2
|
Hussain F, Basu S, Heng JJH, Loo LH, Zink D. Predicting direct hepatocyte toxicity in humans by combining high-throughput imaging of HepaRG cells and machine learning-based phenotypic profiling. Arch Toxicol 2020; 94:2749-2767. [PMID: 32533217 DOI: 10.1007/s00204-020-02778-3] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2019] [Accepted: 05/05/2020] [Indexed: 02/07/2023]
Abstract
Accurate prediction of drug- and chemical-induced hepatotoxicity remains to be a problem for pharmaceutical companies as well as other industries and regulators. The goal of the current study was to develop an in vitro/in silico method for the rapid and accurate prediction of drug- and chemical-induced hepatocyte injury in humans. HepaRG cells were employed for high-throughput imaging in combination with phenotypic profiling. A reference set of 69 drugs and chemicals was screened at a range of 7 concentrations, and the cellular response values were used for training a supervised classifier and for determining assay performance by using tenfold cross-validation. The results showed that the best performing phenotypic features were related to nuclear translocation of RELA (RELA proto-oncogene, NF-kB subunit; also known as NF-kappa B p65), DNA organization, and the F-actin cytoskeleton. Using a subset of 30 phenotypic features, direct hepatocyte toxicity in humans could be predicted with a test sensitivity, specificity and balanced accuracy of 73%, 92%, and 83%, respectively. The method was applied to another set of 26 drugs and chemicals with unclear annotation and their hepatocyte toxicity in humans was predicted. The results also revealed that the identified discriminative phenotypic changes were related to cell death and cellular senescence. Whereas cell death-related endpoints are widely applied in in vitro toxicology, cellular senescence-related endpoints are not, although cellular senescence can be induced by various drugs and other small molecule compounds and plays an important role in liver injury and disease. These findings show how phenotypic profiling can reveal unexpected chemical-induced mechanisms in toxicology.
Collapse
Affiliation(s)
- Faezah Hussain
- NanoBio Lab and Institute of Bioengineering and Nanotechnology (IBN), 31 Biopolis Way, The Nanos, Singapore, 138669, Singapore
| | - Sreetama Basu
- Bioinformatics Institute, 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Singapore
| | - Javen Jun Hao Heng
- NanoBio Lab and Institute of Bioengineering and Nanotechnology (IBN), 31 Biopolis Way, The Nanos, Singapore, 138669, Singapore
| | - Lit-Hsin Loo
- Bioinformatics Institute, 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Singapore. .,Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, 16 Medical Drive, Singapore, 117600, Singapore.
| | - Daniele Zink
- NanoBio Lab and Institute of Bioengineering and Nanotechnology (IBN), 31 Biopolis Way, The Nanos, Singapore, 138669, Singapore.
| |
Collapse
|
3
|
Ramm S, Todorov P, Chandrasekaran V, Dohlman A, Monteiro MB, Pavkovic M, Muhlich J, Shankaran H, Chen WW, Mettetal JT, Vaidya VS. A Systems Toxicology Approach for the Prediction of Kidney Toxicity and Its Mechanisms In Vitro. Toxicol Sci 2020; 169:54-69. [PMID: 30649541 DOI: 10.1093/toxsci/kfz021] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
The failure to predict kidney toxicity of new chemical entities early in the development process before they reach humans remains a critical issue. Here, we used primary human kidney cells and applied a systems biology approach that combines multidimensional datasets and machine learning to identify biomarkers that not only predict nephrotoxic compounds but also provide hints toward their mechanism of toxicity. Gene expression and high-content imaging-derived phenotypical data from 46 diverse kidney toxicants were analyzed using Random Forest machine learning. Imaging features capturing changes in cell morphology and nucleus texture along with mRNA levels of HMOX1 and SQSTM1 were identified as the most powerful predictors of toxicity. These biomarkers were validated by their ability to accurately predict kidney toxicity of four out of six candidate therapeutics that exhibited toxicity only in late stage preclinical/clinical studies. Network analysis of similarities in toxic phenotypes was performed based on live-cell high-content image analysis at seven time points. Using compounds with known mechanism as reference, we could infer potential mechanisms of toxicity of candidate therapeutics. In summary, we report an approach to generate a multidimensional biomarker panel for mechanistic de-risking and prediction of kidney toxicity in in vitro for new therapeutic candidates and chemical entities.
