Skip to main content

Advertisement

SpringerLink
Log in

A validated gene expression profile for detecting clinical outcome in breast cancer using artificial neural networks

  • Preclinical study
  • Published:
Breast Cancer Research and Treatment Aims and scope Submit manuscript

Abstract

Gene expression microarrays allow for the high throughput analysis of huge numbers of gene transcripts and this technology has been widely applied to the molecular and biological classification of cancer patients and in predicting clinical outcome. A potential handicap of such data intensive molecular technologies is the translation to clinical application in routine practice. In using an artificial neural network bioinformatic approach, we have reduced a 70 gene signature to just 9 genes capable of accurately predicting distant metastases in the original dataset. Upon validation in a follow-up cohort, this signature was an independent predictor of metastases free and overall survival in the presence of the 70 gene signature and other factors. Interestingly, the ANN signature and CA9 expression also split the groups defined by the 70 gene signature into prognostically distinct groups. Subsequently, the presence of protein for the principal prognosticator gene was categorically assessed in breast cancer tissue of an experimental and independent validation patient cohort, using immunohistochemistry. Importantly our principal prognosticator, CA9, showed that it is capable of selecting an aggressive subgroup of patients who are known to have poor prognosis.

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

Similar content being viewed by others

Abbreviations

ANN:

Artificial neural networks

BCSS:

Breast cancer specific survival

CA9:

Carbonic anhydrase IX

EGF:

Epidermal growth factor

DFI:

Disease-free interval

EST:

Expressed sequence tag

HR:

Hormonal receptors

HIF-1α:

Hypoxia induced factor 1 alpha

ROC:

Receiver operating characteristic

RMH:

Royal marsden hospital

TMA:

Tissue microarray

TNP:

Triple negative phenotype

AUC:

Area under the curve

References

  1. Brown PO, Botstein D (1999) Exploring the new world of the genome with DNA microarrays. Nat Genet 21((1)(Suppl)):33–37. doi:10.1038/4462

    Article  CAS  PubMed  Google Scholar 

  2. Bhattacharjee A, Richards WG, Staunton J et al (2001) Classification of human lung carcinomas by mRNA expression profiling reveals distinct adenocarcinoma subclasses. Proc Natl Acad Sci USA 98(24):13790–13795. doi:10.1073/pnas.191502998

    Article  CAS  PubMed  Google Scholar 

  3. Khan J, Wei JS, Ringner M et al (2001) Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nat Med 7(6):673–679. doi:10.1038/89044

    Article  CAS  PubMed  Google Scholar 

  4. Rosenwald A, Wright G, Chan WC et al (2002) The use of molecular profiling to predict survival after chemotherapy for diffuse large-B-cell lymphoma. N Engl J Med 346(25):1937–1947. doi:10.1056/NEJMoa012914

    Article  PubMed  Google Scholar 

  5. Sorlie T, Perou CM, Tibshirani R et al (2001) Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications. Proc Natl Acad Sci USA 98(19):10869–10874. doi:10.1073/pnas.191367098

    Article  CAS  PubMed  Google Scholar 

  6. West M, Blanchette C, Dressman H et al (2001) Predicting the clinical status of human breast cancer by using gene expression profiles. Proc Natl Acad Sci USA 98(20):11462–11467. doi:10.1073/pnas.201162998

    Article  CAS  PubMed  Google Scholar 

  7. Callagy G, Cattaneo E, Daigo Y et al (2003) Molecular classification of breast carcinomas using tissue microarrays. Diagn Mol Pathol 12(1):27–34. doi:10.1097/00019606-200303000-00004

    Article  CAS  PubMed  Google Scholar 

  8. Paik S, Shak S, Tang G et al (2004) A multigene assay to predict recurrence of tamoxifen-treated, node-negative breast cancer. N Engl J Med 351(27):2817–2826. doi:10.1056/NEJMoa041588

    Article  CAS  PubMed  Google Scholar 

  9. Perou CM, Sorlie T, Eisen MB et al (2000) Molecular portraits of human breast tumours. Nature 406(6797):747–752. doi:10.1038/35021093

    Article  CAS  PubMed  Google Scholar 

  10. Abd El-Rehim DM, Ball G, Pinder SE et al (2005) High-throughput protein expression analysis using tissue microarray technology of a large well-characterised series identifies biologically distinct classes of breast cancer confirming recent cDNA expression analyses. Int J Cancer 116(3):340–350. doi:10.1002/ijc.21004

