{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T02:27:45Z","timestamp":1787020065656,"version":"3.56.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,7,24]],"date-time":"2022-07-24T00:00:00Z","timestamp":1658620800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,7,24]],"date-time":"2022-07-24T00:00:00Z","timestamp":1658620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Computer-aided analysis of biological images typically requires extensive training on large-scale annotated datasets, which is not viable in many situations. In this paper, we present Generative Adversarial Network Discriminator Learner (GAN-DL), a novel self-supervised learning paradigm based on the StyleGAN2 architecture, which we employ for self-supervised image representation learning in the case of fluorescent biological images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We show that Wasserstein Generative Adversarial Networks enable high-throughput compound screening based on raw images. We demonstrate this by classifying active and inactive compounds tested for the inhibition of SARS-CoV-2 infection in two different cell models: the primary human renal cortical epithelial cells (HRCE) and the African green monkey kidney epithelial cells (VERO). In contrast to previous methods, our deep learning-based approach does not require any annotation, and can also be used to solve subtle tasks it was not specifically trained on, in a self-supervised manner. For example, it can effectively derive a dose-response curve for the tested treatments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>\n                      Our code and embeddings are available at\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/gitlab.com\/AlesioRFM\/gan-dl\">https:\/\/gitlab.com\/AlesioRFM\/gan-dl<\/jats:ext-link>\n                      StyleGAN2 is available at\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/NVlabs\/stylegan2\">https:\/\/github.com\/NVlabs\/stylegan2<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12859-022-04845-1","type":"journal-article","created":{"date-parts":[[2022,7,24]],"date-time":"2022-07-24T12:02:38Z","timestamp":1658664158000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations"],"prefix":"10.1186","volume":"23","author":[{"given":"Alessio","family":"Mascolini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dario","family":"Cardamone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Ponzio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santa","family":"Di Cataldo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ficarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,24]]},"reference":[{"key":"4845_CR1","doi-asserted-by":"crossref","unstructured":"Liu X, Zhang F, Hou Z, Wang Z, Mian L, Zhang J, Tang J. Self-supervised learning: generative or contrastive, 2020;1(2). arXiv preprint. arXiv:2006.08218.","DOI":"10.1109\/TKDE.2021.3090866"},{"issue":"3","key":"4845_CR2","doi-asserted-by":"publisher","first-page":"256","DOI":"10.3390\/electronics8030256","volume":"8","author":"F Ponzio","year":"2019","unstructured":"Ponzio F, Urgese G, Ficarra E, Di Cataldo S. Dealing with lack of training data for convolutional neural networks: the case of digital pathology. Electronics. 2019;8(3):256.","journal-title":"Electronics"},{"key":"4845_CR3","doi-asserted-by":"publisher","unstructured":"Melinscak M, Loncaric S. Retinal oct image segmentation: how well do algorithms generalize or how transferable are the data? 2020. https:\/\/doi.org\/10.23919\/MIPRO48935.2020.9245336.","DOI":"10.23919\/MIPRO48935.2020.9245336"},{"key":"4845_CR4","doi-asserted-by":"crossref","unstructured":"Wallace B, Hariharan B. Extending and analyzing self-supervised learning across domains. 2020. arXiv:2004.11992.","DOI":"10.1007\/978-3-030-58574-7_43"},{"key":"4845_CR5","doi-asserted-by":"crossref","unstructured":"Ponzio F, Deodato G, Macii E, Di\u00a0Cataldo S, Ficarra E. Exploiting \u201cuncertain\u201d deep networks for data cleaning in digital pathology. In: IEEE 17th international symposium on biomedical imaging (ISBI). IEEE; 2020. p. 1139\u201343.","DOI":"10.1109\/ISBI45749.2020.9098605"},{"issue":"1","key":"4845_CR6","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2020","unstructured":"Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H, Xiong H, He Q. A comprehensive survey on transfer learning. Proc IEEE. 2020;109(1):43\u201376.","journal-title":"Proc IEEE"},{"key":"4845_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71704-9_65","author":"A Farahani","year":"2021","unstructured":"Farahani A, Voghoei S, Rasheed K, Arabnia HR. A brief review of domain adaptation. Adv Data Sci Inf Eng. 2021. https:\/\/doi.org\/10.1007\/978-3-030-71704-9_65.","journal-title":"Adv Data Sci Inf Eng"},{"issue":"3","key":"4845_CR8","doi-asserted-by":"publisher","first-page":"1718","DOI":"10.3390\/app12031718","volume":"12","author":"AR Sajun","year":"2022","unstructured":"Sajun AR, Zualkernan I. Survey on implementations of generative adversarial networks for semi-supervised learning. Appl Sci. 2022;12(3):1718.","journal-title":"Appl Sci"},{"issue":"2","key":"4845_CR9","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","volume":"109","author":"JE Van Engelen","year":"2020","unstructured":"Van Engelen JE, Hoos HH. A survey on semi-supervised learning. Mach Learn. 