Skip to main content

Advertisement

SpringerLink
Log in

CASSL: A cell-type annotation method for single cell transcriptomics data using semi-supervised learning

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Single cell RNA sequencing (scRNA-seq) allows global transcriptomic profiling at a cellular resolution, thus, identifying underlying cell types and corresponding lineages. Such cell type identification and annotation rely heavily on models that learn by training themselves on a large amount of individual cells with accurate, annotated labels. Presently, this task of cell-type annotation is done based on inspection of marker genes from each of the statistically significant groups of cells. This is both challenging and time consuming. In this article, we have proposed a semi-supervised cell-type annotation method, called CASSL, based on Non-negative matrix factorization (NMF) coupled with recursive k-means algorithm. A semi-supervised model is capable of learning labels for a large amount of unlabelled data with the help of a limited amount of labelled data. The effectiveness of CASSL has been demonstrated on eight publicly available human and mice scRNA-seq datasets across varied organs and protocols. It has been able to correctly annotate majority of the unlabelled cells with high accuracy. It has also been evaluated for its correctness of clustering solution, robustness across varying percentage of missing labels, and time taken for execution. When compared with state-of-the-art unsupervised and semi-supervised cell-type annotation methods, CASSL has consistently outperformed others across all metrics for most of the datasets. It has also shown competitive results when compared against state-of-the-art supervised methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data and Code Availability

CASSL has been implemented in Python 3 in Google Colab and is freely available at https://doi.org/https://github.com/deeplearner87/CASSL. The data used in this study can be downloaded from https://doi.org/10.5281/zenodo.5681184.

References

  1. Abdelaal T, Michielsen L, Cats D, Hoogduin D, Mei H, Reinders MJT, Mahfouz A (2019) A comparison of automatic cell identification methods for single-cell rna sequencing data. Genome Biol 20(1):194. https://doi.org/10.1186/s13059-019-1795-z

    Article  Google Scholar 

  2. Alquicira-Hernandez J, Sathe A, Ji HP, Nguyen Q, Powell JE (2019) scpred: Accurate supervised method for cell-type classification from single-cell rna-seq data. Genome Biology 20(1):264. https://doi.org/10.1186/s13059-019-1862-5

    Article  Google Scholar 

  3. Baron M, Veres A, Wolock S, Faust A, Gaujoux R, Vetere A, Ryu J, Wagner B, Shen-Orr S, Klein A, Melton D, Yanai I (2016) A single-cell transcriptomic map of the human and mouse pancreas reveals inter- and intra-cell population structure. Cell Systems 3(4):346–360.e4. https://doi.org/10.1016/j.cels.2016.08.011

    Article  Google Scholar 

  4. Caliński T, Harabasz J (1974) A dendrite method for cluster analysis. Communications in Statistics 3(1):1–27. https://doi.org/10.1080/03610927408827101

    Article  MathSciNet  MATH  Google Scholar 

  5. Cao Y, Wang X, Peng G (2020) Scsa: A cell type annotation tool for single-cell rna-seq data. Front Genet 11:490. https://doi.org/10.3389/fgene.2020.00490

    Article  Google Scholar 

  6. Chung W, Eum HH, Lee HO, Lee KM, Lee HB, Kim KT, Ryu HS, Kim S, Lee JE, Park YH, Kan Z, Han W, Park WY (2017) Single-cell rna-seq enables comprehensive tumour and immune cell profiling in primary breast cancer. Nat Commun 8(1):15081. https://doi.org/10.1038/ncomms15081

    Article  Google Scholar 

  7. Dong Z, Alterovitz G (2020) netAE: Semi-supervised dimensionality reduction of single-cell RNA sequencing to facilitate cell labeling. Bioinforma 37(1):43–49. https://doi.org/10.1093/bioinformatics/btaa669, https://academic.oup.com/bioinformatics/article-pdf/37/1/43/37005969/btaa669_supplementary_data.pdf

