CoChat
Sign Up
Cited by 14Sepsis Diagnosis and TreatmentMachine Learning in HealthcareSingle-cell and spatial transcriptomics

scCaT: An explainable capsulating architecture for sepsis diagnosis transferring from single-cell RNA sequencing

Open access
Zheng, Xubin, Meng, Dian, Chen, Duo, Wong, Wan-Ki, To, Ka-Ho, Zhu, Lei, Wu, JiaFei, Liang, Yining +3 more·2024·PLOS Computational Biology
DOI 10.1371/journal.pcbi.1012083PMC PMC11527285

Published version of a preprint

Open this paper in CoChat — free account

Abstract

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pcbi.1012083

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Recent omics-based diagnostic models illustrate both the promise of transferring single-cell or molecular signatures across bulk and single-cell sequencing data and the dependence of such models on platform compatibility, normalization, and cohort-specific processing choices.

    “Recent omics-based diagnostic models illustrate both the promise of transferring single-cell or molecular signatures across bulk and single-cell sequencing data and the dependence of such models on platform compatibility, normalization, and cohort-specific processing choices [45–47].”

    From Validation is not enough: Longitudinal evidence of post-deployment fragility in clinical AI systems (2026) · cites this paper as [45]

    Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 39 · Cited by 14

Research works printed but not linked: 37

  1. [1]Vincent JL, Opal SM, Marshall JC, Tracey KJ. Sepsis definitions: time for change. Lancet. 2013; 381(9868): 774– 5. doi: 10.1016/S0140-6736(12)61815-7; PubMed Central PMCID: PMC4535310. 23472921 PMC4535310 · DOI
  2. [2]Li Q, Zheng X, Xie J, Wang R, Li M, Wong M-H, et al. bvnGPS: a generalizable diagnostic model for acute bacterial and viral infection using integrative host transcriptomics and pretrained neural networks. Bioinformatics. 2023. doi: 10.1093/bioinformatics/btad109 36857587 PMC9997702 · DOI
  3. [3]Wu Q, Zheng X, Leung KS, Wong MH, Tsui SK, Cheng L. meGPS: a multi-omics signature for hepatocellular carcinoma detection integrating methylome and transcriptome data. Bioinformatics. 2022. Epub 2022/06/09. doi: 10.1093/bioinformatics/btac379. 35674358 · DOI
  4. [4]Li H, Zheng X, Gao J, Leung K-S, Wong M-H, Yang S, et al. Whole transcriptome analysis reveals non-coding RNA’s competing endogenous gene pairs as novel form of motifs in serous ovarian cancer. Computers in Biology and Medicine. 2022; 148: 105881. doi: 10.1016/j.compbiomed.2022.105881 35940161 · DOI
  5. [5]Zheng X, Leung KS, Wong MH, Cheng L. Long non-coding RNA pairs to assist in diagnosing sepsis. BMC Genomics. 2021; 22(1): 275. Epub 2021/04/18. doi: 10.1186/s12864-021-07576-4; PubMed Central PMCID: PMC8050902. 33863291 PMC8050902 · DOI
  6. [6]Wang R, Zheng X, Wang J, Wan S, Song F, Wong MH, et al. Improving bulk RNA-seq classification by transferring gene signature from single cells in acute myeloid leukemia. Brief Bioinform. 2022; 23(2). Epub 2022/02/10. doi: 10.1093/bib/bbac002. 35136933 · DOI · Paper page
  7. [7]Al-Mualemi BY, Lu L. A Deep Learning-Based Sepsis Estimation Scheme. Ieee Access. 2021; 9: 5442– 52. doi: 10.1109/Access.2020.3043732 WOS:000608200200001. · DOI
  8. [8]Strickler EAT, Thomas J, Thomas JP, Benjamin B, Shamsuddin R. Exploring a global interpretation mechanism for deep learning networks when predicting sepsis. Scientific Reports. 2023; 13(1): 3067. doi: 10.1038/s41598-023-30091-3 36810645 PMC9945464 · DOI
  9. [10]Scicluna BP, Wiewel MA, van Vught LA, Hoogendijk AJ, Klarenbeek AM, Franitza M, et al. Molecular Biomarker to Assist in Diagnosing Abdominal Sepsis upon ICU Admission. American Journal of Respiratory and Critical Care Medicine. 2018; 197(8): 1070– 3. doi: 10.1164/rccm.201707-1339LE WOS:000430039900019. 28972859 · DOI
