{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:49:30Z","timestamp":1773938970931,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1012083","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000}}],"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32370711"],"award-info":[{"award-number":["32370711"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32300554"],"award-info":[{"award-number":["32300554"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013853","name":"Shenzhen Hospital, Southern Medical University","doi-asserted-by":"publisher","award":["A2303033"],"award-info":[{"award-number":["A2303033"]}],"id":[{"id":"10.13039\/501100013853","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220530152409020"],"award-info":[{"award-number":["JCYJ20220530152409020"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Sepsis is a life-threatening condition characterized by an exaggerated immune response to pathogens, leading to organ damage and high mortality rates in the intensive care unit. Although deep learning has achieved impressive performance on prediction and classification tasks in medicine, it requires large amounts of data and lacks explainability, which hinder its application to sepsis diagnosis. We introduce a deep learning framework, called scCaT, which blends the capsulating architecture with Transformer to develop a sepsis diagnostic model using single-cell RNA sequencing data and transfers it to bulk RNA data. The capsulating architecture effectively groups genes into capsules based on biological functions, which provides explainability in encoding gene expressions. The Transformer serves as a decoder to classify sepsis patients and controls. Our model achieves high accuracy with an AUROC of 0.93 on the single-cell test set and an average AUROC of 0.98 on seven bulk RNA cohorts. Additionally, the capsules can recognize different cell types and distinguish sepsis from control samples based on their biological pathways. This study presents a novel approach for learning gene modules and transferring the model to other data types, offering potential benefits in diagnosing rare diseases with limited subjects.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012083","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T13:42:36Z","timestamp":1729518156000},"page":"e1012083","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["scCaT: An explainable capsulating architecture for sepsis diagnosis transferring from single-cell RNA sequencing"],"prefix":"10.1371","volume":"20","author":[{"given":"Xubin","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Dian","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Duo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Wan-Ki","family":"Wong","sequence":"additional","affiliation":[]},{"given":"Ka-Ho","family":"To","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"JiaFei","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yining","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Kwong-Sak","family":"Leung","sequence":"additional","affiliation":[]},{"given":"Man-Hon","family":"Wong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-383X","authenticated-orcid":true,"given":"Lixin","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"issue":"9868","key":"pcbi.1012083.ref001","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1016\/S0140-6736(12)61815-7","article-title":"Sepsis definitions: time for change","volume":"381","author":"JL Vincent","year":"2013","journal-title":"Lancet"},{"key":"pcbi.1012083.ref002","article-title":"bvnGPS: a generalizable diagnostic model for acute bacterial and viral infection using integrative host transcriptomics and pretrained neural networks","author":"Q Li","year":"2023","journal-title":"Bioinformatics"},{"key":"pcbi.1012083.ref003","article-title":"meGPS: a multi-omics signature for hepatocellular carcinoma detection integrating methylome and transcriptome data","author":"Q Wu","year":"2022","journal-title":"Bioinformatics"},{"key":"pcbi.1012083.ref004","doi-asserted-by":"crossref","first-page":"105881","DOI":"10.1016\/j.compbiomed.2022.105881","article-title":"Whole transcriptome analysis reveals non-coding RNA\u2019s competing endogenous gene pairs as novel form of motifs in serous ovarian cancer","volume":"148","author":"H Li","year":"2022","journal-title":"Computers in Biology and Medicine"},{"issue":"1","key":"pcbi.1012083.ref005","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1186\/s12864-021-07576-4","article-title":"Long non-coding RNA pairs to assist in diagnosing sepsis","volume":"22","author":"X Zheng","year":"2021","journal-title":"BMC Genomics"},{"issue":"2","key":"pcbi.1012083.ref006","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac002","article-title":"Improving bulk RNA-seq classification by transferring gene signature from single cells in acute myeloid leukemia","volume":"23","author":"R Wang","year":"2022","journal-title":"Brief Bioinform"},{"key":"pcbi.1012083.ref007","doi-asserted-by":"crossref","first-page":"5442","DOI":"10.1109\/ACCESS.2020.3043732","article-title":"A Deep Learning-Based Sepsis Estimation Scheme","volume":"9","author":"BY