{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T11:44:39Z","timestamp":1753875879650,"version":"3.41.2"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T00:00:00Z","timestamp":1744761600000},"content-version":"vor","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Contrat de Plan Etat-R\u00e9gions\u2014Biologie Sant\u00e9 du site Lorrain"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Several machine learning (ML) algorithms dedicated to the detection of healthy and diseased cell types from single-cell RNA sequencing (scRNA-seq) data have been proposed for biomedical purposes. This raises concerns about their vulnerability to adversarial attacks, exploiting threats causing malicious alterations of the classifiers\u2019 output with defective and well-crafted input.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>With adverSCarial, adversarial attacks of single-cell transcriptomic data can easily be simulated in a range of ways, from expanded but undetectable modifications to aggressive and targeted ones, enabling vulnerability assessment of scRNA-seq classifiers to variations of gene expression, whether technical, biological, or intentional. We exemplify the usefulness and performance with a panel of attack modes proposed in adverSCarial by assessing the robustness of five scRNA-seq classifiers, each belonging to a distinct class of ML algorithm, and explore the potential unlocked by exposing their inner workings and sensitivities on four different datasets. These analyses can guide the development of more reliable models, with improved interpretability, usable in biomedical research and future clinical applications.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>adverSCarial is a freely available R package accessible from Bioconductor: https:\/\/bioconductor.org\/packages\/adverSCarial\/ or https:\/\/doi.org\/10.18129\/B9.bioc.adverSCarial. A development version is available at https:\/\/github.com\/GhislainFievet\/adverSCarial.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf168","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T02:59:18Z","timestamp":1744772358000},"source":"Crossref","is-referenced-by-count":0,"title":["adverSCarial: assessing the vulnerability of single-cell RNA-sequencing classifiers to adversarial attacks"],"prefix":"10.1093","volume":"41","author":[{"given":"Ghislain","family":"Fievet","sequence":"first","affiliation":[{"name":"INSERM U1256, Nutrition, Genetics, and Environmental Risk Exposure (NGERE), University of Lorraine , Nancy, 54500,","place":["France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Bros\u00e9us","sequence":"additional","affiliation":[{"name":"INSERM U1256, Nutrition, Genetics, and Environmental Risk Exposure (NGERE), University of Lorraine , Nancy, 54500,","place":["France"]},{"name":"Department of Biological Hematology, Laboratory Center, University Hospital of Nancy , Nancy, 54500,","place":["France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Meyre","sequence":"additional","affiliation":[{"name":"INSERM U1256, Nutrition, Genetics, and Environmental Risk Exposure (NGERE), University of Lorraine , Nancy, 54500,","place":["France"]},{"name":"Department of Molecular Medicine, Division of Biochemistry, Molecular Biology, and Nutrition, University Hospital of Nancy , Nancy, 54500,","place":["France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8456-7992","authenticated-orcid":false,"given":"S\u00e9bastien","family":"Hergalant","sequence":"additional","affiliation":[{"name":"INSERM U1256, Nutrition, Genetics, and Environmental Risk Exposure (NGERE), University of Lorraine , Nancy, 54500,","place":["France"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,4,15]]},"reference":[{"key":"2025042816064478700_btaf168-B1","first-page":"C1","volume-title":"Handbook of Neural Computation","author":"Almeida","year":"2020"},{"key":"2025042816064478700_btaf168-B2","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1038\/s41592-019-0654-x","article-title":"Orchestrating single-cell analysis with Bioconductor","volume":"17","author":"Amezquita","year":"2020","journal-title":"Nat Methods"},{"key":"2025042816064478700_btaf168-B3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2025042816064478700_btaf168-B4","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1038\/s41540-017-0038-8","article-title":"Classification of gene signatures for their information value and functional redundancy","volume":"4","author":"Cantini","year":"2018","journal-title":"NPJ Syst Biol Appl"},{"key":"2025042816064478700_btaf168-B5","doi-asserted-by":"crossref","first-page":"1717","DOI":"10.1093\/bib\/bbz093","article-title":"Universal concept signature analysis: genome-wide quantification of new biological and pathological functions of genes and pathways","volume":"21","author":"Chi","year":"2020","journal-title":"Brief Bioinf"},{"key":"2025042816064478700_btaf168-B6","doi-asserted-by":"crossref","first-page":"e95","DOI":"10.1093\/nar\/gkz543","article-title":"CHETAH: a selective, hierarchical cell type identification method for single-cell RNA sequencing","volume":"47","author":"de Kanter","year":"2019","journal-title":"Nucleic Acids Res"},{"year":"2015","author":"Goodfellow","key":"2025042816064478700_btaf168-B7"},{"key":"2025042816064478700_btaf168-B8","doi-asserted-by":"crossref","first-page":"5711","DOI":"10.1038\/s41467-022-33266-0","article-title":"Adversarial attacks and adversarial robustness in computational pathology","volume":"13","author":"Ghaffari