CoChat
Sign Up
Cited by 92Gene expression and cancer classificationBioinformatics and Genomic NetworksBreast Cancer Treatment Studies

Performance comparison of deep learning autoencoders for cancer subtype detection using multi-omics data

Open access
Franco, Edian F., Rana, Pratip, Cruz, Aline, Calderón, Víctor V., Azevedo, Vasco, Ramos, Rommel T. J., Ghosh, Preetam·2021·Cancers
DOI 10.3390/cancers13092013PMC PMC8122584

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

A heterogeneous disease such as cancer is activated through multiple pathways and different perturbations. Depending upon the activated pathway(s), the survival of the patients varies significantly and shows different efficacy to various drugs. Therefore, cancer subtype detection using genomics level data is a significant research problem. Subtype detection is often a complex problem, and in most cases, needs multi-omics data fusion to achieve accurate subtyping. Different data fusion and subtyping approaches have been proposed over the years, such as kernel-based fusion, matrix factorization, and deep learning autoencoders. In this paper, we compared the performance of different deep learning autoencoders for cancer subtype detection. We performed cancer subtype detection on four different cancer types from The Cancer Genome Atlas (TCGA) datasets using four autoencoder implementations. We also predicted the optimal number of subtypes in a cancer type using the silhouette score and found that the detected subtypes exhibit significant differences in survival profiles. Furthermore, we compared the effect of feature selection and similarity measures for subtype detection. For further evaluation, we used the Glioblastoma multiforme (GBM) dataset and identified the differentially expressed genes in each of the subtypes. The results obtained are consistent with other genomic studies and can be corroborated with the involved pathways and biological functions. Thus, it shows that the results from the autoencoders, obtained through the interaction of different datatypes of cancer, can be used for the prediction and characterization of patient subgroups and survival profiles.

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 · 10.3390/cancers13092013

Cites

6 of 6 references verified0 citation errors · 0 not checkable

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?

  • In Franco et al.'s comparison, regular AE and VAE architectures seemed to outperform other AEs.

    “Though regular AE and VAE architectures seemed to outperform other AEs, the strong variation between performance on different data sets indicate the importance of choice of architecture.”

    From Multimodal deep learning for biomedical data fusion: a review (2022) · cites this paper as [33]

  • Strong variation between performance on different data sets indicates the importance of choice of architecture.

    “Though regular AE and VAE architectures seemed to outperform other AEs, the strong variation between performance on different data sets indicate the importance of choice of architecture.”

    From Multimodal deep learning for biomedical data fusion: a review (2022) · cites this paper as [33]