Al-Mualemi","year":"2021","journal-title":"Ieee Access"},{"issue":"1","key":"pcbi.1012083.ref008","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.1038\/s41598-023-30091-3","article-title":"Exploring a global interpretation mechanism for deep learning networks when predicting sepsis","volume":"13","author":"EAT Strickler","year":"2023","journal-title":"Scientific Reports"},{"key":"pcbi.1012083.ref009","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.compbiomed.2017.08.015","article-title":"Learning representations for the early detection of sepsis with deep neural networks","volume":"89","author":"HJ Kam","year":"2017","journal-title":"Comput Biol Med"},{"issue":"8","key":"pcbi.1012083.ref010","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1164\/rccm.201707-1339LE","article-title":"Molecular Biomarker to Assist in Diagnosing Abdominal Sepsis upon ICU Admission","volume":"197","author":"BP Scicluna","year":"2018","journal-title":"American Journal of Respiratory and Critical Care Medicine"},{"issue":"12","key":"pcbi.1012083.ref011","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1001916","article-title":"A Molecular Host Response Assay to Discriminate Between Sepsis and Infection-Negative Systemic Inflammation in Critically Ill Patients: Discovery and Validation in Independent Cohorts","volume":"12","author":"L McHugh","year":"2015","journal-title":"PLoS Med"},{"issue":"7","key":"pcbi.1012083.ref012","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1164\/rccm.201502-0355OC","article-title":"A molecular biomarker to diagnose community-acquired pneumonia on intensive care unit admission","volume":"192","author":"BP Scicluna","year":"2015","journal-title":"Am J Respir Crit Care Med"},{"key":"pcbi.1012083.ref013","article-title":"Dynamic routing between capsules","volume":"30","author":"S Sabour","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pcbi.1012083.ref014","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"pcbi.1012083.ref015","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1093\/bioinformatics\/btw570","article-title":"Precrec: fast and accurate precision\u2013recall and ROC curve calculations in R","volume":"33","author":"T Saito","year":"2017","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1012083.ref016","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1186\/s13059-024-03266-y","article-title":"Commonly used software tools produce conflicting and overly-optimistic AUPRC values","volume":"25","author":"W Chen","year":"2024","journal-title":"Genome Biology"},{"issue":"3","key":"pcbi.1012083.ref017","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1186\/1710-1492-2-3-98","article-title":"Mechanisms of degranulation in neutrophils","volume":"2","author":"P. Lacy","year":"2006","journal-title":"Allergy Asthma Clin Immunol"},{"issue":"1","key":"pcbi.1012083.ref018","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1038\/cr.2010.177","article-title":"Non-canonical NF-kappaB signaling pathway","volume":"21","author":"SC Sun","year":"2011","journal-title":"Cell Res"},{"key":"pcbi.1012083.ref019","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1146\/annurev.iy.13.040195.001343","article-title":"Interleukin-12\u2014a Proinflammatory Cytokine with Immunoregulatory Functions That Bridge Innate Resistance and Antigen-Specific Adaptive Immunity","volume":"13","author":"G. Trinchieri","year":"1995","journal-title":"Annu Rev Immunol"},{"issue":"9","key":"pcbi.1012083.ref020","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1038\/s41577-018-0029-z","article-title":"IFNgamma: signalling, epigenetics and roles in immunity, metabolism, disease and cancer immunotherapy","volume":"18","author":"LB Ivashkiv","year":"2018","journal-title":"Nat Rev Immunol"},{"issue":"6","key":"pcbi.1012083.ref021","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1002\/jlb.59.6.789","article-title":"Regulation of leukocyte adhesion and signaling in inflammation and disease","volume":"59","author":"SM Wahl","year":"1996","journal-title":"J Leukoc Biol"},{"issue":"6","key":"pcbi.1012083.ref022","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1161\/CIRCRESAHA.117.311401","article-title":"Reactive Oxygen Species in Metabolic and Inflammatory Signaling","volume":"122","author":"SJ Forrester","year":"2018","journal-title":"Circ Res"},{"key":"pcbi.1012083.ref023","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.coi.2018.01.002","article-title":"The regulation of lymphocyte activation and proliferation","volume":"51","author":"S Heinzel","year":"2018","journal-title":"Curr Opin Immunol"},{"issue":"1","key":"pcbi.1012083.ref024","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1038\/nrmicro2266","article-title":"The molecular basis of the host response to lipopolysaccharide","volume":"8","author":"CE Bryant","year":"2010","journal-title":"Nat Rev Microbiol"},{"issue":"3","key":"pcbi.1012083.ref025","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1038\/nrd3669","article-title":"Inflammatory bone loss: pathogenesis and therapeutic intervention","volume":"11","author":"K Redlich","year":"2012","journal-title":"Nat Rev Drug