Laleh","year":"2022","journal-title":"Nat Commun"},{"key":"2025042816064478700_btaf168-B9","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.trecan.2019.11.010","article-title":"Tumor functional heterogeneity unraveled by scRNA-seq technologies","volume":"6","author":"Gonz\u00e1lez-Silva","year":"2020","journal-title":"Trends Cancer"},{"key":"2025042816064478700_btaf168-B10","doi-asserted-by":"crossref","first-page":"e43","DOI":"10.1002\/imt2.43","article-title":"Complex heatmap visualization","volume":"1","author":"Gu","year":"2022","journal-title":"iMeta"},{"key":"2025042816064478700_btaf168-B11","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1038\/s41591-020-0791-x","article-title":"Deep learning models for electrocardiograms are susceptible to adversarial attack","volume":"26","author":"Han","year":"2020","journal-title":"Nat Med"},{"key":"2025042816064478700_btaf168-B12","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1038\/s41587-023-01767-y","article-title":"Dictionary learning for integrative, multimodal and scalable single-cell analysis","volume":"42","author":"Hao","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2025042816064478700_btaf168-B13","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1038\/s41467-022-28803-w","article-title":"Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data","volume":"13","author":"Ianevski","year":"2022","journal-title":"Nat Commun"},{"year":"2017","author":"Kingma","key":"2025042816064478700_btaf168-B14"},{"key":"2025042816064478700_btaf168-B15","doi-asserted-by":"crossref","first-page":"3236","DOI":"10.1038\/s41591-024-03215-z","article-title":"A multi-modal single-cell and spatial expression map of metastatic breast cancer biopsies across clinicopathological features","volume":"30","author":"Klughammer","year":"2024","journal-title":"Nat Med"},{"key":"2025042816064478700_btaf168-B16","doi-asserted-by":"crossref","first-page":"e0205499","DOI":"10.1371\/journal.pone.0205499","article-title":"CaSTLe\u2014classification of single cells by transfer learning: harnessing the power of publicly available single cell RNA sequencing experiments to annotate new experiments","volume":"13","author":"Lieberman","year":"2018","journal-title":"PLoS One"},{"year":"2019","author":"Madry","key":"2025042816064478700_btaf168-B17"},{"key":"2025042816064478700_btaf168-B18","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s12859-022-04574-5","article-title":"scAnnotatR: framework to accurately classify cell types in single-cell RNA-sequencing data","volume":"23","author":"Nguyen","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2025042816064478700_btaf168-B19","first-page":"vbad166","article-title":"Adversarial training improves model interpretability in single-cell RNA-seq analysis","volume":"3","author":"Sadria","year":"2023","journal-title":"Bioinf Adv"},{"key":"2025042816064478700_btaf168-B20","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1126\/science.aat5031","article-title":"Spatiotemporal immune zonation of the human kidney","volume":"365","author":"Stewart","year":"2019","journal-title":"Science"},{"key":"2025042816064478700_btaf168-B21","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1186\/s40779-022-00434-8","article-title":"Data analysis guidelines for single-cell RNA-seq in biomedical studies and clinical applications","volume":"9","author":"Su","year":"2022","journal-title":"Military Med Res"},{"key":"2025042816064478700_btaf168-B22","volume-title":"Introduction to Data Mining","author":"Tan","year":"2018","edition":"2nd edn."},{"key":"2025042816064478700_btaf168-B23","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.cels.2019.06.004","article-title":"SingleCellNet: a computational tool to classify single cell RNA-Seq data across platforms and across species","volume":"9","author":"Tan","year":"2019","journal-title":"Cell Syst"},{"key":"2025042816064478700_btaf168-B24","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1038\/s41592-019-0529-1","article-title":"Probabilistic cell-type assignment of single-cell RNA-seq for tumor microenvironment profiling","volume":"16","author":"Zhang","year":"2019","journal-title":"Nat Methods"},{"key":"2025042816064478700_btaf168-B25","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1093\/bib\/bbz096","article-title":"Evaluation of single-cell classifiers for single-cell RNA sequencing data sets","volume":"21","author":"Zhao","year":"2020","journal-title":"Brief Bioinf"},{"key":"2025042816064478700_btaf168-B26","doi-asserted-by":"crossref","first-page":"7281","DOI":"10.1038\/s41467-021-27577-x","article-title":"A machine and human reader study on AI diagnosis model safety under attacks of adversarial images","volume":"12","author":"Zhou","year":"2021","journal-title":"Nat Commun"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf168\/62934401\/btaf168.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf168\/62934401\/btaf168.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf168\/62934401\/btaf168.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T20:06:58Z","timestamp":1745870818000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf168\/8114001"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,3,29]]},"references-count":26,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf168","relation":{},"ISSN":["1367-4811"],"issn-type":[{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2025,4]]},"published":{"date-parts":[[2025,3,29]]},"article-number":"btaf168"}}