    Article  Google Scholar 

  8. Elyanow R, Dumitrascu B, Engelhardt BE, Raphael BJ (2020) netnmf-sc: Leveraging gene–gene interactions for imputation and dimensionality reduction in single-cell expression analysis. Genome Res 30(2):195–204

    Article  Google Scholar 

  9. Enge M, Arda HE, Mignardi M, Beausang J, Bottino R, Kim SK, Quake SR (2017) Single-cell analysis of human pancreas reveals transcriptional signatures of aging and somatic mutation patterns. Cell 171(2):321–330.e14. https://doi.org/10.1016/j.cell.2017.09.004, https://www.sciencedirect.com/science/article/pii/S009286741731053X

    Article  Google Scholar 

  10. Feng C, Liu S, Zhang H, Guan R, Li D, Zhou F, Liang Y, Feng X (2020) Dimension reduction and clustering models for single-cell rna sequencing data: a comparative study. Int J Mol Sci 21(6):2181

    Article  Google Scholar 

  11. Gan Y, Li N, Zou G, Xin Y, Guan J (2018) Identification of cancer subtypes from single-cell rna-seq data using a consensus clustering method. BMC Med Genet 11(6):117. https://doi.org/10.1186/s12920-018-0433-z

    Article  Google Scholar 

  12. Gowda HS, Suhil M, Guru DS, Raju LN (2017) Semi-supervised text categorization using recursive k-means clustering. CoRR arXiv:abs/1706.07913

  13. Grün D, Lyubimova A, Kester L, Wiebrands K, Basak O, Sasaki N, Clevers H, van Oudenaarden A (2015) Single-cell messenger rna sequencing reveals rare intestinal cell types. Nature 525(7568):251–255. https://doi.org/10.1038/nature14966

    Article  Google Scholar 

  14. Guo M, Wang H, Potter SS, Whitsett JA, Xu Y (2015) Sincera: A pipeline for single-cell rna-seq profiling analysis. PLoS Computational Biology 11(11):e1004575–e1004575. https://doi.org/10.1371/journal.pcbi.1004575, https://pubmed.ncbi.nlm.nih.gov/26600239

    Article  Google Scholar 

  15. Han X, Wang R, Zhou Y, Fei L, Sun H, Lai S, Saadatpour A, Zhou Z, Chen H, Ye F, Huang D, Xu Y, Huang W, Jiang M, Jiang X, Mao J, Chen Y, Lu C, Xie J, Fang Q, Wang Y, Yue R, Li T, Huang H, AYuan GC, Chen M, Guo G (2018) Mapping the mouse cell atlas by microwell-seq. Cell 172(5):1091–1107.e17. https://doi.org/10.1016/j.cell.2018.02.001, https://www.sciencedirect.com/science/article/pii/S0092867418301168

    Article  Google Scholar 

  16. Hao Y, Hao S, Andersen-Nissen E, Mauck WM, Zheng S, Butler A, Lee MJ, Wilk AJ, Darby C, Zager M, Hoffman P, Stoeckius M, Papalexi E, Mimitou EP, Jain J, Srivastava A, Stuart T, Fleming LM, Yeung B, Rogers AJ, McElrath JM, Blish CA, Gottardo R, Smibert P, Satija R (2021) Integrated analysis of multimodal single-cell data. Cell 184(13):3573–3587.e29. https://doi.org/10.1016/j.cell.2021.04.048, https://www.sciencedirect.com/science/article/pii/S0092867421005833

    Article  Google Scholar 

  17. Haque A, Engel J, Teichmann SA, Lönnberg T (2017) A practical guide to single-cell rna-sequencing for biomedical research and clinical applications. Genome Med 9(1):75. https://doi.org/10.1186/s13073-017-0467-4

    Article  Google Scholar 

  18. Huang Q, Liu Y, Du Y, Garmire LX (2021) Evaluation of cell type annotation r packages on single-cell rna-seq data. Genomics, Proteomics & Bioinformatics 19(2):267–281

