Skip to content
2000
Volume 20, Issue 10
  • ISSN: 1574-8936
  • E-ISSN: 2212-392X

Abstract

Background

With the rapid evolution of single-cell RNA sequencing technology, the study of cellular heterogeneity in complex tissues has reached an unprecedented resolution. One critical task of the technology is cell-type annotation. However, challenges persist, particularly in annotating novel cell types.

Objective

Current methods rely heavily on well-annotated reference data, using correlation comparisons to determine cell types. However, identifying novel cells remains unstable due to the inherent complexity and heterogeneity of scRNA-seq data and cell types. To address this problem, we propose scADCA, a method based on anomaly detection, for identifying novel cell types and annotating the entire dataset.

Methods

The convolutional modules and fully connected networks are integrated into an autoencoder, and the reference dataset is trained to obtain the reconstruction errors. The threshold based on these errors can distinguish between novel and known cells in the query dataset. After novel cells are identified, a multinomial logistic regression model fully annotates the dataset.

Results

Using a simulation dataset, three real scRNA-seq pancreatic datasets, and a real scRNA-seq lung cancer cell line dataset, we compare scADCA with six other cell-type annotation methods, demonstrating competitive performance in terms of distinguished accuracy, full accuracy, -score, and confusion matrix.

Conclusion

In conclusion, the scADCA method can be further improved and expanded to achieve better performance and application effects in cell type annotation, which is helpful to improve the accuracy and reliability of cytology research and promote the development of single-cell omics.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cbio/10.2174/0115748936334071240903064630
2024-10-10
2025-12-21