2020;109(2):373\u2013440.","journal-title":"Mach Learn"},{"issue":"11","key":"4845_CR10","doi-asserted-by":"publisher","first-page":"4037","DOI":"10.1109\/TPAMI.2020.2992393","volume":"43","author":"L Jing","year":"2020","unstructured":"Jing L, Tian Y. Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans Pattern Anal Mach Intell. 2020;43(11):4037\u201358.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4845_CR11","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J. Learning transferable visual models from natural language supervision. In: International conference on machine learning. PMLR; 2021. p. 8748\u20138763."},{"key":"4845_CR12","unstructured":"AAAI 2020 conference. 2020. https:\/\/aaai.org\/Conferences\/AAAI-20\/. Accessed 29 April 2021."},{"key":"4845_CR13","doi-asserted-by":"crossref","unstructured":"Goldsborough P, Pawlowski N, Caicedo JC, Singh S, Carpenter AE. Cytogan: generative modeling of cell images. BioRxiv 2017; p. 227645.","DOI":"10.1101\/227645"},{"key":"4845_CR14","unstructured":"Gildenblat J, Klaiman E. Self-supervised similarity learning for digital pathology. arXiv preprint. arXiv:1905.08139 (2019)"},{"key":"4845_CR15","doi-asserted-by":"crossref","unstructured":"Abbet C, Zlobec I, Bozorgtabar B, Thiran J-P. Divide-and-rule: self-supervised learning for survival analysis in colorectal cancer. In: International conference on medical image computing and computer-assisted intervention. Springer; 2020. p. 480\u201389.","DOI":"10.1007\/978-3-030-59722-1_46"},{"key":"4845_CR16","doi-asserted-by":"crossref","unstructured":"Yang P, Hong Z, Yin X, Zhu C, Jiang R. Self-supervised visual representation learning for histopathological images. In: International conference on medical image computing and computer-assisted intervention. Springer; 2021. p. 47\u201357.","DOI":"10.1007\/978-3-030-87196-3_5"},{"key":"4845_CR17","doi-asserted-by":"crossref","unstructured":"Sahasrabudhe M, Christodoulidis S, Salgado R, Michiels S, Loi S, Andr\u00e9 F, Paragios N, Vakalopoulou M. Self-supervised nuclei segmentation in histopathological images using attention. In: International conference on medical image computing and computer-assisted intervention. Springer; 2020. p. 393\u2013402.","DOI":"10.1007\/978-3-030-59722-1_38"},{"key":"4845_CR18","unstructured":"Dmitrenko, A., Masiero, M.M., Zamboni, N.: Self-supervised learning for analysis of temporal and morphological drug effects in cancer cell imaging data. arXiv preprint. arXiv:2203.04289 (2022)."},{"key":"4845_CR19","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aittala M, Hellsten J, Lehtinen J, Aila T. Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition; 2020. p. 8110\u201319.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"4845_CR20","unstructured":"Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:arXiv:1511.06434 (2016)."},{"issue":"11","key":"4845_CR21","doi-asserted-by":"publisher","first-page":"2092","DOI":"10.1109\/LGRS.2017.2752750","volume":"14","author":"D Lin","year":"2017","unstructured":"Lin D, Fu K, Wang Y, Xu G, Sun X. MARTA GANs: unsupervised representation learning for remote sensing image classification. IEEE Geosci Remote Sens Lett. 2017;14(11):2092\u20136.","journal-title":"IEEE Geosci Remote Sens Lett"},{"issue":"5","key":"4845_CR22","doi-asserted-by":"publisher","first-page":"2669","DOI":"10.1109\/TGRS.2018.2876123","volume":"57","author":"M Zhang","year":"2018","unstructured":"Zhang M, Gong M, Mao Y, Li J, Wu Y. Unsupervised feature extraction in hyperspectral images based on wasserstein generative adversarial network. IEEE Trans Geosci Remote Sens. 2018;57(5):2669\u201388.","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"4845_CR23","unstructured":"Mao X, Su Z, Tan PS, Chow JK, Wang Y-H. Is discriminator a good feature extractor? arXiv:arXiv:1912.00789 (2020)"},{"key":"4845_CR24","unstructured":"Arjovsky M, Chintala S, Bottou L. Wasserstein gan. arXiv:arXiv:1701.07875 (2017)."},{"key":"4845_CR25","unstructured":"RecursionAI: RxRx19 dataset. https:\/\/www.rxrx.ai\/rxrx19 (2020)."},{"key":"4845_CR26","unstructured":"RecursionAI. RxRx1 dataset. https:\/\/www.rxrx.ai\/rxrx1 (2019)."},{"key":"4845_CR27","unstructured":"Taylor J, Earnshaw B, Mabey B, Victors M, Yosinski J. Rxrx1: an image set for cellular morphological variation across many experimental batches. In: The 7th international conference on learning representations; 2019."