    Article  Google Scholar 

  19. Hwang B, Lee JH, Bang D (2018) Single-cell rna sequencing technologies and bioinformatics pipelines. Exp Mol Med 50(8):1–14. https://doi.org/10.1038/s12276-018-0071-8, https://pubmed.ncbi.nlm.nih.gov/30089861, 30089861[pmid]

    Article  Google Scholar 

  20. Jaitin DA, Weiner A, Yofe I, Lara-Astiaso D, Keren-Shaul H, David E, Salame TM, Tanay A, van Oudenaarden A, Amit I (2016) Dissecting immune circuits by linking crispr-pooled screens with single-cell rna-seq. Cell 167(7):1883–1896.e15. https://doi.org/10.1016/j.cell.2016.11.039, https://www.sciencedirect.com/science/article/pii/S0092867416316117

    Article  Google Scholar 

  21. Kim T, Lo K, Geddes TA, Kim HJ, Yang JYH, Yang P (2019) screclassify: Post hoc cell type classification of single-cell rna-seq data. BMC Genomics 20(9):913. https://doi.org/10.1186/s12864-019-6305-x

    Article  Google Scholar 

  22. Kiselev VY, Kirschner K, Schaub MT, Andrews T, Yiu A, Chandra T, Natarajan KN, Reik W, Barahona M, Green AR, Hemberg M (2017) Sc3: Consensus clustering of single-cell rna-seq data. Nat Methods 14(5):483–486. https://doi.org/10.1038/nmeth.4236

    Article  Google Scholar 

  23. Kiselev VY, Yiu A, Hemberg M (2018) scmap: Projection of single-cell rna-seq data across data sets. Nat Methods 15(5):359–362. https://doi.org/10.1038/nmeth.4644

    Article  Google Scholar 

  24. Kiselev VY, Andrews TS, Hemberg M (2019) Challenges in unsupervised clustering of single-cell rna-seq data. Nat Rev Genet 20(5):273–282. https://doi.org/10.1038/s41576-018-0088-9

    Article  Google Scholar 

  25. Kolodziejczyk A, Kim JK, Svensson V, Marioni J, Teichmann S (2015) The technology and biology of single-cell rna sequencing. Mol Cell 58(4):610–620. https://doi.org/10.1016/j.molcel.2015.04.005, https://www.sciencedirect.com/science/article/pii/S1097276515002610

    Article  Google Scholar 

  26. Lee D, Seung HS (2001) Algorithms for non-negative matrix factorization. In: Leen T, Dietterich T, Tresp V (eds) Advances in neural information processing systems, MIT Press, vol 13, https://proceedings.neurips.cc/paper/2000/file/f9d1152547c0bde01830b7e8bd60024c-Paper.pdf

  27. Lin P, Troup M, Ho JWK (2017) Cidr: Ultrafast and accurate clustering through imputation for single-cell rna-seq data. Genome Biol 18(1):59. https://doi.org/10.1186/s13059-017-1188-0

    Article  Google Scholar 

  28. authors listed N (2017) What Is Your Conceptual Definition of “Cell Type” in the Context of a Mature Organism?. Cell Syst 4(3):255–259

    Article  Google Scholar 

  29. van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605. http://www.jmlr.org/papers/v9/vandermaaten08a.html

    MATH  Google Scholar 

  30. Moon KR, van Dijk D, Wang Z, Gigante S, Burkhardt DB, Chen WS, Yim K, Avd Elzen, Hirn MJ, Coifman RR, Ivanova NB, Wolf G, Krishnaswamy S (2019) Visualizing structure and transitions in high-dimensional biological data. Nat Biotechnol 37(12):1482–1492. https://doi.org/10.1038/s41587-019-0336-3

    Article  Google Scholar 

  31. Petropoulos S, Edsgärd D, Reinius B, Deng Q, Panula SP, Codeluppi S, Reyes AP, Linnarsson S, Sandberg R, Lanner F (2016) Single-cell rna-seq reveals lineage and x chromosome dynamics in human preimplantation embryos. Cell 167(1):285–285. https://doi.org/10.1016/j.cell.2016.08.009, https://pubmed.ncbi.nlm.nih.gov/27662094