  10. [11]McHugh L, Seldon TA, Brandon RA, Kirk JT, Rapisarda A, Sutherland AJ, et al. A Molecular Host Response Assay to Discriminate Between Sepsis and Infection-Negative Systemic Inflammation in Critically Ill Patients: Discovery and Validation in Independent Cohorts. PLoS Med. 2015; 12(12). ARTN e1001916 doi: 10.1371/journal.pmed.1001916 WOS:000368451100006. 26645559 PMC4672921 · DOI
  11. [12]Scicluna BP, Klein Klouwenberg PM, van Vught LA, Wiewel MA, Ong DS, Zwinderman AH, et al. A molecular biomarker to diagnose community-acquired pneumonia on intensive care unit admission. Am J Respir Crit Care Med. 2015; 192(7): 826– 35. doi: 10.1164/rccm.201502-0355OC. 26121490 · DOI
  12. [13]Sabour S, Frosst N, Hinton GE. Dynamic routing between capsules. Advances in neural information processing systems. 2017; 30.
  13. [14]Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Advances in neural information processing systems. 2017; 30.
  14. [15]Saito T, Rehmsmeier M. Precrec: fast and accurate precision–recall and ROC curve calculations in R. Bioinformatics. 2017; 33(1): 145– 7. doi: 10.1093/bioinformatics/btw570 27591081 PMC5408773 · DOI
  15. [16]Chen W, Miao C, Zhang Z, Fung CS-H, Wang R, Chen Y, et al. Commonly used software tools produce conflicting and overly-optimistic AUPRC values. Genome Biology. 2024; 25(1): 118. doi: 10.1186/s13059-024-03266-y 38741205 PMC11089773 · DOI
  16. [17]Lacy P. Mechanisms of degranulation in neutrophils. Allergy Asthma Clin Immunol. 2006; 2(3): 98– 108. Epub 20060915. doi: 10.1186/1710-1492-2-3-98; PubMed Central PMCID: PMC2876182. 20525154 PMC2876182 · DOI
  17. [18]Sun SC. Non-canonical NF-kappaB signaling pathway. Cell Res. 2011; 21(1): 71– 85. Epub 20101221. doi: 10.1038/cr.2010.177; PubMed Central PMCID: PMC3193406. 21173796 PMC3193406 · DOI
  18. [19]Trinchieri G. Interleukin-12—a Proinflammatory Cytokine with Immunoregulatory Functions That Bridge Innate Resistance and Antigen-Specific Adaptive Immunity. Annu Rev Immunol. 1995; 13: 251– 76. doi: 10.1146/annurev.iy.13.040195.001343 WOS:A1995QV29000010. 7612223 · DOI
  19. [20]Ivashkiv LB. IFNgamma: signalling, epigenetics and roles in immunity, metabolism, disease and cancer immunotherapy. Nat Rev Immunol. 2018; 18(9): 545– 58. doi: 10.1038/s41577-018-0029-z; PubMed Central PMCID: PMC6340644. 29921905 PMC6340644 · DOI
  20. [21]Wahl SM, Feldman GM, McCarthy JB. Regulation of leukocyte adhesion and signaling in inflammation and disease. J Leukoc Biol. 1996; 59(6): 789– 96. doi: 10.1002/jlb.59.6.789. 8691062 · DOI
  21. [23]Heinzel S, Marchingo JM, Horton MB, Hodgkin PD. The regulation of lymphocyte activation and proliferation. Curr Opin Immunol. 2018; 51: 32– 8. Epub 20180203. doi: 10.1016/j.coi.2018.01.002. 29414529 · DOI
  22. [25]Redlich K, Smolen JS. Inflammatory bone loss: pathogenesis and therapeutic intervention. Nat Rev Drug Discov. 2012; 11(3): 234– 50. Epub 20120301. doi: 10.1038/nrd3669. 22378270 · DOI
  23. [26]Szklarczyk D, Kirsch R, Koutrouli M, Nastou K, Mehryary F, Hachilif R, et al. The STRING database in 2023: protein–protein association networks and functional enrichment analyses for any sequenced genome of interest. Nucleic acids research. 2023; 51(D1): D638– D46. doi: 10.1093/nar/gkac1000 36370105 PMC9825434 · DOI · Paper page
  24. [27]Park DS, Chan W, Zhang Y, Chiu C-C, Zoph B, Cubuk ED, et al. Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:190408779. 2019.
  25. [28]Huang X, Belongie S, editors. Arbitrary style transfer in real-time with adaptive instance normalization. Proceedings of the IEEE international conference on computer vision; 2017.
