{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T07:11:12Z","timestamp":1791529872207,"version":"4.3.4"},"posted":{"date-parts":[[2025,1,24]]},"group-title":"Pharmacology and Toxicology","reference-count":70,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T00:00:00Z","timestamp":1737676800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,1,24]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>High-throughput, human-relevant approaches for predicting chemical toxicity are urgently needed for better decision-making in human health. Here, we apply image-based profiling (the Cell Painting assay) and two cytotoxicity assays (metabolic and membrane damage readouts) to primary human hepatocytes after exposure to eight concentrations of 1085 compounds that include pharmaceuticals, pesticides, and industrial chemicals with known liver toxicity-related outcomes. Three computational methods (CellProfiler, a Cell Painting-specific convolutional neural network, and a pretrained vision transformer) were compared to extract morphology features from single cells or entire images. We used these morphology features to predict activity in the measured cytotoxicity assays, as well as in 412 curated ToxCast assays that span cytotoxicity, cell-based, and cell-free categories. We found that the morphological profiles detect compound bioactivity at lower concentrations than standard cytotoxicity assays. In supervised analyses, they predict cytotoxicity and targeted cell-based assay readouts, but not cell-free assay readouts. We also found that the various feature extraction methods performed relatively similarly and that filtering out non-bioactive or cytotoxic concentrations did not boost supervised assay prediction performance for any assay endpoint category, although it did have a large influence on unsupervised cluster analysis. We envision that image-based profiling could serve as a key component of modern safety assessment.<\/jats:p>","DOI":"10.1101\/2025.01.22.634152","type":"posted-content","created":{"date-parts":[[2025,1,25]],"date-time":"2025-01-25T00:30:17Z","timestamp":1737765017000},"source":"Crossref","is-referenced-by-count":14,"title":["Cell Painting for cytotoxicity and mode-of-action analysis in primary human hepatocytes"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7555-736X","authenticated-orcid":false,"given":"Jessica D.","family":"Ewald","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine L.","family":"Titterton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"B\u00e4uerle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Beatson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniil A.","family":"Boiko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c1ngel A.","family":"Cabrera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaime","family":"Cheah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9640-9318","authenticated-orcid":false,"given":"Beth A.","family":"Cimini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bram","family":"Gorissen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6584-9660","authenticated-orcid":false,"given":"Thouis","family":"Jones","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konrad J.","family":"Karczewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rouquie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2790-8679","authenticated-orcid":false,"given":"Srijit","family":"Seal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6437-2458","authenticated-orcid":false,"given":"Erin","family":"Weisbart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brandon","family":"White","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1555-8261","authenticated-orcid":false,"given":"Anne E.","family":"Carpenter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3150-3025","authenticated-orcid":false,"given":"Shantanu","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025012805350421000_2025.01.22.634152v1.1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.est.9b06379"},{"key":"2025012805350421000_2025.01.22.634152v1.2","unstructured":"Ewart, L. et al. Performance assessment and economic analysis of a human Liver-Chip for predictive toxicology. Commun. Med. 2, 154 (2022)."