    Article  Google Scholar 

  32. Picelli S, Björklund ÅK, Faridani OR, Sagasser S, Winberg G, Sandberg R (2013) Smart-seq2 for sensitive full-length transcriptome profiling in single cells. Nat Methods 10(11):1096–1098. https://doi.org/10.1038/nmeth.2639

    Article  Google Scholar 

  33. Pierson E, Yau C (2015) Zifa: Dimensionality reduction for zero-inflated single-cell gene expression analysis. Genome Biol 16(1):241. https://doi.org/10.1186/s13059-015-0805-z

    Article  Google Scholar 

  34. Ranjan B, Schmidt F, Sun W, Park J, Honardoost MA, Tan J, Arul Rayan N, Prabhakar S (2021) scconsensus: Combining supervised and unsupervised clustering for cell type identification in single-cell rna sequencing data. BMC Bioinformatics 22(1):186. https://doi.org/10.1186/s12859-021-04028-4

    Article  Google Scholar 

  35. Rizvi AH, Camara PG, Kandror EK, Roberts TJ, Schieren I, Maniatis T, Rabadan R (2017) Single-cell topological rna-seq analysis reveals insights into cellular differentiation and development. Nat Biotechnol 35(6):551–560. https://doi.org/10.1038/nbt.3854

    Article  Google Scholar 

  36. Rozenblatt-Rosen O, Shin JW, Rood JE, Hupalowska A, Ardlie K, Clatworthy M, Carninci P, Enard W, Greenleaf W, Heyn H, Lein E, Levin JZ, Linnarsson S, Lundberg E, Meyer K, Navin N, Nolan G, Teichmann S, Voet T, Zhuang X, Regev A, Standards HCA, Group TW (2021) Building a high-quality human cell atlas. Nat Biotechnol 39(2):149–153. https://doi.org/10.1038/s41587-020-00812-4

    Article  Google Scholar 

  37. Williams S (2019) celaref: Single-cell RNAseq cell cluster labelling by reference. Monash University, Australia. https://bioconductor.org/packages/celaref

  38. Satija R, Farrell JA, Gennert D, Schier AF, Regev A (2015) Spatial reconstruction of single-cell gene expression data. Nat Biotechnol 33(5):495–502. https://doi.org/10.1038/nbt.3192

    Article  Google Scholar 

  39. Segerstolpe Å, Palasantza A, Eliasson P, Andersson EM, Andréasson AC, Sun X, Picelli S, Sabirsh A, Clausen M, Bjursell MK, Smith DM, Kasper M, Ämmälä C, Sandberg R (2016) Single-cell transcriptome profiling of human pancreatic islets in health and type 2 diabetes. Cell Metabolism 24(4):593–607. https://doi.org/10.1016/j.cmet.2016.08.020, https://pubmed.ncbi.nlm.nih.gov/27667667

    Article  Google Scholar 

  40. Shao X, Liao J, Lu X, Xue R, Ai N, Fan X (2020) sccatch: Automatic annotation on cell types of clusters from single-cell rna sequencing data. iScience 23(3):100882. https://doi.org/10.1016/j.isci.2020.100882, https://www.sciencedirect.com/science/article/pii/S2589004220300663

    Article  Google Scholar 

  41. Stegle O, Teichmann SA, Marioni JC (2015) Computational and analytical challenges in single-cell transcriptomics. Nat Rev Genet 16(3):133–145. https://doi.org/10.1038/nrg3833

    Article  Google Scholar 

  42. Trapnell C, Cacchiarelli D, Grimsby J, Pokharel P, Li S, Morse M, Lennon NJ, Livak KJ, Mikkelsen TS, Rinn JL (2014) The dynamics and regulators of cell fate decisions are revealed by pseudotemporal ordering of single cells. Nat Biotechnol 32(4):381–386. https://doi.org/10.1038/nbt.2859

