Skip to main content

Advertisement

SpringerLink
Log in

Improving the generalization of unsupervised feature learning by using data from different sources on gene expression data for cancer diagnosis

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Machine learning techniques have been utilized on gene expression profiling for cancer diagnosis. However, the gene expression data suffer from the curse of high dimensionality. Different kinds of feature reduction methods have been proposed to decrease the features for specific cancer diagnosis. However, with the difficulty of obtaining the samples of a particular tumor, the lack of training samples may lead to the overfitting problem. In addition, the feature reduction model on a specific tumor may lead to the problem that the model is not scalable and cannot be generalized to new cancer types. To handle these problems, this paper proposes an unsupervised feature learning method to reduce the data dimensionality of gene expression data. This method amplifies the training samples of feature learning by utilizing the unlabeled samples from different sources. Two heuristic rules are devised to check if the unlabeled samples could be used for amplifying the training set. The amplified training set is used to train the feature learning model based on sparse autoencoder. Since the method leverages the knowledge among the expression data from different sources, it improves the generalization of unsupervised feature learning and further boosts the cancer diagnosis performance. A series of experiments are carried out on the gene expression datasets from TCGA and other sources. Experimental results prove that our method improves the generalization of cancer diagnosis when unlabeled data are used for latent feature learning.

Graphical abstract

The flowchart of our proposed feature learning method

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
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Notes

  1. The Cancer Genome Atlas (TCGA) Research Network. Available: https://www.cancer.gov/ tcga.

References

  1. Salem H, Attiya G, El-Fishawy N (2017) Classification of human cancer diseases by gene expression profiles. Appl Soft Comput 50:124–134

    Article  Google Scholar 

  2. Liu JX, Xu Y, Zheng C-H, Kong H, Lai Z-H (2015) RPCA-based tumor classification using gene expression data. IEEE/ACM Trans Comput Biol Bioinf 12(4):964–970

    Article  CAS  Google Scholar 

  3. Mignone P, Pio G, Džeroski S, Ceci M (2020) Multi-task learning for the simultaneous reconstruction of the human and mouse gene regulatory networks. Scientific reports 10:22295

    Article  CAS  Google Scholar 

  4. Erola P, Björkegren JLM, Michoel T (2020) Model-based clustering of multi-tissue gene expression data. Bioinformatics 36(6):1807–1813

    CAS  PubMed  Google Scholar 

  5. Bao W, Yuan CA, Zhang Y, Han K, Nandi AK, Honig B, Huang D (2017) Mutli-features prediction of protein translational modification sites. IEEE/ACM Trans Comput Biol Bioinforma 15(5):1453–1460

    Article  Google Scholar 

  6. Bao W, Dong W, Chen Y (2017) Classification of protein structure classes on flexible neutral tree. IEEE/ACM trans comput biol bioinforma 14(5):1122–1133

    Article  CAS  Google Scholar 

  7. Yuan F, Lu L, Zou Q (2020) Analysis of gene expression profiles of lung cancer subtypes with machine learning algorithms. BBA-Mol Basis of Dis 866:165822

    Article  Google Scholar 

  8. Khorshed TA (2020) Deep learning for multi-tissue cancer classification of gene expressions (GeneXNet). IEEE Access 8:90615–90629

    Article  Google Scholar 

  9. Tirumala SS, Narayanan A (2016) Attribute selection and classification of prostate cancer gene expression data using artificial neural networks. Pacific-asia Conference on Knowledge Discovery & Data Mining 2016:206–234

    Google Scholar 

  10. Khorshed T, Moustafa MN, Rafea A (2020) Multi-tissue cancer classification of gene expressions using deep learning. IEEE Sixth International Conference on Big Data Computing Service and Applications (BigDataService) 2020:128–135

    Article  Google Scholar 

  11. Abdulla M, Khasawneh MT (2020) G-Forest: an ensemble method for cost-sensitive feature selection in gene expression microarrays. Artif Intell Med 108:101941

    Article  Google Scholar 

  12. Hira ZM, Gillies DF (2015) A review of feature selection and feature extraction methods applied on microarray data. Adv Bioinforma 2015:198363

    Article  Google Scholar 

  13. Hall MA, Smith LA (1998) Practical feature subset selection for machine learning, 21st Australasian Computer Science Conference (ACSC ’98), 1998, pp. 1–11.

  14. Hall MA (2000) Correlation-based feature selection for discrete and numeric class machine learning, 17th International Conference on Machine Learning (ICML’00), 2000, pp. 359–366.

  15. Peng H, Long F, Ding C (2005) Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238

    Article  Google Scholar 

  16. Perez M, Marwala T (2012) Microarray data feature selection using hybrid genetic algorithm simulated annealing, IEEE 27th Convention of Electrical and Electronics Engineers in Israel (IEEEI ’12), 2012, pp. 1–5.

  17. Tang EK, Suganthan PN, Yao X (2006) Gene selection algorithms for microarray data based on least squares support vector machine. BMC Bioinformatics 7(95):1–16

    Google Scholar 

  18. Dashtban M, Balafar M (2017) Gene selection for microarray cancer classification using a new evolutionary method employing artificial intelligence concepts. Genomics 109(2):91–107

    Article  CAS  Google Scholar 

  19. Lu H, Chen J, Yan K, Jin Q, Xue Y, Gao Z (2017) A hybrid feature selection algorithm for gene expression data classification. Neurocomputing 256:56–62

    Article  Google Scholar 

  20. Jonnalagadda S, Srinivasan R (2008) Principal components analysis based methodology to identify differentially expressed genes in time-course microarray data. BMC Bioinformatics 9:267

    Article  Google Scholar 

  21. Sevakula RK, Singh V, Verma NK, Kumar C, Cui Y (2019) Transfer learning for molecular cancer classification using deep neural networks. IEEE/ACM Trans Comput Biol Bioinf 16(6):2089–2100

    Article  Google Scholar 

  22. Fakoor R, Ladhak F, Nazi A, Huber M (2013) Using deep learning to enhance cancer diagnosis and classification, the 30th International Conference on Machine Learning (ICML 2013), 2013, pp. 1–8.