},{"key":"4845_CR28","doi-asserted-by":"publisher","unstructured":"Cuccarese MF, Earnshaw BA, Heiser K, Fogelson B, Davis CT, McLean PF, Gordon HB, Skelly K-R, Weathersby FL, Rodic V, Quigley IK, Pastuzyn ED, Mendivil BM, Lazar NH, Brooks CA, Carpenter J, Jacobson P, lazier SW, Ford J, Jensen JD, Campbell ND, Statnick MA, Low AS, Thomas KR, Carpenter AE, Hegde SS, Alfa RW, Victors ML, Haque IS, Chong YT, Gibson CC. Functional immune mapping with deep-learning enabled phenomics applied toimmunomodulatory and covid-19 drug discovery. bioRxiv2020. https:\/\/doi.org\/10.1101\/2020.04.21.054387. https:\/\/www.biorxiv.org\/content\/early\/2020\/08\/03\/2020.08.02.233064.full.pdf.","DOI":"10.1101\/2020.04.21.054387"},{"issue":"17","key":"4845_CR29","doi-asserted-by":"publisher","first-page":"7772","DOI":"10.3390\/app11177772","volume":"11","author":"D Zhuang","year":"2021","unstructured":"Zhuang D, Ibrahim AK. Deep learning for drug discovery: a study of identifying high efficacy drug compounds using a cascade transfer learning approach. Appl Sci. 2021;11(17):7772.","journal-title":"Appl Sci"},{"key":"4845_CR30","doi-asserted-by":"crossref","unstructured":"Saberian MS, Moriarty KP, Olmstead AD, Nabi IR, Jean F, Libbrecht MW, Hamarneh G. Deemd: drug efficacy estimation against SARS-COV-2 based on cell morphology with deep multiple instance learning. arXiv preprint. arXiv:2105.05758 (2021).","DOI":"10.36227\/techrxiv.19326665"},{"key":"4845_CR31","doi-asserted-by":"publisher","unstructured":"Heiser K, McLean PF, Davis CT, Fogelson B, Gordon HB, Jacobson P, Hurst B, Miller B, Alfa RW, Earnshaw BA, Victors ML, Chong YT, Haque IS, Low AS, Gibson CC. Identification of potential treatments for covid-19 through artificial intelligence-enabled phenomic analysis of human cells infected with SARS-COV-2. bioRxiv. https:\/\/doi.org\/10.1101\/2020.04.21.054387. https:\/\/www.biorxiv.org\/content\/early\/2020\/04\/23\/2020.04.21.054387.full.pdf (2020).","DOI":"10.1101\/2020.04.21.054387"},{"key":"4845_CR32","unstructured":"Mescheder L, Geiger A, Nowozin S. Which training methods for GANs do actually converge? arXiv:arXiv1801.04406 (2018)."},{"key":"4845_CR33","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Xue N, Zafeiriou S. Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2019. p. 4690\u201399.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"4845_CR34","doi-asserted-by":"publisher","unstructured":"Pihlgren GG, Sandin F, Liwicki M. Improving image autoencoder embeddings with perceptual loss. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2001.03444. https:\/\/arxiv.org\/abs\/2001.03444 (2020).","DOI":"10.48550\/ARXIV.2001.03444"},{"key":"4845_CR35","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1002\/jmv.26397","volume":"93","author":"M Ko","year":"2020","unstructured":"Ko M, Jeon S, Ryu W-S, Kim S. Comparative analysis of antiviral efficacy of FDA-approved drugs against SARS-COV-2 in human lung cells. J Med Virol. 2020;93:1403\u20138.","journal-title":"J Med Virol"},{"key":"4845_CR36","doi-asserted-by":"crossref","unstructured":"Ponzio F, Macii E, Ficarra E, Di\u00a0Cataldo S. Colorectal cancer classification using deep convolutional networks. In: Proceedings of the 11th international joint conference on biomedical engineering systems and technologies, vol. 2; 2018. p. 58\u201366.","DOI":"10.5220\/0006643100580066"},{"key":"4845_CR37","doi-asserted-by":"crossref","unstructured":"Mormont R, Geurts P, Mar\u00e9e R. Comparison of deep transfer learning strategies for digital pathology. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshopsm, 2018. p. 2262\u201371.","DOI":"10.1109\/CVPRW.2018.00303"},{"key":"4845_CR38","unstructured":"Chen X, Duan Y, Houthooft R, Schulman J, Sutskever I, Abbeel P. Infogan: interpretable representation learning by information maximizing generative adversarial nets. arXiv preprint. arXiv:1606.03657 (2016)."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04845-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-022-04845-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04845-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:09:43Z","timestamp":1658707783000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-022-04845-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,24]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["4845"],"URL":"https:\/\/doi.org\/10.1186\/s12859-022-04845-1","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,24]]},"assertion":[{"value":"9 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All methods were carried out in accordance with relevant guidelines and regulations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"295"}}