  26. [29]Reyes M, Filbin MR, Bhattacharyya RP, Billman K, Eisenhaure T, Hung DT, et al. An immune-cell signature of bacterial sepsis. Nat Med. 2020; 26(3): 333– 40. Epub 20200217. doi: 10.1038/s41591-020-0752-4; PubMed Central PMCID: PMC7235950. 32066974 PMC7235950 · DOI
  27. [30]Baghela A, Pena OM, Lee AH, Baquir B, Falsafi R, An A, et al. Predicting sepsis severity at first clinical presentation: The role of endotypes and mechanistic signatures. EBioMedicine. 2022; 75: 103776. Epub 20220110. doi: 10.1016/j.ebiom.2021.103776; PubMed Central PMCID: PMC8808161. 35027333 PMC8808161 · DOI
  28. [31]Venet F, Schilling J, Cazalis MA, Demaret J, Poujol F, Girardot T, et al. Modulation of LILRB2 protein and mRNA expressions in septic shock patients and after ex vivo lipopolysaccharide stimulation. Hum Immunol. 2017; 78(5–6): 441– 50. doi: 10.1016/j.humimm.2017.03.010. 28341250 · DOI
  29. [32]Wong HR, Cvijanovich NZ, Allen GL, Thomas NJ, Freishtat RJ, Anas N, et al. Corticosteroids are associated with repression of adaptive immunity gene programs in pediatric septic shock. American journal of respiratory and critical care medicine. 2014; 189(8): 940– 6. doi: 10.1164/rccm.201401-0171OC. 24650276 PMC4098101 · DOI
  30. [33]Cazalis MA, Lepape A, Venet F, Frager F, Mougin B, Vallin H, et al. Early and dynamic changes in gene expression in septic shock patients: a genome-wide approach. Intensive Care Med Exp. 2014; 2(1): 20. doi: 10.1186/s40635-014-0020-3; PubMed Central PMCID: PMC4512996. 26215705 PMC4512996 · DOI
  31. [34]Sutherland A, Thomas M, Brandon RA, Brandon RB, Lipman J, Tang B, et al. Development and validation of a novel molecular biomarker diagnostic test for the early detection of sepsis. Crit Care. 2011; 15(3): R149. doi: 10.1186/cc10274; PubMed Central PMCID: PMC3219023. 21682927 PMC3219023 · DOI
  32. [35]Shanley TP, Cvijanovich N, Lin R, Allen GL, Thomas NJ, Doctor A, et al. Genome-level longitudinal expression of signaling pathways and gene networks in pediatric septic shock. Mol Med. 2007; 13(9–10): 495– 508. doi: 10.2119/2007-00065.Shanley; PubMed Central PMCID: PMC2014731. 17932561 PMC2014731 · DOI
  33. [36]Cvijanovich N, Shanley TP, Lin R, Allen GL, Thomas NJ, Checchia P, et al. Validating the genomic signature of pediatric septic shock. Physiol Genomics. 2008; 34(1): 127– 34. doi: 10.1152/physiolgenomics.00025.2008; PubMed Central PMCID: PMC2440641. 18460642 PMC2440641 · DOI
  34. [37]Wong HR, Cvijanovich N, Allen GL, Lin R, Anas N, Meyer K, et al. Genomic expression profiling across the pediatric systemic inflammatory response syndrome, sepsis, and septic shock spectrum. Crit Care Med. 2009; 37(5): 1558– 66. doi: 10.1097/CCM.0b013e31819fcc08; PubMed Central PMCID: PMC2747356. 19325468 PMC2747356 · DOI
  35. [38]Wong HR, Cvijanovich N, Wheeler DS, Bigham MT, Monaco M, Odoms K, et al. Interleukin-8 as a stratification tool for interventional trials involving pediatric septic shock. American journal of respiratory and critical care medicine. 2008; 178(3): 276– 82. Epub 05/29. doi: 10.1164/rccm.200801-131OC. 18511707 PMC2542425 · DOI
  36. [39]Jin Nana1,2; Cheng Lixin1; Geng Qingshan1. Multiomics on Mental Stress-Induced Myocardial Ischemia: A Narrative Review. Heart and Mind 8(1):p 15– 20, Jan–Mar 2024. | doi: 10.4103/hm.HM-D-23-00021 · DOI
  37. [40]Li Xiaodan, Bai Yi, Tian Ci, Yang Fan, Fan Wenyang, Zhang Kuo and Ma Qingbian. “ Effects of metaraminol and norepinephrine on hemodynamics and kidney function in a miniature pig model of septic shock” Journal of Translational Internal Medicine, vol. 12, no. 3, 2024, pp. 253– 262. doi: 10.2478/jtim-2023-0131 39081274 PMC11284895 · DOI