    Article  Google Scholar 

  43. Trong TN, Mehtonen J, González G, Kramer R, Hautamäki V, Heinäniemi M (2020) Semisupervised generative autoencoder for single-cell data. Journal of Computational Biology : A Journal of Computational Molecular Cell Biology 27(8):1190–1203. https://doi.org/10.1089/cmb.2019.0337, https://pubmed.ncbi.nlm.nih.gov/31794242

    Article  Google Scholar 

  44. Usoskin D, Furlan A, Islam S, Abdo H, Lönnerberg P, Lou D, Hjerling-Leffler J, Haeggström J, Kharchenko O, Kharchenko PV, Linnarsson S, Ernfors P (2015) Unbiased classification of sensory neuron types by large-scale single-cell rna sequencing. Nat Neurosci 18(1):145–153. https://doi.org/10.1038/nn.3881

    Article  Google Scholar 

  45. Vieira Braga FA, Kar G, Berg M, Carpaij OA, Polanski K, Simon LM, Brouwer S, Gomes T, Hesse L, Jiang J, Fasouli ES, Efremova M, Vento-Tormo R, Talavera-López C, Jonker MR, Affleck K, Palit S, Strzelecka PM, Firth HV, Mahbubani KT, Cvejic A, Meyer KB, Saeb-Parsy K, Luinge M, Brandsma CA, Timens W, Angelidis I, Strunz M, Koppelman GH, van Oosterhout AJ, Schiller HB, Theis FJ, van den Berge M, Nawijn MC, Teichmann SA (2019) A cellular census of human lungs identifies novel cell states in health and in asthma. Nat Med 25(7):1153–1163. https://doi.org/10.1038/s41591-019-0468-5

    Article  Google Scholar 

  46. Villani AC, Satija R, Reynolds G, Sarkizova S, Shekhar K, Fletcher J, Griesbeck M, Butler A, Zheng S, Lazo S, Jardine L, Dixon D, Stephenson E, Nilsson E, Grundberg I, McDonald D, Filby A, Li W, De Jager PL, Rozenblatt-Rosen O, Lane AA, Haniffa M, Regev A, Hacohen N (2017) Single-cell rna-seq reveals new types of human blood dendritic cells, monocytes, and progenitors. Science 356(6335), https://doi.org/10.1126/science.aah4573, https://science.sciencemag.org/content/356/6335/eaah4573

  47. Wang B, Zhu J, Pierson E, Ramazzotti D, Batzoglou S (2017) Visualization and analysis of single-cell rna-seq data by kernel-based similarity learning. Nat Methods 14(4):414–416. https://doi.org/10.1038/nmeth.4207

    Article  Google Scholar 

  48. Wei Z, Zhang S (2021) CALLR: A semi-supervised cell-type annotation method for single-cell rna sequencing data. Bioinformatics 37(Supplement_1):i51–i58

    Article  Google Scholar 

  49. Wolf FA, Angerer P, Theis FJ (2018) Scanpy: Large-scale single-cell gene expression data analysis. Genome Biol 19(1):15. https://doi.org/10.1186/s13059-017-1382-0

    Article  Google Scholar 

  50. Wu P, An M, Zou HR, Zhong CY, Wang W, Wu CP (2020) A robust semi-supervised nmf model for single cell rna-seq data. PeerJ 8:e10091–e10091. https://doi.org/10.7717/peerj.10091,https://pubmed.ncbi.nlm.nih.gov/33088619

    Article  Google Scholar 

  51. Xu C, Su Z (2015) Identification of cell types from single-cell transcriptomes using a novel clustering method. Bioinformatics 31(12):1974–1980. https://doi.org/10.1093/bioinformatics/btv088, https://academic.oup.com/bioinformatics/article-pdf/31/12/1974/17100675/btv088.pdf