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 45

  1. [1]Rana P. Berry C. Ghosh P. Fong S.S. Recent advances on constraint-based models by integrating machine learning Curr. Opin. Biotechnol. 2020 64 85 91 10.1016/j.copbio.2019.11.007 31812921 · DOI
  2. [2]Martini P. Chiogna M. Calura E. Romualdi C. MOSClip: Multi-omic and survival pathway analysis for the identification of survival associated gene and modules Nucleic Acids Res. 2019 47 e80 10.1093/nar/gkz324 31049575 PMC6698707 · DOI
  3. [3]Ramazzotti D. Lal A. Wang B. Batzoglou S. Sidow A. Multi-omic tumor data reveal diversity of molecular mechanisms that correlate with survival Nat. Commun. 2018 9 1 14 10.1038/s41467-018-06921-8 30367051 PMC6203719 · DOI
  4. [5]Chung R.H. Kang C.Y. A multi-omics data simulator for complex disease studies and its application to evaluate multi-omics data analysis methods for disease classification GigaScience 2019 8 giz045 10.1093/gigascience/giz045 31029063 PMC6486474 · DOI
  5. [6]Huang S. Chaudhary K. Garmire L.X. More is better: Recent progress in multi-omics data integration methods Front. Genet. 2017 8 84 10.3389/fgene.2017.00084 28670325 PMC5472696 · DOI
  6. [8]Wang B. Mezlini A.M. Demir F. Fiume M. Tu Z. Brudno M. Haibe-Kains B. Goldenberg A. Similarity network fusion for aggregating data types on a genomic scale Nat. Methods 2014 11 333 10.1038/nmeth.2810 24464287 · DOI · Paper page
  7. [9]Chiu Y.C. Chen H.I.H. Zhang T. Zhang S. Gorthi A. Wang L.J. Huang Y. Chen Y. Predicting drug response of tumors from integrated genomic profiles by deep neural networks BMC Med. Genom. 2019 12 18 PMC6357352 30704458
  8. [10]Luck M. Sylvain T. Cardinal H. Lodi A. Bengio Y. Deep learning for patient-specific kidney graft survival analysis arXiv 2017 1705.10245
  9. [12]Marivate V.N. Nelwamodo F.V. Marwala T. Autoencoder, principal component analysis and support vector regression for data imputation arXiv 2007 0709.2506
  10. [14]Zhang Z. Zhao Y. Liao X. Shi W. Li K. Zou Q. Peng S. Deep learning in omics: A survey and guideline Briefings Funct. Genom. 2018 18 41 57 10.1093/bfgp/ely030 30265280 · DOI
  11. [15]Wang S. Ding Z. Fu Y. Feature selection guided auto-encoder Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence San Francisco, CA, USA 4–9 February 2017
  12. [16]Chaudhary K. Poirion O.B. Lu L. Garmire L.X. Deep learning–based multi-omics integration robustly predicts survival in liver cancer Clin. Cancer Res. 2018 24 1248 1259 10.1158/1078-0432.CCR-17-0853 28982688 PMC6050171 · DOI · Paper page
  13. [17]Tan J. Ung M. Cheng C. Greene C.S. Unsupervised feature construction and knowledge extraction from genome-wide assays of breast cancer with denoising autoencoders Proceedings of the Pacific Symposium on Biocomputing Co-Chairs Kohala Coast, HI, USA 4–8 January 2015 World Scientific Singapore 2014 132 143 PMC4299935 25592575
  14. [18]Ronen J. Hayat S. Akalin A. Evaluation of colorectal cancer subtypes and cell lines using deep learning Life Sci. Alliance 2019 2 10.26508/lsa.201900517 PMC6892438 31792061 · DOI
  15. [21]Sheet S. Ghosh A. Ghosh R. Chakrabarti A. Identification of Cancer Mediating Biomarkers using Stacked Denoising Autoencoder Model-An Application on Human Lung Data Procedia Comput. Sci. 2020 167 686 695 10.1016/j.procs.2020.03.341 · DOI
  16. [22]Makki J. Diversity of breast carcinoma: Histological subtypes and clinical relevance Clin. Med. Insights Pathol. 2015 8 CPath.S31563 10.4137/CPath.S31563 26740749 PMC4689326 · DOI
  17. [23]Siegel R.L. Miller K.D. Jemal A. Cancer statistics, 2016 CA Cancer J. Clin. 2016 66 7 30 10.3322/caac.21332 26742998 · DOI · Paper page
  18. [26]Chow W.H. Dong L.M. Devesa S.S. Epidemiology and risk factors for kidney cancer Nat. Rev. Urol. 2010 7 245 10.1038/nrurol.2010.46 20448658 PMC3012455 · DOI
  19. [27]Colaprico A. Silva T.C. Olsen C. Garofano L. Cava C. Garolini D. Sabedot T.S. Malta T.M. Pagnotta S.M. Castiglioni I. TCGAbiolinks: An R/Bioconductor package for integrative analysis of TCGA data Nucleic Acids Res. 2016 44 e71 10.1093/nar/gkv1507 26704973 PMC4856967 · DOI
  20. [28]Xu T. Le T.D. Liu L. Su N. Wang R. Sun B. Colaprico A. Bontempi G. Li J. CancerSubtypes: An R/Bioconductor package for molecular cancer subtype identification, validation and visualization Bioinformatics 2017 33 3131 3133 10.1093/bioinformatics/btx378 28605519 · DOI
  21. [29]Wu C. Ma S. A selective review of robust variable selection with applications in bioinformatics Briefings Bioinform. 2015 16 873 883 10.1093/bib/bbu046 PMC4570200 25479793 · DOI
  22. [30]LeCun Y. Bengio Y. Hinton G. Deep learning Nature 2015 521 436 444 10.1038/nature14539 26017442 · DOI · Paper page
  23. [31]Kingma D.P. Welling M. Auto-encoding variational bayes arXiv 2013 1312.6114
