Skip to main content

Advertisement

SpringerLink
Log in

Predicting bladder cancer prognosis by integrating multi-omics data through a transfer learning-based Cox proportional hazards network

  • Regular Paper
  • Published:
CCF Transactions on High Performance Computing Aims and scope Submit manuscript

Abstract

Predicting bladder cancer outcomes is important for patients’ treatments, and it’s common to predict the outcomes from omics data. However, using a single type of omics data suffers from data noise since individual omics type represents only one single view of bladder cancer patients. In this study, we have estimated bladder cancer prognosis by integrating multi-omics data including RNA-seq, miRNA-seq, DNA methylation, and copy number variation data. To effectively integrate the multi-omics data, we have developed a transfer-learning based Cox proportional hazards network (TCAP) by utilizing an integrated loss function consisted of two modules: the data reconstruction module to ensure learning a representative hidden layer for the input data, and the proportional hazard module to estimate patients’ risks. The experiments on 336 patients from The Cancer Genome Atlas (TCGA) showed that our method achieved a concordance index (C-index) of 0.665, which is higher than previous methods. In consideration of the expense to obtain multi-omics data in clinics, we fitted the risks estimated from TCAP by training an XGboost model based on mRNA data only. The model achieved a reasonable C-index of 0.621, and independent tests on three additional datasets achieved an average C-index of 0.637 \(\pm\) 0.047. The essentially same result as the one achieved on TCGA dataset indicates the robustness of our model. Based on the risk subgroups divided by TCAP, we identified 12 candidate genes that affected the survival of bladder cancer patients, among which 7 genes (58.3%) have been proved to associate with bladder cancer through literature review. In summary, the results indicated that we have constructed an accurate and robust model for predicting bladder cancer outcomes.

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

Similar content being viewed by others

Availability of data and material

All the data analyzed during the current study are available in the TCGA dataset (https://tcga-data.nci.nih.gov/tcga/) and the GEO database (https://www.ncbi.nlm.nih.gov).

Code availability

The method codes are available at: https://github.com/Hua0113/TCAP.

References

  • Bokde, N., et al.: A novel imputation methodology for time series based on pattern sequence forecasting. Pattern Recognit. Lett. 116, 88–96 (2018)

    Article  Google Scholar 

  • Chai, H., et al.: Integrating multi-omics data through deep learning for accurate cancer prognosis prediction. Comput. Biol. Med. 2021, 104481 (2021)

    Article  Google Scholar 

  • Cheerla, A., Gevaert, O.: Deep learning with multimodal representation for pancancer prognosis prediction. Bioinformatics 35(14), i446–i454 (2019)

    Article  Google Scholar 

  • Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM; 2016, pp. 785–794 (2016)

  • Knowles, L.M., et al.: CLT1 targets bladder cancer through integrin α5β1 and CLIC3. Mol. Cancer Res. 11(2), 194–203 (2013)

    Article  Google Scholar 

  • Lee, T.-Y., et al.: Incorporating deep learning and multi-omics autoencoding for analysis of lung adenocarcinoma prognostication. Comput. Biol. 87, 107277 (2020)

    Google Scholar 

  • Lin, J., et al.: A robust 11-genes prognostic model can predict overall survival in bladder cancer patients based on five cohorts. Cancer Cell Int. 20(1), 1–14 (2020)

    Article  Google Scholar 

  • Liu, A., et al.: Prognostic value of the combined expression of tumor-associated trypsin inhibitor (TATI) and p53 in patients with bladder cancer undergoing radical cystectomy. Cancer Biomark. 26(3), 281–289 (2019)

    Article  Google Scholar 

  • Lv, S., et al.: PPARγ activation serves as therapeutic strategy against bladder cancer via inhibiting PI3K–Akt signaling pathway. BMC Cancer 19(1), 1–13 (2019)

    Article  Google Scholar 

  • Mariette, J., Villa-Vialaneix, N.: Unsupervised multiple kernel learning for heterogeneous data integration. Bioinformatics 34(6), 1009–1015 (2018)

    Article  Google Scholar 

  • Noguchi, S., et al.: Replacement treatment with microRNA-143 and-145 induces synergistic inhibition of the growth of human bladder cancer cells by regulating PI3K/Akt and MAPK signaling pathways. Cancer Lett. 328(2), 353–361 (2013)

    Article  Google Scholar 

  • Ou, Y., et al.: Activation of cyclic AMP/PKA pathway inhibits bladder cancer cell invasion by targeting MAP4-dependent microtubule dynamics. Urol. Oncol. Semin. Orig. Investig. 32(1), 47–e21 (2014)

    MathSciNet  Google Scholar 

  • Richters, A., Aben, K.K., Kiemeney, L.A.: The global burden of urinary bladder cancer: an update. World J. Urol. 38(8), 1895–1904 (2020)

    Article  Google Scholar 

  • Ritchie, M.E., et al.: limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 43(7), e47 (2015)