    Article  CAS  PubMed  Google Scholar 

  11. Masters JR, Lakhani SR (2000) How diagnosis with microarrays can help cancer patients. Nature 404(6781):921. doi:10.1038/35010139

    Article  CAS  PubMed  Google Scholar 

  12. Naderi A, Teschendorff AE, Barbosa-Morais NL et al (2007) A gene-expression signature to predict survival in breast cancer across independent data sets. Oncogene 26(10):1507–1516. doi:10.1038/sj.onc.1209920

    Article  CAS  PubMed  Google Scholar 

  13. van ‘t Veer LJ, Dai H, van de Vijver MJ et al (2002) Gene expression profiling predicts clinical outcome of breast cancer. Nature 415(6871):530–536. doi:10.1038/415530a

    Article  Google Scholar 

  14. Fan C, Oh DS, Wessels L et al (2006) Concordance among gene-expression-based predictors for breast cancer. N Engl J Med 355(6):560–569. doi:10.1056/NEJMoa052933

    Article  CAS  PubMed  Google Scholar 

  15. Wirapati P, Sotiriou C, Kunkel S et al (2008) Meta-analysis of gene expression profiles in breast cancer: toward a unified understanding of breast cancer subtyping and prognosis signatures. Breast Cancer Res 10(4):R65. doi:10.1186/bcr2124

    Article  PubMed  Google Scholar 

  16. Lancashire LJ, Rees RC, Ball GR (2008) Identification of gene transcript signatures predictive for estrogen receptor and lymph node status using a stepwise forward selection artificial neural network modelling approach. Artif Intell Med 43(2):99–111. doi:10.1016/j.artmed.2008.03.001

    Article  PubMed  Google Scholar 

  17. Ball G, Mian S, Holding F et al (2002) An integrated approach utilizing artificial neural networks and SELDI mass spectrometry for the classification of human tumours and rapid identification of potential biomarkers. Bioinformatics 18(3):395–404. doi:10.1093/bioinformatics/18.3.395

    Article  CAS  PubMed  Google Scholar 

  18. Lancashire L, Schmid O, Shah H et al (2005) Classification of bacterial species from proteomic data using combinatorial approaches incorporating artificial neural networks, cluster analysis and principal components analysis. Bioinformatics 21(10):2191–2199. doi:10.1093/bioinformatics/bti368

    Article  CAS  PubMed  Google Scholar 

  19. Matharoo-Ball B, Ball G, Rees R (2007) Clinical proteomics: discovery of cancer biomarkers using mass spectrometry and bioinformatics approaches—a prostate cancer perspective. Vaccine 25(Suppl 2):B110–B121

    Article  CAS  PubMed  Google Scholar 

  20. van de Vijver MJ, He YD, van ‘t Veer LJ et al (2002) A gene-expression signature as a predictor of survival in breast cancer. N Engl J Med 347(25):1999–2009. doi:10.1056/NEJMoa021967

    Article  PubMed  Google Scholar 

  21. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536

    Article  Google Scholar 

  22. Picard RR, Cook RD (1984) Cross-validation of regression models. J Am Stat Assoc 79(387):575–583

    Article  Google Scholar 

  23. Xu QS, Liang YZ, Du YP (2004) Monte Carlo cross-validation for selecting a model and estimating the prediction error in multivariate calibration. J Chemometr 18(2):112–120. doi:10.1002/cem.858

    Article  CAS  Google Scholar 

  24. Shao J (1993) Linear model selection by cross-validation. J Am Stat Assoc 88(422):486–494. doi:10.2307/2290328

    Article  Google Scholar 

  25. Efron B (1986) How biased is the apparent error rate of a prediction rule? J Am Stat Assoc 81(394):461–470. doi:10.2307/2289236

    Article  Google Scholar 

  26. Bloom HJ, Richardson WW (1957) Histological grading and prognosis in breast cancer; a study of 1409 cases of which 359 have been followed for 15 years. Br J Cancer 11(3):359–377

    CAS  PubMed  Google Scholar 

  27. Colpaert CG, Vermeulen PB, Fox SB et al (2004) The presence of a fibrotic focus in invasive breast carcinoma correlates with the expression of carbonic anhydrase IX and is a marker of hypoxia and poor prognosis. Breast Cancer Res Treat 81(2):137–147. doi:10.1023/A:1025702330207

    Article  Google Scholar 

  28. Nielsen TO, Hsu FD, Jensen K et al (2004) Immunohistochemical and clinical characterization of the basal-like subtype of invasive breast carcinoma. Clin Cancer Res 10(16):5367–5374. doi:10.1158/1078-0432.CCR-04-0220