Authors
Zheng, X., Meng, D., Chen, D., Wong, W.-K., To, K.-H., Zhu, L., Wu, J., Liang, Y., Leung, K.-S., Wong, M.-H., & Cheng, L.
Affiliations
  • Jinan University (CN)
  • Great Bay University (CN)
  • Capital Medical University (CN)
  • Chinese University of Hong Kong (HK)
  • City University of Hong Kong (HK)
  • Southern University of Science and Technology (CN)
Corresponding author
Cheng, Lixin
ORCID
Venue
PLOS Computational Biology
Publisher
Public Library of Science (PLoS)
Published
2024-10-21
Volume
20
Issue
10
Pages
e1012083
ISSN
  • 1553-734X (ISSN-L)
  • 1553-7358
DOI
10.1371/journal.pcbi.1012083
PMC
PMC11527285
OpenAlex
W4403598089
Cited by
14
References
39
Citations by year
2026: 5 · 2025: 7 · 2024: 2
FWCI
4.27
Type
journal article
Language
en
Update notices
new_version (2024-10-31)
Open access
Licence
Locations
  • PLoS Computational Biology (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • CityU Scholars (submittedVersion, cc-by)
Funders
  • National Natural Science Foundation of China (32370711, 32300554)
  • Shenzhen Hospital, Southern Medical University (A2303033)
  • Shenzhen Science and Technology Program (JCYJ20220530152409020)
Topics
  • Health Sciences › Medicine › Epidemiology › Sepsis Diagnosis and Treatment
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
Keywords
sepsis diagnosis, capsule networks, transformer models, single-cell RNA sequencing, explainable deep learning, cross-dataset transfer, gene modules, biological pathways, rare disease diagnosis
MeSH terms
Deep Learning, Humans, Sequence Analysis, RNA, Sepsis, Computational Biology, Single-Cell Analysis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review