    Article  Google Scholar 

  • Rohart, F., et al.: mixOmics: an R package for ’omics feature selection and multiple data integration. PLoS Comput. Biol. 13(11), e1005752 (2017)

    Article  Google Scholar 

  • Salimian, J., et al.: MiR-486-5p enhances cisplatin sensitivity of human muscle-invasive bladder cancer cells by induction of apoptosis and down-regulation of metastatic genes. Urol. Oncol. Semin. Orig. Investig. 38(9), 738–e9 (2020)

    Google Scholar 

  • Song, B.N., Chu, I.S.: A gene expression signature of FOXM1 predicts the prognosis of hepatocellular carcinoma. Exp. Mol. Med. 50(1), e418 (2018)

    Article  Google Scholar 

  • Stevens, T.A., et al.: Identification of novel binding elements and gene targets for the homeodomain protein BARX2. J. Biol. Chem. 279(15), 14520–14530 (2004)

    Article  Google Scholar 

  • Stirzaker, C., et al.: Methylome sequencing in triple-negative breast cancer reveals distinct methylation clusters with prognostic value. Nat. Commun. 6, 5899 (2015)

    Article  Google Scholar 

  • Tomczak, K., Czerwinska, P., Wiznerowicz, M.: The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge. Contemp. Oncol. (pozn) 19(1A), A68-77 (2015)

    Google Scholar 

  • Tong, D., et al.: Improving prediction performance of colon cancer prognosis based on the integration of clinical and multi-omics data. BMC Med. Inform. 20(1), 22 (2020a)

    Article  Google Scholar 

  • Tong, L., et al.: Deep learning based feature-level integration of multi-omics data for breast cancer patients survival analysis. BMC Med. Inform. 20(1), 1–12 (2020b)

    Article  Google Scholar 

  • Van Belle, V., et al.: Support vector methods for survival analysis: a comparison between ranking and regression approaches. Artif. Intell. Med. 53(2), 107–118 (2011)

    Article  Google Scholar 

  • Vanacker, H., et al.: Enhanced performance of prognostic estimation from TCGA RNAseq data using transfer learning. Ann. Oncol. 30, v52 (2019)

    Article  Google Scholar 

  • Volinia, S., Croce, C.M.: Prognostic microRNA/mRNA signature from the integrated analysis of patients with invasive breast cancer. Proc. Natl. Acad. Sci. USA 110(18), 7413–7417 (2013)

    Article  Google Scholar 

  • Volkmer, J.P., et al.: Three differentiation states risk-stratify bladder cancer into distinct subtypes. Proc. Natl. Acad. Sci. USA 109(6), 2078–2083 (2012)

    Article  Google Scholar 

  • Wei, L., et al.: TCGA-assembler 2: software pipeline for retrieval and processing of TCGA/CPTAC data. Bioinformatics 34(9), 1615–1617 (2018)

    Article  Google Scholar 

  • Xie, C., et al.: KOBAS 2.0: a web server for annotation and identification of enriched pathways and diseases. Nucleic Acids Res. 39(3), W316-322 (2011)

    Article  Google Scholar 

  • Zhang, Y., et al.: Identification of core genes and key pathways via integrated analysis of gene expression and DNA methylation profiles in bladder cancer. Med. Sci. Monit. Int. Med. J. Exp. 24, 3024 (2018)

    Article  Google Scholar 

Download references

Funding

The work was supported in part by the National Key R&D Program of China (2020YFB0204803), National Natural Science Foundation of China (61772566 and 81801132), Guangdong Frontier & Key Tech Innovation Program (2018B010109006, 2019B020228001), Natural Science Foundation of Guangdong, China (2019A1515012207), and Introducing Innovative and Entrepreneurial Teams (2016ZT06D211).

Author information

Author notes

  1. Hua Chai and Zhongyue Zhang are co-first authors of this article.

Authors and Affiliations

  1. School of Computer Science, Sun Yat-sen University, Guangzhou, 510000, China

    Hua Chai, Zhongyue Zhang, Yi Wang & Yuedong Yang

Authors
  1. Hua Chai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhongyue Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuedong Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

CH and YY conceived the study. CH and ZZ performed the data analysis. CH and WY interpreted the results. CH and ZZ wrote the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Yuedong Yang.

Ethics declarations

Conflict of interest

The authors declare that they have no competing interests.

Ethics approval

Not applicable.

Consent to participate

All the authors listed have approved the manuscript.

Consent for publication

All the authors listed have approved the manuscript.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 13 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chai, H., Zhang, Z., Wang, Y. et al. Predicting bladder cancer prognosis by integrating multi-omics data through a transfer learning-based Cox proportional hazards network. CCF Trans. HPC 3, 311–319 (2021). https://doi.org/10.1007/s42514-021-00074-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s42514-021-00074-9

Keywords

Search

Navigation