    Article  CAS  PubMed  Google Scholar 

  29. Raghunand N, He X, van Sluis R et al (1999) Enhancement of chemotherapy by manipulation of tumour pH. Br J Cancer 80(7):1005–1011. doi:10.1038/sj.bjc.6690455

    Article  CAS  PubMed  Google Scholar 

  30. van Berkel M, van der Groep P, Schvarts A et al (2002) HIF-1alpha/CAIX coexpression in invasive human breast cancer. Breast Cancer Res Treat 76(Suppl 1):S146

    Google Scholar 

  31. Saarnio J, Parkkila S, Parkkila AK et al (1998) Immunohistochemical study of colorectal tumors for expression of a novel transmembrane carbonic anhydrase, MN/CA IX, with potential value as a marker of cell proliferation. Am J Pathol 153(1):279–285

    CAS  PubMed  Google Scholar 

  32. Liao SY, Brewer C, Zavada J et al (1994) Identification of the MN antigen as a diagnostic biomarker of cervical intraepithelial squamous and glandular neoplasia and cervical carcinomas. Am J Pathol 145(3):598–609

    CAS  PubMed  Google Scholar 

  33. Hockel M, Schlenger K, Aral B et al (1996) Association between tumor hypoxia and malignant progression in advanced cancer of the uterine cervix. Cancer Res 56(19):4509–4515

    CAS  PubMed  Google Scholar 

  34. Brizel DM, Scully SP, Harrelson JM et al (1996) Tumor oxygenation predicts for the likelihood of distant metastases in human soft tissue sarcoma. Cancer Res 56(5):941–943

    CAS  PubMed  Google Scholar 

  35. Brennan DJ, Jirstrom K, Kronblad A et al (2006) CA IX is an independent prognostic marker in premenopausal breast cancer patients with one to three positive lymph nodes and a putative marker of radiation resistance. Clin Cancer Res 12(21):6421–6431. doi:10.1158/1078-0432.CCR-06-0480

    Article  CAS  PubMed  Google Scholar 

  36. Chia SK, Wykoff CC, Watson PH et al (2001) Prognostic significance of a novel hypoxia-regulated marker, carbonic anhydrase IX, in invasive breast carcinoma. J Clin Oncol 19(16):3660–3668

    CAS  PubMed  Google Scholar 

  37. Tomes L, Emberley E, Niu Y et al (2003) Necrosis and hypoxia in invasive breast carcinoma. Breast Cancer Res Treat 81(1):61–69. doi:10.1023/A:1025476722493

    Article  PubMed  Google Scholar 

  38. Trastour C, Benizri E, Ettore F et al (2007) HIF-1alpha and CA IX staining in invasive breast carcinomas: prognosis and treatment outcome. Int J Cancer 120(7):1451–1458. doi:10.1002/ijc.22436

    Article  CAS  PubMed  Google Scholar 

  39. Kronblad A, Hedenfalk I, Nilsson E et al (2005) ERK1/2 inhibition increases antiestrogen treatment efficacy by interfering with hypoxia-induced downregulation of ERalpha: a combination therapy potentially targeting hypoxic and dormant tumor cells. Oncogene 24(45):6835–6841. doi:10.1038/sj.onc.1208830

    Article  CAS  PubMed  Google Scholar 

  40. Storci G, Sansone P, Trere D et al (2008) The basal-like breast carcinoma phenotype is regulated by SLUG gene expression. J Pathol 214(1):25–37. doi:10.1002/path.2254

    Article  CAS  PubMed  Google Scholar 

  41. Fadare O, Tavassoli FA (2007) The phenotypic spectrum of basal-like breast cancers: a critical appraisal. Adv Anat Pathol 14(5):358–373. doi:10.1097/PAP.0b013e31814b26fe

    Article  CAS  PubMed  Google Scholar 

  42. Van den Eynden GG, Smid M, Van Laere SJ et al (2008) Gene expression profiles associated with the presence of a fibrotic focus and the growth pattern in lymph node-negative breast cancer. Clin Cancer Res 14(10):2944–2952. doi:10.1158/1078-0432.CCR-07-4397

    Article  PubMed  Google Scholar 

  43. Cheang MC, Voduc D, Bajdik C et al (2008) Basal-like breast cancer defined by five biomarkers has superior prognostic value than triple-negative phenotype. Clin Cancer Res 14(5):1368–1376. doi:10.1158/1078-0432.CCR-07-1658