  23. Liao Q, Ding Y, Jiang ZL, Wang X, Zhang C, Zhang Q (2019) Multi-task deep convolutional neural network for cancer diagnosis. Neurocomputing 348:66–73

    Article  Google Scholar 

  24. Liu Z, Wang R, Zhang W, Tang D (2021) An unsupervised feature learning method for enhancing the generalization of cancer diagnosis. 13th International Conference on Machine Learning and Computing, 2021, pp. 252–257.

  25. Sun L, Zhang X, Qian Y, Xu J, Zhang S (2019) Feature selection using neighborhood entropy-based uncertainty measures for gene expression data classification. Inf Sci 502:18–41

    Article  Google Scholar 

  26. Almugren N, Alshamlan H (2019) A survey on hybrid feature selection methods in microarray gene expression data for cancer classification. IEEE Access 7:78533–78548

    Article  Google Scholar 

  27. Potharaju SP, Sreedevi M (2019) Distributed feature selection (DFS) strategy for microarray gene expression data to improve the classification performance. Clin Epidemiol Glob Health 7:171–176

    Article  Google Scholar 

  28. Wahid A, Khan DM, Iqbal N, Khan SA, Ali A, Khan M, Khan Z (2020) Feature selection and classification for gene expression data using novel correlation based overlapping score method via Chou’s 5-Steps rule. Chemom Intell Lab Syst 199:103958

    Article  CAS  Google Scholar 

  29. Uzma, Al-Obeidat F, Tubaishat A, Shah B, Halim Z (2020) Gene encoder: a feature selection technique through unsupervised deep learning-based clustering for large gene expression data, Neural Computing and Applications 2020: 1–23 (published online).

  30. Manosij G, Sukdev A, Kanti GK, Aritra S, Shemim B, Ram S (2019) Genetic algorithm based cancerous gene identification from microarray data using ensemble of filter methods. Med Biol Eng Compu 57:159–176

    Article  Google Scholar 

  31. Nikulin V, McLachlan GJ (2009) Penalized principal component analysis of microarray data. Computational Intelligence Methods for Bioinformatics and Biostatistics 2009:82–96

    Google Scholar 

  32. Huynh PH, Nguyen VH, Do TN (2018) A coupling support vector machines with the feature learning of deep convolutional neural networks for classifying microarray gene expression data. In book: Modern Approaches for Intelligent Information and Database Systems 2018:233–243

    Google Scholar 

  33. Danaee P, Ghaeini R, Hendrix DA (2016) A deep learning approach for cancer detection and relevant gene identification. Pac Symp Biocomput Pac Symp Biocomput 22:219–229

    Google Scholar 

  34. Zhu Z, Ong YS, Dash M (2007) Markov blanket-embedded genetic algorithm for gene selection. Pattern Recogn 49(11):3236–3248

    Article  Google Scholar 

  35. Hess KR (2006) Pharmacogenomic predictor of sensitivity to preoperative chemotherapy with paclitaxel and fluorouracil, doxorubicin, and cyclophosphamide in breast cancer. J Clin Oncol 24(26):4236–4244

    Article  CAS  Google Scholar 

  36. Chin K, DeVries S, Fridlyand J, Spellman PT, Roydasgupta R, Kuo W, Lapuk A, Neve RM, Qian Z, Ryder T et al (2006) Genomic and transcriptional aberrations linked to breast cancer pathophysiologies. Cancer Cell 10(6):529–541

    Article  CAS  Google Scholar 

  37. Telikani A, Gandomi AH (2009) Cost-sensitive stacked auto-encoders for intrusion detection in the Internet of Things. Internet of Things 14:100122

    Article  Google Scholar 

Download references

Acknowledgements

We thank the anonymous reviewers for their constructive comments. An earlier version of this paper [24] was presented at the International Conference on the 13th International Conference on Machine Learning and Computing.

Funding

This work is supported by the Key Research Platforms and Projects of Colleges and Universities in Guangdong Province [Grant Nos. 2020ZDZX3060 and 2019KZDZX1020], National Natural Science Foundation of China [Grant No. 61501128], financial support from China Scholarship Council, and Natural Science Foundation of Guangdong Province [Grant No. 2017A030313345].

Key Laboratory of Microbial Resources and Drug Development in Guizhou Province, 2020ZDZX3060, Zhen Liu, National Natural Science Foundation of China, 61501128, Zhen Liu, Natural Science Foundation of Guangdong Province, 2017A030313345, Ruoyu Wang

Author information

Authors and Affiliations

  1. School of Information Science and Technology/School of Cyber Security, Guangdong University of Foreign Studies, Guangzhou, 510006, China

    Zhen Liu

  2. School of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, 510006, China

    Zhen Liu

  3. Information and Network Engineering Research Center, South China University of Technology, Guangzhou, 510041, China

    Ruoyu Wang

  4. University of Maryland, Baltimore County, MD, 21250, USA

    Wenbin Zhang

Authors
  1. Zhen Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ruoyu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wenbin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ruoyu Wang.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, Z., Wang, R. & Zhang, W. Improving the generalization of unsupervised feature learning by using data from different sources on gene expression data for cancer diagnosis. Med Biol Eng Comput 60, 1055–1073 (2022). https://doi.org/10.1007/s11517-022-02522-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-022-02522-2

Keywords

Search

Navigation