    Article  Google Scholar 

  52. Yang L, Jin R, Sukthankar R (2008) Semi-supervised learning with weakly-related unlabeled data: Towards better categorization. In: Proceedings of the 21st international conference on neural information processing, systems, Curran Associates Inc., Red Hook, NY, USA, NIPS’08, p 1857– 1864

  53. Zeisel A, Muñoz-Manchado AB, Codeluppi S, Lönnerberg P, La Manno G, Juréus A, Marques S, Munguba H, He L, Betsholtz C, Rolny C, Castelo-Branco G, Hjerling-Leffler J, Linnarsson S (2015) Cell types in the mouse cortex and hippocampus revealed by single-cell rna-seq. Science 347 (6226):1138–1142. https://doi.org/10.1126/science.aaa1934, https://science.sciencemag.org/content/347/6226/1138

    Article  Google Scholar 

  54. Zhang S, Yang L, Yang J, Lin Z, Ng MK (2020) Dimensionality reduction for single cell RNA sequencing data using constrained robust non-negative matrix factorization. NAR Genomics and Bioinformatics 2(3), https://doi.org/10.1093/nargab/lqaa064, lqaa064, https://academic.oup.com/nargab/article-pdf/2/3/lqaa064/34054697/lqaa064_supplemental_file.pdf

  55. Zhang W, Tang X, Yoshida T (2015) Tesc: An approach to text classification using semi-supervised clustering. Knowl Based Syst 75:152–160

    Article  Google Scholar 

  56. Zhang Z, Luo D, Zhong X, Choi JH, Ma Y, Wang S, Mahrt E, Guo W, Stawiski EW, Modrusan Z, Seshagiri S, Kapur P, Hon GC, Brugarolas J, Wang T (2019) Scina: A semi-supervised subtyping algorithm of single cells and bulk samples. Genes 10(7):531. https://doi.org/10.3390/genes10070531, https://pubmed.ncbi.nlm.nih.gov/31336988

    Article  Google Scholar 

  57. Zhao X, Wu S, Fang N, Sun X, Fan J (2019) Evaluation of single-cell classifiers for single-cell RNA sequencing data sets. Briefings in Bioinformatics 21(5):1581–1595. https://doi.org/10.1093/bib/bbz096, https://academic.oup.com/bib/article-pdf/21/5/1581/36543433/bbz096.pdf

    Article  Google Scholar 

  58. Zhu X, Goldberg AB (2009) Introduction to semi-supervised learning. http://site.ebrary.com/id/10515619

Download references

Acknowledgements

RKD acknowledges SyMeC Project grant [BT/Med-II/NIBMG/SyMeC/2014/Vol. II] given to the Indian Statistical Institute by the Department of Biotechnology (DBT), Government of India.

Author information

Authors and Affiliations

  1. A. K. Choudhury School of Information Technology, University of Calcutta, JD - II, Sector III, Salt Lake City, Kolkata, 700106, India

    Dibyendu Bikash Seal

  2. Novo Nordisk A/S, Novo Nordisk Park 1, 2760, Måløv, Denmark

    Vivek Das

  3. Machine Intelligence Unit, Indian Statistical Institute, 203 Barrackpore Trunk Road, Kolkata, 700108, India

    Rajat K. De

Authors
  1. Dibyendu Bikash Seal
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vivek Das
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rajat K. De
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization of Methodology: DBS, VD, RKD. Data Curation, Data analysis, Formal analysis, Visualization, Investigation, Implementation, Validation, Original draft preparation: DBS, VD. Validation, Reviewing, Editing, Overall Supervision: RKD.

Corresponding author

Correspondence to Rajat K. De.

Ethics declarations

Conflict of Interests

VD works as a Senior Research Scientist at Novo Nordisk A/S, Måløv.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

(TEX 5.90 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Seal, D.B., Das, V. & De, R.K. CASSL: A cell-type annotation method for single cell transcriptomics data using semi-supervised learning. Appl Intell 53, 1287–1305 (2023). https://doi.org/10.1007/s10489-022-03440-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03440-4

Keywords

Search

Navigation