},{"key":"2025012805350421000_2025.01.22.634152v1.3","doi-asserted-by":"publisher","DOI":"10.1080\/10937404.2010.483176"},{"key":"2025012805350421000_2025.01.22.634152v1.4","first-page":"317","article-title":"The Next Generation Blueprint of Computational Toxicology at the U","volume":"169","year":"2019","journal-title":"S. Environmental Protection Agency. Toxicol. Sci"},{"key":"2025012805350421000_2025.01.22.634152v1.5","doi-asserted-by":"crossref","unstructured":"Gilmour, N. et al. Development of a next generation risk assessment framework for the evaluation of skin sensitisation of cosmetic ingredients. Regul. Toxicol. Pharmacol. 116, 104721 (2020).","DOI":"10.1016\/j.yrtph.2020.104721"},{"key":"2025012805350421000_2025.01.22.634152v1.6","doi-asserted-by":"crossref","unstructured":"Fortin, A.-M. V. et al. Application of a new approach methodology (NAM)-based strategy for genotoxicity assessment of data-poor compounds. Front. Toxicol. 5, 1098432 (2023).","DOI":"10.3389\/ftox.2023.1098432"},{"key":"2025012805350421000_2025.01.22.634152v1.7","doi-asserted-by":"publisher","DOI":"10.1002\/etc.34"},{"key":"2025012805350421000_2025.01.22.634152v1.8","doi-asserted-by":"publisher","DOI":"10.1093\/toxsci\/kfu199"},{"key":"2025012805350421000_2025.01.22.634152v1.9","first-page":"163","article-title":"The US Federal Tox21 Program: A strategic and operational plan for continued leadership","volume":"35","year":"2018","journal-title":"ALTEX"},{"key":"2025012805350421000_2025.01.22.634152v1.10","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrestox.6b00135"},{"key":"2025012805350421000_2025.01.22.634152v1.11","doi-asserted-by":"crossref","unstructured":"Feshuk, M. et al. The ToxCast pipeline: updates to curve-fitting approaches and database structure. Front. Toxicol. 5, 1275980 (2023).","DOI":"10.3389\/ftox.2023.1275980"},{"key":"2025012805350421000_2025.01.22.634152v1.12","doi-asserted-by":"crossref","unstructured":"Seal, S. et al. Cell Painting: a decade of discovery and innovation in cellular imaging. Nat. Methods 1\u201315 (2024).","DOI":"10.1038\/s41592-024-02528-8"},{"key":"2025012805350421000_2025.01.22.634152v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/nprot.2016.105"},{"key":"2025012805350421000_2025.01.22.634152v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36829-x"},{"key":"2025012805350421000_2025.01.22.634152v1.15","doi-asserted-by":"crossref","unstructured":"Nyffeler, J. et al. Combining phenotypic profiling and targeted RNA-Seq reveals linkages between transcriptional perturbations and chemical effects on cell morphology: Retinoic acid as an example. Toxicol. Appl. Pharmacol. 444, 116032 (2022).","DOI":"10.1016\/j.taap.2022.116032"},{"key":"2025012805350421000_2025.01.22.634152v1.16","doi-asserted-by":"crossref","unstructured":"Bundy, J. L. et al. High-Throughput Transcriptomics screen of ToxCast chemicals in U-2 OS cells. Toxicol. Appl. Pharmacol. 491, 117073 (2024).","DOI":"10.1016\/j.taap.2024.117073"},{"key":"2025012805350421000_2025.01.22.634152v1.17","doi-asserted-by":"publisher","DOI":"10.1093\/toxsci\/kfae108"},{"key":"2025012805350421000_2025.01.22.634152v1.18","doi-asserted-by":"publisher","DOI":"10.1177\/2472555220950245"},{"key":"2025012805350421000_2025.01.22.634152v1.19","doi-asserted-by":"publisher","DOI":"10.22427\/NTP-RR-5"},{"key":"2025012805350421000_2025.01.22.634152v1.20","doi-asserted-by":"crossref","unstructured":"O\u2019Brien, J. et al. Bioinformatic workflows for deriving transcriptomic points of departure: Current status, data gaps, and research priorities. Toxicol. Sci. kfa e145 (2024).","DOI":"10.1093\/toxsci\/kfae145"},{"key":"2025012805350421000_2025.01.22.634152v1.21","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrestox.0c00303"},{"key":"2025012805350421000_2025.01.22.634152v1.22","doi-asserted-by":"crossref","unstructured":"Bundy, J. L. et al. Predicting molecular initiating events using chemical target annotations and gene expression. BioData Min. 15, 7 (2022).","DOI":"10.1186\/s13040-022-00292-z"},{"key":"2025012805350421000_2025.01.22.634152v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37570-1"},{"key":"2025012805350421000_2025.01.22.634152v1.24","doi-asserted-by":"publisher","DOI":"10.1091\/mbc.E20-12-0784"},{"key":"2025012805350421000_2025.01.22.634152v1.25","doi-asserted-by":"publisher","DOI":"10.1101\/pdb.prot095497"},{"key":"2025012805350421000_2025.01.22.634152v1.26","first-page":"69","article-title":"The MTT assay to evaluate chemosensitivity","volume":"110","year":"2005","journal-title":"Methods Mol. Med"},{"key":"2025012805350421000_2025.01.22.634152v1.27","doi-asserted-by":"crossref","unstructured":"Stirling, D. R. et al. CellProfiler 4: improvements in speed, utility and usability. BMC Bioinformatics 22, 433 (2021).","DOI":"10.1186\/s12859-021-04344-9"},{"key":"2025012805350421000_2025.01.22.634152v1.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45999-1"},{"key":"2025012805350421000_2025.01.22.634152v1.29","unstructured":"Oquab, M. , et al. DINOv2: Learning robust visual features without supervision. arXiv [cs.CV] (2023)."},{"key":"2025012805350421000_2025.01.22.634152v1.30","doi-asserted-by":"publisher","DOI":"10.1517\/14740338.4.1.69"},{"key":"2025012805350421000_2025.01.22.634152v1.31","doi-asserted-by":"publisher","DOI":"10.1002\/hep.20634"},{"key":"2025012805350421000_2025.01.22.634152v1.32","doi-asserted-by":"publisher","DOI":"10.1210\/jc.82.7.2153"},{"key":"2025012805350421000_2025.01.22.634152v1.33","doi-asserted-by":"publisher","DOI":"10.1042\/bj2260183"},{"key":"2025012805350421000_2025.01.22.634152v1.34","doi-asserted-by":"crossref","unstructured":"Williams, A. J. et al. The CompTox Chemistry Dashboard: a community data resource for environmental chemistry. J. Cheminform. 9, 61 (2017).","DOI":"10.1186\/s13321-017-0247-6"},{"key":"2025012805350421000_2025.01.22.634152v1.35","doi-asserted-by":"publisher","DOI":"10.1007\/s00204-017-2068-9"},{"key":"2025012805350421000_2025.01.22.634152v1.36","doi-asserted-by":"publisher","DOI":"10.1093\/toxsci\/kfab009"},{"key":"2025012805350421000_2025.01.22.634152v1.37","doi-asserted-by":"publisher","DOI":"10.1038\/2221076a0"},{"key":"2025012805350421000_2025.01.22.634152v1.38","doi-asserted-by":"publisher","DOI":"10.1101\/2024.12.02.624527"},{"key":"2025012805350421000_2025.01.22.634152v1.39","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50613-5"},{"key":"2025012805350421000_2025.01.22.634152v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/j.phrs.2011.06.020"},{"key":"2025012805350421000_2025.01.22.634152v1.41","doi-asserted-by":"publisher","DOI":"10.1517\/17425255.2013.816283"},{"key":"2025012805350421000_2025.01.22.634152v1.42","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0128708"},{"key":"2025012805350421000_2025.01.22.634152v1.43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2014.02.014"},{"key":"2025012805350421000_2025.01.22.634152v1.44","doi-asserted-by":"publisher","DOI":"10.1038\/s41589-020-0472-6"},{"key":"2025012805350421000_2025.01.22.634152v1.45","doi-asserted-by":"publisher","DOI":"10.3390\/ijms25147544"},{"key":"2025012805350421000_2025.01.22.634152v1.46","doi-asserted-by":"publisher","DOI":"10.1021\/tx700326b"},{"key":"2025012805350421000_2025.01.22.634152v1.47","doi-asserted-by":"crossref","unstructured":"Ghasemi, M. , Turnbull, T. , Sebastian, S. & Kempson, I . The MTT assay: Utility, limitations, pitfalls, and interpretation in bulk and single-cell analysis. Int. J. Mol. Sci. 22, 12827 (2021).","DOI":"10.3390\/ijms222312827"},{"key":"2025012805350421000_2025.01.22.634152v1.48","doi-asserted-by":"publisher","DOI":"10.1038\/s41570-022-00391-9"},{"key":"2025012805350421000_2025.01.22.634152v1.49","doi-asserted-by":"crossref","unstructured":"Nyffeler, J. et al. Application of Cell Painting for chemical hazard evaluation in support of screening-level chemical assessments. Toxicol. Appl. Pharmacol. 