mahnaz Maddah1, Mohammad A Mandegar2, Keri Dame3
1Dana Solutions, Palo Alto, CA, USA.
Abstract:
Cardiac and hepatic toxicity result from induced disruption of the functioning of cardiomyocytes and hepatocytes, respectively, which is tightly related to the organization of their subcellular structures. Cellular structure can be analyzed from microscopy imaging data. However, subtle or complex structural changes that are not easily perceived may be missed by conventional image-analysis techniques. Here we report the evaluation of PhenoTox, an image-based deep-learning method of quantifying drug-induced structural changes using human hepatocytes and cardiomyocytes derived from human induced pluripotent stem cells. We assessed the ability of the deep learning method to detect variations in the organization of cellular structures from images of fixed or live cells. We also evaluated the power and sensitivity of the method for detecting toxic effects of drugs by conducting a set of experiments using known toxicants and other methods of screening for cytotoxic effects. Moreover, we used PhenoTox to characterize the effects of tamoxifen and doxorubicin-which cause liver toxicity-on hepatocytes. PhenoTox revealed differences related to loss of cytochrome P450 3A4 activity, for which it showed greater sensitivity than a caspase 3/7 assay. Finally, PhenoTox detected structural toxicity in cardiomyocytes, which was correlated with contractility defects induced by doxorubicin, erlotinib, and sorafenib. Taken together, the results demonstrated that PhenoTox can capture the subtle morphological changes that are early signs of toxicity in both hepatocytes and cardiomyocytes.
Insights
PhenoTox, an image-based deep learning method, identifies subtle cellular structure changes indicative of drug toxicity in heart and liver cells. This advanced technique offers greater sensitivity for early toxicity detection compared to traditional assays.
Area of Science:
- Cardiovascular Biology
- Hepatology
- Toxicology
- Biotechnology
Background:
- Drug-induced cardiac and hepatic toxicity arise from disruptions in cardiomyocyte and hepatocyte function, linked to subcellular structural organization.
- Conventional image analysis may miss subtle or complex structural changes, hindering early toxicity detection.
- Human induced pluripotent stem cells (hiPSCs) offer a valuable model for studying cellular toxicity.
Purpose of the Study:
- To evaluate PhenoTox, an image-based deep learning method, for quantifying drug-induced structural changes in human hepatocytes and cardiomyocytes.
- To assess PhenoTox's ability to detect variations in cellular structure organization from microscopy images.
- To determine the sensitivity and power of PhenoTox in identifying drug-induced toxic effects.
Main Methods:
- Utilized human hepatocytes and cardiomyocytes derived from hiPSCs.
- Applied PhenoTox, an image-based deep learning approach, to analyze microscopy images of fixed and live cells.
- Conducted experiments with known toxicants and compared PhenoTox with other cytotoxic screening methods, including a caspase 3/7 assay.
Main Results:
- PhenoTox successfully detected variations in cellular structure organization.
- The method demonstrated higher sensitivity than a caspase 3/7 assay in detecting liver toxicity related to loss of cytochrome P450 3A4 activity caused by tamoxifen and doxorubicin.
- PhenoTox identified structural toxicity in cardiomyocytes, correlating with contractility defects induced by doxorubicin, erlotinib, and sorafenib.
Conclusions:
- PhenoTox effectively captures subtle morphological changes, serving as early indicators of toxicity in hepatocytes and cardiomyocytes.
- This deep learning method provides a sensitive and powerful tool for assessing drug-induced cellular toxicity.
- PhenoTox advances the field of predictive toxicology by enabling early detection of subtle structural alterations.