  24. [32]Doersch C. Tutorial on variational autoencoders arXiv 2016 1606.05908
  25. [35]Kingma D.P. Ba J. Adam: A method for stochastic optimization arXiv 2014 1412.6980
  26. [36]MacQueen J. Some methods for classification and analysis of multivariate observations Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability Oakland, CA, USA 21 June–18 July 1965 Volume 1 281 297
  27. [37]Kaufman L. Rousseeuw P.J. Partitioning around medoids (program pam) Finding Groups in Data: An Introduction to Cluster Analysis John Wiley & Sons, Inc. Hoboken, NJ, USA 1990 Volume 344 68 125
  28. [38]Cox D.R. Regression models and life-tables J. R. Stat. Soc. Ser. Methodol. 1972 34 187 202 10.1111/j.2517-6161.1972.tb00899.x · DOI · Paper page
  29. [39]Wu C. Zhou F. Ren J. Li X. Jiang Y. Ma S. A selective review of multi-level omics data integration using variable selection High-Throughput 2019 8 4 10.3390/ht8010004 PMC6473252 30669303 · DOI
  30. [41]Yu G. Wang L.G. Han Y. He Q.Y. clusterProfiler: An R package for comparing biological themes among gene clusters Omics J. Integr. Biol. 2012 16 284 287 10.1089/omi.2011.0118 PMC3339379 22455463 · DOI · Paper page
  31. [42]Ashburner M. Ball C.A. Blake J.A. Botstein D. Butler H. Cherry J.M. Davis A.P. Dolinski K. Dwight S.S. Eppig J.T. Gene ontology: Tool for the unification of biology Nat. Genet. 2000 25 25 29 10.1038/75556 10802651 PMC3037419 · DOI · Paper page
  32. [43]Verhaak R.G. Hoadley K.A. Purdom E. Wang V. Qi Y. Wilkerson M.D. Miller C.R. Ding L. Golub T. Mesirov J.P. Integrated genomic analysis identifies clinically relevant subtypes of glioblastoma characterized by abnormalities in PDGFRA, IDH1, EGFR, and NF1 Cancer Cell 2010 17 98 110 10.1016/j.ccr.2009.12.020 20129251 PMC2818769 · DOI · Paper page
  33. [44]Wang H. Zheng H. Wang J. Wang C. Wu F.X. Integrating omics data with a multiplex network-based approach for the identification of cancer subtypes IEEE Trans. Nanobiosci. 2016 15 335 342 10.1109/TNB.2016.2556640 28113909 · DOI
  34. [45]Ji’an Yang L.W. Xu Z. Wu L. Liu B. Wang J. Tian D. Xiong X. Chen Q. Integrated analysis to evaluate the prognostic value of signature mRNAs in glioblastoma multiforme Front. Genet. 2020 11 253 10.3389/fgene.2020.00253 32296458 PMC7136556 · DOI
  35. [46]Zhang M. Lv X. Jiang Y. Li G. Qiao Q. Identification of aberrantly methylated differentially expressed genes in glioblastoma multiforme and their association with patient survival Exp. Ther. Med. 2019 18 2140 2152 10.3892/etm.2019.7807 31452706 PMC6704589 · DOI
  36. [47]Zhao F. Cannons J.L. Dutta M. Griffiths G.M. Schwartzberg P.L. Positive and negative signaling through SLAM receptors regulate synapse organization and thresholds of cytolysis Immunity 2012 36 1003 1016 10.1016/j.immuni.2012.05.017 22683123 PMC3389133 · DOI
  37. [48]Xiong D.D. Xu W.Q. He R.Q. Dang Y.W. Chen G. Luo D.Z. In silico analysis identified miRNA-based therapeutic agents against glioblastoma multiforme Oncol. Rep. 2019 41 2194 2208 10.3892/or.2019.7022 30816530 PMC6412522 · DOI
  38. [49]Südhof T.C. Towards an understanding of synapse formation Neuron 2018 100 276 293 10.1016/j.neuron.2018.09.040 30359597 PMC6226307 · DOI · Paper page
  39. [50]Dabrowski A. Terauchi A. Strong C. Umemori H. Distinct sets of FGF receptors sculpt excitatory and inhibitory synaptogenesis Development 2015 142 1818 1830 10.1242/dev.115568 25926357 PMC4440923 · DOI
  40. [51]Yool A.J. Ramesh S.A. Molecular targets for combined therapeutic strategies to limit glioblastoma cell migration and invasion Front. Pharmacol. 2020 11 358 10.3389/fphar.2020.00358 32292341 PMC7118801 · DOI
  41. [52]Corsi L. Mescola A. Alessandrini A. Glutamate receptors and glioblastoma multiforme: An old “Route” for new perspectives Int. J. Mol. Sci. 2019 20 1796 10.3390/ijms20071796 30978987 PMC6479730 · DOI
  42. [53]Graner M.W. Roles of extracellular vesicles in high-grade gliomas: Tiny particles with outsized influence Annu. Rev. Genom. Hum. Genet. 2019 20 331 357 10.1146/annurev-genom-083118-015324 30978305 PMC6717010 · DOI
  43. [54]Van der Pol E. Böing A.N. Harrison P. Sturk A. Nieuwland R. Classification, functions, and clinical relevance of extracellular vesicles Pharmacol. Rev. 2012 64 676 705 10.1124/pr.112.005983 22722893 · DOI
  44. [55]Yáñez-Mó M. Siljander P.R.M. Andreu Z. Bedina Zavec A. Borràs F.E. Buzas E.I. Buzas K. Casal E. Cappello F. Carvalho J. Biological properties of extracellular vesicles and their physiological functions J. Extracell. Vesicles 2015 4 27066 10.3402/jev.v4.27066 25979354 PMC4433489 · DOI · Paper page
  45. [56]Simon T. Jackson E. Giamas G. Breaking through the glioblastoma micro-environment via extracellular vesicles Oncogene 2020 39 4477 4490 10.1038/s41388-020-1308-2 32366909 PMC7269906 · DOI

