Building predictive in vitro pulmonary toxicity assays using high-throughput imaging and artificial intelligence
Lee, J.-Y.J Miller, J.A Basu, S Kee, T.-Z.V Loo, L.-H
Lee, J.-Y.J
Miller, J.A
Basu, S
Kee, T.-Z.V
Citations
Altmetric:
Alternative Title
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. © 2018, The Author(s).
Keywords
amiodarone, aristolochic acid, bleomycin, butylcresol, cadmium chloride, carbamazepine, DNA, doxorubicin, lithium chloride, myrcene, nitrofurantoin, nystatin, ochratoxin, paraquat, patulin, phalloidin, phenylenediamine, skatole, tenofovir, xenobiotic agent, Article, artificial intelligence, automation, BEAS-2B cell line, cell viability assay, chemical structure, controlled study, diagnostic accuracy, diagnostic test accuracy study, DNA damage response, DNA strand breakage, HBEC cell line (bronchial epithelium), high throughput in vitro phenotypic profiling for toxicity prediction, high throughput screening, human, human cell, in vitro study, in vivo study, lung cell line, lung toxicity, phenotype, predictive value, priority journal, sensitivity and specificity, A-549 cell line, bronchus, cell line, cell survival, chemistry, drug effect, high throughput screening, lung, pathology, procedures, toxicity testing, A549 Cells, Artificial Intelligence, Bronchi, Cell Line, Cell Survival, High-Throughput Screening Assays, Humans, Lung, Predictive Value of Tests, Sensitivity and Specificity, Toxicity Tests, Xenobiotics
Source Title
Archives of Toxicology
Publisher
Springer Verlag
Series/Report No.
Collections
Rights
Attribution 4.0 International
Date
2018
DOI
10.1007/s00204-018-2213-0
Type
Article