    Article  CAS  PubMed  Google Scholar 

  44. Turner NC, Reis-Filho JS (2006) Basal-like breast cancer and the BRCA1 phenotype. Oncogene 25(43):5846–5853. doi:10.1038/sj.onc.1209876

    Article  CAS  PubMed  Google Scholar 

  45. Vleugel MM, Greijer AE, Shvarts A et al (2005) Differential prognostic impact of hypoxia induced and diffuse HIF-1alpha expression in invasive breast cancer. J Clin Pathol 58(2):172–177. doi:10.1136/jcp.2004.019885

    Article  CAS  PubMed  Google Scholar 

  46. Gery S, Sawyers CL, Agus DB et al (2002) TMEFF2 is an androgen-regulated gene exhibiting antiproliferative effects in prostate cancer cells. Oncogene 21(31):4739–4746. doi:10.1038/sj.onc.1205142

    Article  CAS  PubMed  Google Scholar 

  47. Gery S, Koeffler HP (2003) Repression of the TMEFF2 promoter by c-Myc. J Mol Biol 328(5):977–983. doi:10.1016/S0022-2836(03)00404-2

    Article  CAS  PubMed  Google Scholar 

  48. Glinsky GV, Berezovska O, Glinskii AB (2005) Microarray analysis identifies a death-from-cancer signature predicting therapy failure in patients with multiple types of cancer. J Clin Invest 115(6):1503–1521. doi:10.1172/JCI23412

    Article  CAS  PubMed  Google Scholar 

  49. Hayama S, Daigo Y, Kato T et al (2006) Activation of CDCA1-KNTC2, members of centromere protein complex, involved in pulmonary carcinogenesis. Cancer Res 66(21):10339–10348. doi:10.1158/0008-5472.CAN-06-2137

    Article  CAS  PubMed  Google Scholar 

  50. Gurzov EN, Izquierdo M (2006) RNA interference against Hec1 inhibits tumor growth in vivo. Gene Ther 13(1):1–7. doi:10.1038/sj.gt.3302595

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgments

This study was supported by a grant from the UK HEFCE and ENACT (The European Network for the identification and validation of antigens and biomarkers in cancer and their application in clinical tumour immunology) and the Breast Cancer Campaign (2005). The authors thank Dr. Kay Savage for production of the Royal Marsden tumour tissue sections. Thanks also to the John and Lucille Van Geest Foundation.

Author information

Authors and Affiliations

  1. Clinical and Experimental Pharmacology, Paterson Institute for Cancer Research, University of Manchester, Manchester, M20 4BX, UK

    L. J. Lancashire

  2. John Van Geest Cancer Research Centre, Nottingham Trent University, Clifton Campus, Clifton Lane, Nottingham, NG11 8NS, UK

    L. J. Lancashire, C. Lemetre, R. C. Rees & G. R. Ball

  3. Department of Histopathology, Nottingham University Hospitals Trust and University of Nottingham, Nottingham, NG7 2UH, UK

    D. G. Powe, E. Rakha, T. M. Abdel-Fatah, A. R. Green, R. Mukta, E. C. Paish & I. O. Ellis

  4. The Breakthrough Breast Cancer Research Centre, Institute of Cancer Research, Chester Beatty Laboratories, 237 Fulham Road, London, SW3 6JB, UK

    J. S. Reis-Filho

  5. Department of Surgery, Breast Institute, City Hospital Nottingham, Nottingham, NG5 1PB, UK

    R. Blamey

  6. Signal Transduction Laboratory, London Research Institute, Lincoln’s Inn Fields Laboratories, 44 Lincoln’s Inn Fields, London, WC2A 3PX, UK

    B. Weigelt

Authors
  1. L. J. Lancashire
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. G. Powe
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. S. Reis-Filho
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. E. Rakha
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. C. Lemetre
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. B. Weigelt
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. T. M. Abdel-Fatah
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. A. R. Green
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. R. Mukta
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. R. Blamey
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. E. C. Paish
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. R. C. Rees
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. I. O. Ellis
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. G. R. Ball
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to I. O. Ellis or G. R. Ball.

Additional information

L. J. Lancashire and D. G. Powe contributed equally.

Electronic supplementary material

Below is the link to the electronic supplementary material.

(PDF 83 kb)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lancashire, L.J., Powe, D.G., Reis-Filho, J.S. et al. A validated gene expression profile for detecting clinical outcome in breast cancer using artificial neural networks. Breast Cancer Res Treat 120, 83–93 (2010). https://doi.org/10.1007/s10549-009-0378-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10549-009-0378-1

Keywords

Search

Navigation