Discov"},{"issue":"D1","key":"pcbi.1012083.ref026","doi-asserted-by":"crossref","first-page":"D638","DOI":"10.1093\/nar\/gkac1000","article-title":"The STRING database in 2023: protein\u2013protein association networks and functional enrichment analyses for any sequenced genome of interest","volume":"51","author":"D Szklarczyk","year":"2023","journal-title":"Nucleic acids research"},{"key":"pcbi.1012083.ref027","article-title":"Specaugment: A simple data augmentation method for automatic speech recognition","author":"DS Park","year":"2019","journal-title":"arXiv preprint arXiv:190408779"},{"key":"pcbi.1012083.ref028","article-title":"editors. Arbitrary style transfer in real-time with adaptive instance normalization","author":"X Huang","year":"2017","journal-title":"Proceedings of the IEEE international conference on computer vision"},{"issue":"3","key":"pcbi.1012083.ref029","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1038\/s41591-020-0752-4","article-title":"An immune-cell signature of bacterial sepsis","volume":"26","author":"M Reyes","year":"2020","journal-title":"Nat Med"},{"key":"pcbi.1012083.ref030","doi-asserted-by":"crossref","first-page":"103776","DOI":"10.1016\/j.ebiom.2021.103776","article-title":"Predicting sepsis severity at first clinical presentation: The role of endotypes and mechanistic signatures","volume":"75","author":"A Baghela","year":"2022","journal-title":"EBioMedicine"},{"issue":"5\u20136","key":"pcbi.1012083.ref031","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.humimm.2017.03.010","article-title":"Modulation of LILRB2 protein and mRNA expressions in septic shock patients and after ex vivo lipopolysaccharide stimulation","volume":"78","author":"F Venet","year":"2017","journal-title":"Hum Immunol"},{"issue":"8","key":"pcbi.1012083.ref032","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1164\/rccm.201401-0171OC","article-title":"Corticosteroids are associated with repression of adaptive immunity gene programs in pediatric septic shock","volume":"189","author":"HR Wong","year":"2014","journal-title":"American journal of respiratory and critical care medicine"},{"issue":"1","key":"pcbi.1012083.ref033","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s40635-014-0020-3","article-title":"Early and dynamic changes in gene expression in septic shock patients: a genome-wide approach","volume":"2","author":"MA Cazalis","year":"2014","journal-title":"Intensive Care Med Exp"},{"issue":"3","key":"pcbi.1012083.ref034","doi-asserted-by":"crossref","first-page":"R149","DOI":"10.1186\/cc10274","article-title":"Development and validation of a novel molecular biomarker diagnostic test for the early detection of sepsis","volume":"15","author":"A Sutherland","year":"2011","journal-title":"Crit Care"},{"issue":"9\u201310","key":"pcbi.1012083.ref035","doi-asserted-by":"crossref","first-page":"495","DOI":"10.2119\/2007-00065.Shanley","article-title":"Genome-level longitudinal expression of signaling pathways and gene networks in pediatric septic shock","volume":"13","author":"TP Shanley","year":"2007","journal-title":"Mol Med"},{"issue":"1","key":"pcbi.1012083.ref036","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1152\/physiolgenomics.00025.2008","article-title":"Validating the genomic signature of pediatric septic shock","volume":"34","author":"N Cvijanovich","year":"2008","journal-title":"Physiol Genomics"},{"issue":"5","key":"pcbi.1012083.ref037","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1097\/CCM.0b013e31819fcc08","article-title":"Genomic expression profiling across the pediatric systemic inflammatory response syndrome, sepsis, and septic shock spectrum","volume":"37","author":"HR Wong","year":"2009","journal-title":"Crit Care Med"},{"issue":"3","key":"pcbi.1012083.ref038","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1164\/rccm.200801-131OC","article-title":"Interleukin-8 as a stratification tool for interventional trials involving pediatric septic shock","volume":"178","author":"HR Wong","year":"2008","journal-title":"American journal of respiratory and critical care medicine"},{"issue":"1","key":"pcbi.1012083.ref039","doi-asserted-by":"crossref","first-page":"15","DOI":"10.4103\/hm.HM-D-23-00021","article-title":"Multiomics on Mental Stress-Induced Myocardial Ischemia: A Narrative Review","volume":"8","author":"Nana Jin","year":"2024","journal-title":"Heart and Mind"},{"issue":"3","key":"pcbi.1012083.ref040","first-page":"253","article-title":"Effects of metaraminol and norepinephrine on hemodynamics and kidney function in a miniature pig model of septic shock","volume":"12","author":"Xiaodan Li","year":"2024","journal-title":"Journal of Translational Internal Medicine"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1012083","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T13:55:54Z","timestamp":1730382954000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012083"}},"subtitle":[],"editor":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":40,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012083","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.04.17.590014","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,21]]}}}