Cited by

Sorted by citations

Authors
Franco, E. F., Rana, P., Cruz, A., Calderón, V. V., Azevedo, V., Ramos, R. T. J., & Ghosh, P.
Affiliations
  • Instituto Tecnológico de Santo Domingo (DO)
  • Virginia Commonwealth University (US)
  • Universidade Federal do Pará (BR)
  • Universidade Federal de Minas Gerais (BR)
Corresponding author
  • Franco, Edian F.
  • Rana, Pratip
  • Ramos, Rommel T. J.
  • Ghosh, Preetam
ORCID
Venue
Cancers
Publisher
MDPI AG
Published
2021-04-22
Volume
13
Issue
9
Pages
2013
ISSN
2072-6694 (ISSN-L)
DOI
10.3390/cancers13092013
PMC
PMC8122584
OpenAlex
W3154403094
Cited by
92
References
6
Citations by year
2026: 10 · 2025: 29 · 2024: 17 · 2023: 16 · 2022: 13 · 2021: 7
FWCI
4.16
Type
journal article
Language
en
Open access
Licence
Locations
  • Cancers (publishedVersion, cc-by)
  • Preprints.org (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (8881.187658/2018-0)
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico (001)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Breast Cancer Treatment Studies
Keywords
multi-omics integration, TCGA, glioblastoma, feature selection, similarity measures, differentially expressed genes, patient subgroups

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