  • From This Site

    /content/journals/cbio/10.2174/0115748936334071240903064630
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. MortazaviA. WilliamsB.A. McCueK. SchaefferL. WoldB. Mapping and quantifying mammalian transcriptomes by RNA-Seq.Nat. Methods20085762162810.1038/nmeth.122618516045
     [Google Scholar]
  2. SalibaA.E. WestermannA.J. GorskiS.A. VogelJ. Single-cell RNA-seq: Advances and future challenges.Nucleic Acids Res.201442148845886010.1093/nar/gku55525053837
     [Google Scholar]
  3. HanX. ZhouZ. FeiL. Construction of a human cell landscape at single-cell level.Nature2020581780830330910.1038/s41586‑020‑2157‑432214235
     [Google Scholar]
  4. ChengC. ChenW. JinH. ChenX. A review of single-cell rna-seq annotation, integration, and cell–cell communication.Cells20231215197010.3390/cells1215197037566049
     [Google Scholar]
  5. ZengH. What is a cell type and how to define it?Cell2022185152739275510.1016/j.cell.2022.06.03135868277
     [Google Scholar]
  6. ClarkeZ.A. AndrewsT.S. AtifJ. Tutorial: Guidelines for annotating single-cell transcriptomic maps using automated and manual methods.Nat. Protoc.20211662749276410.1038/s41596‑021‑00534‑034031612
     [Google Scholar]
  7. ZappiaL. PhipsonB. OshlackA. Exploring the single-cell RNA-seq analysis landscape with the scRNA-tools database.PLOS Comput. Biol.2018146e100624510.1371/journal.pcbi.100624529939984
     [Google Scholar]
  8. Diaz-MejiaJ.J. MengE.C. PicoA.R. Evaluation of methods to assign cell type labels to cell clusters from single-cell RNA-sequencing data.F1000 Res.20198829632310.12688/f1000research.18490.131508207
     [Google Scholar]
  9. AbdelaalT. MichielsenL. CatsD. A comparison of automatic cell identification methods for single-cell RNA sequencing data.Genome Biol.201920119410.1186/s13059‑019‑1795‑z31500660
     [Google Scholar]
  10. HuangQ. LiuY. DuY. GarmireL.X. Evaluation of cell type annotation R packages on single-cell RNA-seq data.Genomics Proteomics Bioinformatics202119226728110.1016/j.gpb.2020.07.00433359678
     [Google Scholar]
  11. KiselevV.Y. AndrewsT.S. HembergM. Publisher Correction: Challenges in unsupervised clustering of single-cell RNA-seq data.Nat. Rev. Genet.201920531010.1038/s41576‑019‑0095‑530670832
     [Google Scholar]
  12. NewmanA.M. LiuC.L. GreenM.R. Robust enumeration of cell subsets from tissue expression profiles.Nat. Methods201512545345710.1038/nmeth.333725822800
     [Google Scholar]
  13. CrowM. PaulA. BallouzS. HuangZ.J. GillisJ. Characterizing the replicability of cell types defined by single cell RNA-sequencing data using MetaNeighbor.Nat. Commun.20189188410.1038/s41467‑018‑03282‑029491377
     [Google Scholar]
  14. ZhangZ. LuoD. ZhongX. SCINA: A semi-supervised subtyping algorithm of single cells and bulk samples.Genes (Basel)201910753110.3390/genes1007053131336988
     [Google Scholar]
  15. WangJ. MaA. ChangY. scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses.Nat. Commun.2021121188210.1038/s41467‑021‑22197‑x33767197
     [Google Scholar]
  16. JiX. TsaoD. BaiK. TsaoM. XingL. ZhangX. scAnnotate: An automated cell-type annotation tool for single-cell RNA-sequencing data.Bioinformatics Advances202331vbad03010.1093/bioadv/vbad03036949780
     [Google Scholar]
  17. LiuH. LiH. SharmaA. scAnno: A deconvolution strategy-based automatic cell type annotation tool for single-cell RNA-sequencing data sets.Brief. Bioinform.2023243bbad17910.1093/bib/bbad17937183449
     [Google Scholar]
  18. DuanB. ZhuC. ChuaiG. Learning for single-cell assignment.Sci. Adv.2020644eabd085510.1126/sciadv.abd085533127686
     [Google Scholar]
  19. KiselevV.Y. YiuA. HembergM. scmap: Projection of single-cell RNA-seq data across data sets.Nat. Methods201815535936210.1038/nmeth.464429608555
     [Google Scholar]
  20. HuJ. LiX. HuG. LyuY. SusztakK. LiM. Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis.Nat. Mach. Intell.202021060761810.1038/s42256‑020‑00233‑733817554
     [Google Scholar]
  21. SkinniderM.A. SquairJ.W. FosterL.J. Evaluating measures of association for single-cell transcriptomics.Nat. Methods201916538138610.1038/s41592‑019‑0372‑430962620
     [Google Scholar]
  22. LiebermanY. RokachL. ShayT. Correction: CaSTLe - Classification of single cells by transfer learning: Harnessing the power of publicly available single cell RNA sequencing experiments to annotate new experiments.PLoS One20181311e020834910.1371/journal.pone.020834930481223
     [Google Scholar]
  23. BoufeaK. SethS. BatadaN.N. scID uses discriminant analysis to identify transcriptionally equivalent cell types across single-cell RNA-Seq data with batch effect.iScience202023310091410.1016/j.isci.2020.10091432151972
     [Google Scholar]
  24. ZhangA.W. O’FlanaganC. ChavezE.A. Probabilistic cell-type assignment of single-cell RNA-seq for tumor microenvironment profiling.Nat. Methods201916101007101510.1038/s41592‑019‑0529‑131501550
     [Google Scholar]
  25. KimH. LeeJ. KangK. YoonS. MarkerCount: A stable, count-based cell type identifier for single-cell RNA-seq experiments.Comput. Struct. Biotechnol. J.2022203120313210.1016/j.csbj.2022.06.01035782735
     [Google Scholar]
  26. TanY. CahanP. SingleCellNet: A computational tool to classify single cell RNA-Seq data across platforms and across species.Cell Syst.201992207213.e210.1016/j.cels.2019.06.00431377170