468, 116513 (2023).","DOI":"10.1016\/j.taap.2023.116513"},{"key":"2025012805350421000_2025.01.22.634152v1.50","doi-asserted-by":"crossref","unstructured":"Kraus, O. , et al. Masked autoencoders for microscopy are scalable learners of cellular biology. arXiv [cs.CV] (2024).","DOI":"10.1109\/CVPR52733.2024.01117"},{"key":"2025012805350421000_2025.01.22.634152v1.51","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1012463"},{"key":"2025012805350421000_2025.01.22.634152v1.52","doi-asserted-by":"publisher","DOI":"10.1091\/mbc.E21-11-0538"},{"key":"2025012805350421000_2025.01.22.634152v1.53","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1012547"},{"key":"2025012805350421000_2025.01.22.634152v1.54","doi-asserted-by":"publisher","DOI":"10.1021\/es501955g"},{"key":"2025012805350421000_2025.01.22.634152v1.55","doi-asserted-by":"crossref","unstructured":"Armitage, J. M. , Sangion, A. , Parmar, R. , Looky, A. B. & Arnot, J. A . Update and Evaluation of a High-Throughput In Vitro Mass Balance Distribution Model: IV-MBM EQP v2.0. Toxics 9, (2021).","DOI":"10.3390\/toxics9110315"},{"key":"2025012805350421000_2025.01.22.634152v1.56","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2016.02.015"},{"key":"2025012805350421000_2025.01.22.634152v1.57","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gku955"},{"key":"2025012805350421000_2025.01.22.634152v1.58","doi-asserted-by":"publisher","DOI":"10.1016\/J.DRUDIS.2019.09.022"},{"key":"2025012805350421000_2025.01.22.634152v1.59","doi-asserted-by":"publisher","DOI":"10.3389\/ftox.2023.1260305"},{"key":"2025012805350421000_2025.01.22.634152v1.60","doi-asserted-by":"crossref","unstructured":"Svoboda, D. L. , Saddler, T. & Auerbach, S. S . An overview of national toxicology program\u2019s toxicogenomic applications: DrugMatrix and ToxFX. in Challenges and Advances in Computational Chemistry and Physics 141\u2013157 (Springer International Publishing, Cham, 2019).","DOI":"10.1007\/978-3-030-16443-0_8"},{"key":"2025012805350421000_2025.01.22.634152v1.61","doi-asserted-by":"publisher","DOI":"10.1038\/s41596-023-00840-9"},{"key":"2025012805350421000_2025.01.22.634152v1.62","doi-asserted-by":"publisher","DOI":"10.1111\/jmi.12178"},{"key":"2025012805350421000_2025.01.22.634152v1.63","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01663-4"},{"key":"2025012805350421000_2025.01.22.634152v1.64","doi-asserted-by":"publisher","DOI":"10.1111\/jmi.13223"},{"key":"2025012805350421000_2025.01.22.634152v1.65","doi-asserted-by":"publisher","DOI":"10.1371\/JOURNAL.PBIO.2005970"},{"key":"2025012805350421000_2025.01.22.634152v1.66","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02399-z"},{"key":"2025012805350421000_2025.01.22.634152v1.67","doi-asserted-by":"publisher","DOI":"10.1289\/EHP6664"},{"key":"2025012805350421000_2025.01.22.634152v1.68","doi-asserted-by":"publisher","DOI":"10.1093\/toxsci\/kfw092"},{"key":"2025012805350421000_2025.01.22.634152v1.69","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa700"},{"key":"2025012805350421000_2025.01.22.634152v1.70","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.01.22.634152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:11:32Z","timestamp":1782277892000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.01.22.634152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,24]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1101\/2025.01.22.634152","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1016\/j.cels.2026.101566","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2025,1,24]]},"subtype":"preprint"}}