{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T03:55:04Z","timestamp":1774670104528,"version":"3.50.1"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"23","license":[{"start":{"date-parts":[[2021,7,8]],"date-time":"2021-07-08T00:00:00Z","timestamp":1625702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100015311","name":"Novartis Institutes for Biomedical Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The identification and discovery of phenotypes from high content screening images is a challenging task. Earlier works use image analysis pipelines to extract biological features, supervised training methods or generate features with neural networks pretrained on non-cellular images. We introduce a novel unsupervised deep learning algorithm to cluster cellular images with similar Mode-of-Action (MOA) together using only the images\u2019 pixel intensity values as input. It corrects for batch effect during training. Importantly, our method does not require the extraction of cell candidates and works from the entire images directly.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The method achieves competitive results on the labeled subset of the BBBC021 dataset with an accuracy of 97.09% for correctly classifying the MOA by nearest neighbors matching. Importantly, we can train our approach on unannotated datasets. Therefore, our method can discover novel MOAs and annotate unlabeled compounds. The ability to train end-to-end on the full resolution images makes our method easy to apply and allows it to further distinguish treatments by their effect on proliferation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Our code is available at https:\/\/github.com\/Novartis\/UMM-Discovery.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab497","type":"journal-article","created":{"date-parts":[[2021,7,2]],"date-time":"2021-07-02T16:18:00Z","timestamp":1625242680000},"page":"4548-4555","source":"Crossref","is-referenced-by-count":24,"title":["Fully unsupervised deep mode of action learning for phenotyping high-content cellular images"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5717-0340","authenticated-orcid":false,"given":"Rens","family":"Janssens","sequence":"first","affiliation":[{"name":"NIBR, Oncology, Novartis Institutes for BioMedical Research Inc , 4056 Basel, Switzerland"}]},{"given":"Xian","family":"Zhang","sequence":"additional","affiliation":[{"name":"NIBR, Oncology, Novartis Institutes for BioMedical Research Inc , 4056 Basel, Switzerland"}]},{"given":"Audrey","family":"Kauffmann","sequence":"additional","affiliation":[{"name":"NIBR, Oncology, Novartis Institutes for BioMedical Research Inc , 4056 Basel, Switzerland"}]},{"given":"Antoine","family":"de Weck","sequence":"additional","affiliation":[{"name":"NIBR, Oncology, Novartis Institutes for BioMedical Research Inc , 4056 Basel, Switzerland"}]},{"given":"Eric Y","family":"Durand","sequence":"additional","affiliation":[{"name":"NIBR, Oncology, Novartis Institutes for BioMedical Research Inc , 4056 Basel, Switzerland"}]}],"member":"286","published-online":{"date-parts":[[2021,7,8]]},"reference":[{"key":"2023061310492307500_btab497-B1","first-page":"161422","article-title":"Improving phenotypic measurements in high-content imaging screens","author":"Ando","year":"2017","journal-title":"bioRxiv"},{"key":"2023061310492307500_btab497-B2","volume-title":"Assay Guidance Manual.","author":"Buchser","year":"2004"},{"key":"2023061310492307500_btab497-B3","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1038\/nmeth.4397","article-title":"Data-analysis strategies for image-based cell profiling","volume":"14","author":"Caicedo","year":"2017","journal-title":"Nat. Methods"},{"key":"2023061310492307500_btab497-B4","first-page":"9309","article-title":"Weakly supervised learning of single-cell feature embeddings","volume":"2018","author":"Caicedo","year":"2018","journal-title":"Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit"},{"key":"2023061310492307500_btab497-B5","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1158\/1535-7163.MCT-09-1148","article-title":"High-content phenotypic profiling of drug response signatures across distinct cancer cells","volume":"9","author":"Caie","year":"2010","journal-title":"Mol. Cancer Ther"},{"key":"2023061310492307500_btab497-B6","article-title":"Deep clustering for unsupervised learning of visual features","author":"Caron","year":"2019"},{"key":"2023061310492307500_btab497-B7","doi-asserted-by":"crossref","first-page":"R100","DOI":"10.1186\/gb-2006-7-10-r100","article-title":"CellProfiler: image analysis software for identifying and quantifying cell phenotypes","volume":"7","author":"Carpenter","year":"2006","journal-title":"Genome Biol"},{"key":"2023061310492307500_btab497-B8","doi-asserted-by":"crossref","first-page":"13262","DOI":"10.1038\/s41598-020-69354-8","article-title":"Tales of 1,008 small molecules: phenomic profiling through live-cell imaging in a panel of reporter cell lines","volume":"10","author":"Cox","year":"2020","journal-title":"Sci. Rep"},{"key":"2023061310492307500_btab497-B9","doi-asserted-by":"crossref","first-page":"2010","DOI":"10.1093\/bioinformatics\/btx069","article-title":"A