Collapse
Affiliation(s)
- Susanne Ramm
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA.,Renal Division, Department of Medicine, Brigham and Women's Hospital, Boston, MA
| | - Petar Todorov
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA.,Safety and ADME Modeling, Drug Safety, and Metabolism, IMED Biotech Unit, AstraZeneca, Waltham MA
| | - Vidya Chandrasekaran
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA
| | - Anders Dohlman
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA
| | - Maria B Monteiro
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA
| | - Mira Pavkovic
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA.,Renal Division, Department of Medicine, Brigham and Women's Hospital, Boston, MA
| | - Jeremy Muhlich
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA
| | - Harish Shankaran
- Safety and ADME Modeling, Drug Safety, and Metabolism, IMED Biotech Unit, AstraZeneca, Waltham MA
| | - William W Chen
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA
| | - Jerome T Mettetal
- Safety and ADME Modeling, Drug Safety, and Metabolism, IMED Biotech Unit, AstraZeneca, Waltham MA
| | - Vishal S Vaidya
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Sciences, Harvard Medical SchoolBoston, MA.,Renal Division, Department of Medicine, Brigham and Women's Hospital, Boston, MA.,Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA
| |
Collapse
|
4
|
Fedecostante M, Westphal KGC, Buono MF, Sanchez Romero N, Wilmer MJ, Kerkering J, Baptista PM, Hoenderop JG, Masereeuw R. Recellularized Native Kidney Scaffolds as a Novel Tool in Nephrotoxicity Screening. Drug Metab Dispos 2018; 46:1338-1350. [PMID: 29980578 DOI: 10.1124/dmd.118.080721] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2018] [Accepted: 06/28/2018] [Indexed: 12/15/2022] Open
Abstract
Drug-induced kidney injury in medicinal compound development accounts for over 20% of clinical trial failures and involves damage to different nephron segments, mostly the proximal tubule. Yet, currently applied cell models fail to reliably predict nephrotoxicity; neither are such models easy to establish. Here, we developed a novel three-dimensional (3D) nephrotoxicity platform on the basis of decellularized rat kidney scaffolds (DS) recellularized with conditionally immortalized human renal proximal tubule epithelial cells overexpressing the organic anion transporter 1 (ciPTEC-OAT1). A 5-day SDS-based decellularization protocol was used to generate DS, of which 100-μm slices were cut and used for cell seeding. After 8 days of culturing, recellularized scaffolds (RS) demonstrated 3D-tubule formation along with tubular epithelial characteristics, including drug transporter function. Exposure of RS to cisplatin (CDDP), tenofovir (TFV), or cyclosporin A (CsA) as prototypical nephrotoxic drugs revealed concentration-dependent reduction in cell viability, as assessed by PrestoBlue and Live/Dead staining assays. This was most probably attributable to specific uptake of CDDP by the organic cation transporter 2 (OCT2), TFV through organic anion transporter 1 (OAT1), and CsA competing for P-glycoprotein-mediated efflux. Compared with 2D cultures, RS showed an increased sensitivity to cisplatin and tenofovir toxicity after 24-hour exposure (9 and 2.2 fold, respectively). In conclusion, we developed a physiologically relevant 3D nephrotoxicity screening platform that could be a novel tool in drug development.
Collapse
Affiliation(s)
- Michele Fedecostante
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Koen G C Westphal
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Michele F Buono
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Natalia Sanchez Romero
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Martijn J Wilmer
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Janis Kerkering
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Pedro Miguel Baptista
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Joost G Hoenderop
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| | - Rosalinde Masereeuw
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht, The Netherlands (M.F., K.G.C.W., M.F.B., N.S.R., R.M.); Aragon's Health Science Institutes (IACS), Zaragoza, Spain (N.S.M.); Departments of Pharmacology and Toxicology (M.J.W., J.K.) and Physiology (J.G.H.), Radboud Institute for Molecular Life Sciences, Radboud university medical center, Nijmegen, The Netherlands; Aragon Health Research Institute (IIS Aragon), Zaragoza, Spain (P.M.B.); Liver and Digestive Diseases Networking Biomedical Research Centre (CIBERehd), Madrid, Spain (P.M.B.); Jiménez Díaz Foundation Health Research Institute, Madrid, Spain (P.M.B.); and Department of Biomedical and Aerospace Engineering, Carlos III University of Madrid, Spain (P.M.B.)
| |
Collapse
|
5
|
Lee JYJ, Miller JA, Basu S, Kee TZV, Loo LH. Building predictive in vitro pulmonary toxicity assays using high-throughput imaging and artificial intelligence. Arch Toxicol 2018; 92:2055-2075. [PMID: 29705884 PMCID: PMC6002469 DOI: 10.1007/s00204-018-2213-0] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2018] [Accepted: 04/25/2018] [Indexed: 01/22/2023]
Abstract
Human lungs are susceptible to the toxicity induced by soluble xenobiotics. However, the direct cellular effects of many pulmonotoxic chemicals are not always clear, and thus, a general in vitro assay for testing pulmonotoxicity applicable to a wide variety of chemicals is not currently available. Here, we report a study that uses high-throughput imaging and artificial intelligence to build an in vitro pulmonotoxicity assay by automatically comparing and selecting human lung-cell lines and their associated quantitative phenotypic features most predictive of in vivo pulmonotoxicity. This approach is called “High-throughput In vitro Phenotypic Profiling for Toxicity Prediction” (HIPPTox). We found that the resulting assay based on two phenotypic features of a human bronchial epithelial cell line, BEAS-2B, can accurately classify 33 reference chemicals with human pulmonotoxicity information (88.8% balance accuracy, 84.6% sensitivity, and 93.0% specificity). In comparison, the predictivity of a standard cell-viability assay on the same set of chemicals is much lower (77.1% balanced accuracy, 84.6% sensitivity, and 69.5% specificity). We also used the assay to evaluate 17 additional test chemicals with unknown/unclear human pulmonotoxicity, and experimentally confirmed that many of the pulmonotoxic reference and predicted-positive test chemicals induce DNA strand breaks and/or activation of the DNA-damage response (DDR) pathway. Therefore, HIPPTox helps us to uncover these common modes-of-action of pulmonotoxic chemicals. HIPPTox may also be applied to other cell types or models, and accelerate the development of predictive in vitro assays for other cell-type- or organ-specific toxicities.
Collapse
Affiliation(s)
- Jia-Ying Joey Lee
- Bioinformatics Institute, Agency for Science, Technology, and Research, 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Singapore
| | - James Alastair Miller
- Bioinformatics Institute, Agency for Science, Technology, and Research, 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Singapore
| | - Sreetama Basu
- Bioinformatics Institute, Agency for Science, Technology, and Research, 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Singapore
| | - Ting-Zhen Vanessa Kee
- Bioinformatics Institute, Agency for Science, Technology, and Research, 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Singapore
| | - Lit-Hsin Loo
- Bioinformatics Institute, Agency for Science, Technology, and Research, 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Singapore.
| |
Collapse
|