Quantifying drug-induced structural toxicity in hepatocytes and cardiomyocytes derived from hiPSCs using a deep learning method

Maddah, Mahnaz; Mandegar, Mohammad A.; Dame, Keri; Grafton, Francis; Loewke, Kevin; Ribeiro, Alexandre J. S.

doi:10.1016/j.vascn.2020.106895

Cited by 25 publications

(26 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Images from the DMSO control group were trained against the toxic groups (defined as either mildly toxic, toxic, or highly toxic). Each input image was divided into 12 square sub-images to have sizes ranging from 224 x 224 to 300 x 300 pixels (Maddah et al, 2020). Each sub-image was flipped and rotated to create seven more augmented sub-images, and then fed into the input layer of ResNet50.…”

Section: Methodsmentioning

confidence: 99%

“…Cells derived from iPSCs more closely recapitulate human biology than immortalized cells (Moffat et al, 2017; Scannell and Bosley, 2016). These derived cells have been used for disease modeling (Judge et al, 2017; Lan et al, 2013; Pérez-Bermejo et al, 2020; Ribeiro et al, 2017; Sharma et al, 2017; Sun et al, 2012), proposed for drug discovery (Carlson et al, 2013; Grskovic et al, 2011; Robinton and Daley, 2012), and used to assess arrhythmogenic and structural liabilities of drugs (Guo et al, 2011; Maddah et al, 2020). Additionally, iPSCs can be derived from patients carrying deleterious mutations and genetically modified using nucleases (Judge et al, 2017; Kime et al, 2016; Mandegar et al, 2016; Miyaoka et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

“…For example, deep learning, a branch of artificial intelligence, uses a set of machine-learning techniques to train neural networks and learn input data (LeCun et al, 2015). Previously, we used phenotypic interrogation with deep learning to identify drug-induced structural toxicity in hepatocytes and cardiomyocytes (Maddah et al, 2020). Herein, we aimed to expand that work to iPSC-CMs in a high-content screen (HCS) of 1280 bioactive compounds with putative primary targets.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Predicts Patterns of Cardiotoxicity in a High-Content Screen Using Induced Pluripotent Stem Cell–Derived Cardiomyocytes

Grafton¹,

J²,

Ranjbarvaziri

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Drug-induced cardiotoxicity and hepatotoxicity are major causes of drug attrition. To decrease late-stage drug attrition, pharmaceutical and biotechnology industries need to establish biologically relevant models that use phenotypic screening to predict drug-induced toxicity. In this study, we sought to rapidly detect patterns of cardiotoxicity using high-content image analysis with deep learning and induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs). We screened a library of 1280 bioactive compounds and identified those predicted to have cardiotoxic liabilities using a single-parameter score based on deep learning. Compounds with major predicted cardiotoxicity included DNA intercalators, ion channel blockers, epidermal growth factor receptor, cyclin-dependent kinase, and multi-kinase inhibitors. We also screened a diverse library of molecules with unknown targets and identified chemical frameworks with predicted cardiotoxic liabilities. By using this screening approach during target discovery and lead optimization, we can de-risk early-stage drug discovery. We show that the broad applicability of combining deep learning with iPSC technology is an effective way to interrogate cellular phenotypes and identify drugs that protect against diseased phenotypes and deleterious mutations.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Predicts Patterns of Cardiotoxicity in a High-Content Screen Using Induced Pluripotent Stem Cell–Derived Cardiomyocytes

Grafton¹,

J²,

Ranjbarvaziri

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Cells derived from iPSCs more closely recapitulate human biology than immortalized cells ( Moffat et al, 2017 ; Scannell and Bosley, 2016 ). These derived cells have been used for disease modeling ( Judge et al, 2017 ; Lan et al, 2013 ; Pérez-Bermejo et al, 2020 ; Ribeiro et al, 2017 ; Sharma et al, 2017 ; Sun et al, 2012 ), proposed for drug discovery ( Carlson et al, 2013 ; Grskovic et al, 2011 ; Robinton and Daley, 2012 ), and used to assess arrhythmogenic and structural liabilities of drugs ( Guo et al, 2011 ; Maddah et al, 2020 ). Additionally, iPSCs can be derived from patients carrying deleterious mutations and genetically modified using nucleases ( Judge et al, 2017 ; Kime et al, 2016 ; Mandegar et al, 2016 ; Miyaoka et al, 2012 ).…”

Section: Introductionmentioning

confidence: 99%

“…For example, deep learning, a branch of artificial intelligence, uses a set of machine-learning techniques to train neural networks and learn input data ( LeCun et al, 2015 ). Previously, we used phenotypic interrogation with deep learning to identify drug-induced structural toxicity in hepatocytes and cardiomyocytes ( Maddah et al, 2020 ). Herein, we aimed to expand that work to induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) in a high-content screen (HCS) of 1280 bioactive compounds with putative primary targets.…”

Section: Introductionmentioning

confidence: 99%

Deep learning detects cardiotoxicity in a high-content screen with induced pluripotent stem cell-derived cardiomyocytes

Grafton¹,

Ho²,

Ranjbarvaziri

et al. 2021

eLife

Self Cite

View full text Add to dashboard Cite

Drug-induced cardiotoxicity and hepatotoxicity are major causes of drug attrition. To decrease late-stage drug attrition, pharmaceutical and biotechnology industries need to establish biologically relevant models that use phenotypic screening to detect drug-induced toxicity in vitro. In this study, we sought to rapidly detect patterns of cardiotoxicity using high-content image analysis with deep learning and induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs). We screened a library of 1280 bioactive compounds and identified those with potential cardiotoxic liabilities in iPSC-CMs using a single-parameter score based on deep learning. Compounds demonstrating cardiotoxicity in iPSC-CMs included DNA intercalators, ion channel blockers, epidermal growth factor receptor, cyclin-dependent kinase, and multi-kinase inhibitors. We also screened a diverse library of molecules with unknown targets and identified chemical frameworks that show cardiotoxic signal in iPSC-CMs. By using this screening approach during target discovery and lead optimization, we can de-risk early-stage drug discovery. We show that the broad applicability of combining deep learning with iPSC technology is an effective way to interrogate cellular phenotypes and identify drugs that may protect against diseased phenotypes and deleterious mutations.

show abstract

Human‐Based In Vitro Experimental Approaches for the Evaluation of Metabolism‐Dependent Drug Toxicity

2021

Transporters and Drug‐Metabolizing Enzymes in Drug Toxicity

View full text Add to dashboard Cite

Quantifying drug-induced structural toxicity in hepatocytes and cardiomyocytes derived from hiPSCs using a deep learning method

Cited by 25 publications

References 79 publications

Deep Learning Predicts Patterns of Cardiotoxicity in a High-Content Screen Using Induced Pluripotent Stem Cell–Derived Cardiomyocytes

Deep Learning Predicts Patterns of Cardiotoxicity in a High-Content Screen Using Induced Pluripotent Stem Cell–Derived Cardiomyocytes

Deep learning detects cardiotoxicity in a high-content screen with induced pluripotent stem cell-derived cardiomyocytes

Human‐Based In Vitro Experimental Approaches for the Evaluation of Metabolism‐Dependent Drug Toxicity

Contact Info

Product

Resources

About