multi-scale convolutional neural network for phenotyping high-content cellular images","volume":"33","author":"Godinez","year":"2017","journal-title":"Bioinformatics"},{"key":"2023061310492307500_btab497-B10","author":"Godinez","year":"2018"},{"key":"2023061310492307500_btab497-B11","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.jneumeth.2010.07.003","article-title":"An imaging assay to analyze primary neurons for cellular neurotoxicity","volume":"192","author":"G\u00f6tte","year":"2010","journal-title":"J. Neurosci. Methods"},{"key":"2023061310492307500_btab497-B12","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1093\/biostatistics\/kxj037","article-title":"Adjusting batch effects in microarray expression data using empirical Bayes methods","volume":"8","author":"Johnson","year":"2007","journal-title":"Biostatistics"},{"key":"2023061310492307500_btab497-B13","doi-asserted-by":"crossref","first-page":"i52","DOI":"10.1093\/bioinformatics\/btw252","article-title":"Classifying and segmenting microscopy images using convolutional multiple instance learning","volume":"32","author":"Kraus","year":"2016","journal-title":"Bioinformatics"},{"key":"2023061310492307500_btab497-B14","first-page":"315","volume-title":"Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, Proceedings of Machine Learning Research. PMLR","author":"Lafarge","year":"2019"},{"key":"2023061310492307500_btab497-B15","first-page":"655","article-title":"Power iteration clustering","author":"Lin","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"2023061310492307500_btab497-B16","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1177\/1087057113503553","article-title":"Comparison of methods for image-based profiling of cellular morphological responses to small-molecule treatment","volume":"18","author":"Ljosa","year":"2013","journal-title":"J. Biomol. Screen"},{"key":"2023061310492307500_btab497-B17","article-title":"Visualizing data using t-SNE. J. Mach. Learn. Res., 9, 2579\u2013605","author":"Maaten","year":"2008"},{"key":"2023061310492307500_btab497-B18","doi-asserted-by":"crossref","first-page":"205","DOI":"10.21105\/joss.00205","article-title":"hdbscan: hierarchical density based clustering","volume":"2","author":"McInnes","year":"2017","journal-title":"JOSS"},{"key":"2023061310492307500_btab497-B19","article-title":"Evaluation metrics for unsupervised learning algorithms","author":"Palacio-Ni\u00f1o","year":"2019","journal-title":"arXiv"},{"key":"2023061310492307500_btab497-B20","article-title":"Automating morphological profiling with generic deep convolutional networks","volume":"085118","author":"Pawlowski","year":"2016","journal-title":"bioRxiv"},{"key":"2023061310492307500_btab497-B21","doi-asserted-by":"crossref","first-page":"i875","DOI":"10.1093\/bioinformatics\/btaa819","article-title":"Batch equalization with a generative adversarial network","volume":"36","author":"Qian","year":"2020","journal-title":"Bioinformatics"},{"key":"2023061310492307500_btab497-B22","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1111\/jmi.12178","article-title":"Pipeline for illumination correction of images for high-throughput microscopy","volume":"256","author":"Singh","year":"2014","journal-title":"J. Microscopy"},{"key":"2023061310492307500_btab497-B23","article-title":"Metadata-guided visual representation learning for biomedical images","volume":"725754","author":"Spiegel","year":"2019","journal-title":"bioRxiv"},{"key":"2023061310492307500_btab497-B24","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1038\/s41592-020-01018-x","article-title":"Cellpose: a generalist algorithm for cellular segmentation","volume":"18","author":"Stringer","year":"2021","journal-title":"Nat. Methods"},{"key":"2023061310492307500_btab497-B25","first-page":"153","article-title":"Correlation alignment for unsupervised domain adaptation","author":"Sun","year":"2017"},{"key":"2023061310492307500_btab497-B26","doi-asserted-by":"crossref","first-page":"e8594","DOI":"10.7717\/peerj.8594","article-title":"Correcting nuisance variation using Wasserstein distance","volume":"8","author":"Tabak","year":"2020","journal-title":"PeerJ"},{"key":"2023061310492307500_btab497-B27","doi-asserted-by":"crossref","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"DrugBank 5.0: a major update to the DrugBank database for 2018","volume":"46","author":"Wishart","year":"2018","journal-title":"Nucleic Acids Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab497\/39477672\/btab497.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/23\/4548\/50579587\/btab497.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/23\/4548\/50579587\/btab497.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T06:50:45Z","timestamp":1686639045000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/23\/4548\/6317826"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,7,8]]},"references-count":27,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2021,12,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab497","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.07.22.215459","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,12,1]]},"published":{"date-parts":[[2021,7,8]]}}}