     [Google Scholar]
  27. LiuJ. YangM. YuY. XuH. LiK. ZhouX. Large language models in bioinformatics: Applications and perspectives.ArXiv2024
     [Google Scholar]
  28. FloresM. LiuZ. ZhangT. Deep learning tackles single-cell analysis—A survey of deep learning for scRNA-seq analysis.Brief. Bioinform.2022231bbab53110.1093/bib/bbab53134929734
     [Google Scholar]
  29. LazarosK. VlamosP. VrahatisA.G. Methods for cell-type annotation on scRNA-seq data: A recent overview.J. Bioinform. Comput. Biol.2023215234000210.1142/S021972002340002437743364
     [Google Scholar]
  30. LiuT. ChenT. ZhengW. LuoX. ZhaoH. scELMo: Embeddings from language models are good learners for single-cell data analysis.bioRxiv202310.1101/2023.12.07.569910
     [Google Scholar]
  31. HouW. JiZ. Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis.Nat. Methods20242181462146510.1038/s41592‑024‑02235‑438528186
     [Google Scholar]
  32. DongJ. ZhangY. WangF. scSemiAE: a deep model with semi-supervised learning for single-cell transcriptomics.BMC Bioinformatics202223116110.1186/s12859‑022‑04703‑035513780
     [Google Scholar]
  33. WangZ. WangH. ZhaoJ. ZhengC. scSemiAAE: A semi-supervised clustering model for single-cell RNA-seq data.BMC Bioinformatics202324121710.1186/s12859‑023‑05339‑437237310
     [Google Scholar]
  34. LiZ. WangY. Ganan-GomezI. CollaS. DoK.A. A machine learning-based method for automatically identifying novel cells in annotating single-cell RNA-seq data.Bioinformatics202238214885489210.1093/bioinformatics/btac61736083008
     [Google Scholar]
  35. DemestichasK. PeppesN. AlexakisT. AdamopoulouE. An advanced abnormal behavior detection engine embedding autoencoders for the investigation of financial transactions.Information (Basel)20211213410.3390/info12010034
     [Google Scholar]
  36. MuraroM.J. DharmadhikariG. GrünD. A single-cell transcriptome atlas of the human pancreas.Cell Syst.201634385394.e310.1016/j.cels.2016.09.00227693023
     [Google Scholar]
  37. TianL. DongX. FreytagS. Benchmarking single cell RNA-sequencing analysis pipelines using mixture control experiments.Nat. Methods201916647948710.1038/s41592‑019‑0425‑831133762
     [Google Scholar]
  38. SegerstolpeÅ. PalasantzaA. EliassonP. Single-cell transcriptome profiling of human pancreatic islets in health and type 2 diabetes.Cell Metab.201624459360710.1016/j.cmet.2016.08.02027667667
     [Google Scholar]
  39. BaronM. VeresA. WolockS.L. A single-cell transcriptomic map of the human and mouse pancreas reveals inter- and intra-cell population structure.Cell Syst.201634346360.e410.1016/j.cels.2016.08.01127667365
     [Google Scholar]
  40. TianL. XieY. XieZ. TianJ. TianW. AtacAnnoR: A reference-based annotation tool for single cell ATAC-seq data.Brief. Bioinform.2023245bbad26810.1093/bib/bbad26837497729
     [Google Scholar]
  41. FerréQ. ChènebyJ. PuthierD. CapponiC. BallesterB. Anomaly detection in genomic catalogues using unsupervised multi-view autoencoders.BMC Bioinformatics202122146010.1186/s12859‑021‑04359‑234563116
     [Google Scholar]
  42. ShafiqM. GuZ. Deep residual learning for image recognition: A survey.Appl. Sci. (Basel)20221218897210.3390/app12188972
     [Google Scholar]
  43. WangY LiuJ MisicJ MisicVB LvS ChangX Assessing optimizer impact on DNN model sensitivity to adversarial examples.IEEE Access201971527667610.1109/ACCESS.2019.2948658
     [Google Scholar]
  44. TorabiH. MirtaheriS.L. GrecoS. Practical autoencoder based anomaly detection by using vector reconstruction error.Cybersecurity20236111310.1186/s42400‑022‑00134‑9
     [Google Scholar]
  45. HuangY. ZhangP. Evaluation of machine learning approaches for cell-type identification from single-cell transcriptomics data.Brief. Bioinform.2021225bbab03510.1093/bib/bbab03533611343
     [Google Scholar]
  46. AmjoudAB AmrouchM Transfer learning for automatic image orientation detection using deep learning and logistic regression.IEEE Access 2022;1012854312855310.1109/ACCESS.2022.3225455
     [Google Scholar]
  47. AltanG. KutluY. AllahverdiN. Deep learning on computerized analysis of chronic obstructive pulmonary disease.IEEE J. Biomed. Health Inform.20202451344135010.1109/JBHI.2019.293139531369388
     [Google Scholar]
  48. AltanG. DeepOCT: An explainable deep learning architecture to analyze macular edema on OCT images.JESTECH20223410109110.1016/j.jestch.2021.101091
     [Google Scholar]
/content/journals/cbio/10.2174/0115748936334071240903064630
Loading
scADCA: An Anomaly Detection-Based scRNA-seq Dataset Cell Type Annotation Method for Identifying Novel Cells
Curr Bioinform 20, 904 (2025); https://doi.org/10.2174/0115748936334071240903064630
/content/journals/cbio/10.2174/0115748936334071240903064630
/content/journals/cbio/10.2174/0115748936334071240903064630
Loading

Data & Media loading...

Supplements

All supplementary materials mentioned in the article are presented in the documents of the Supplementary material.

file format download Download

  • Article Type:     Research Article
Keyword(s): Anomaly detection; autoencoder; cell type annotation; logistic regression model; novel cell; scRNA-seq data

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test