Premenopausal breast cancer: potential clinical utility of a multi-omics based machine learning approach for patient stratification
The breast cancer (BC) epidemic is a multifactorial disease attributed to the early twenty-first century: about two million of new cases and half a million deaths are registered annually worldwide. New trends are emerging now: on the one hand, with respect to the geographical BC prevalence and, on the other hand, with respect to the age distribution. Recent statistics demonstrate that young populations are getting more and more affected by BC in both Eastern and Western countries. Therefore, the old rule “the older the age, the higher the BC risk” is getting relativised now. Accumulated evidence shows that young premenopausal women deal with particularly unpredictable subtypes of BC such as triple-negative BC, have lower survival rates and respond less to conventional chemotherapy compared to the majority of postmenopausal BC.
Here we hypothesised that a multi-level diagnostic approach may lead to the identification of a molecular signature highly specific for the premenopausal BC. A multi-omic approach using machine learning was considered as a potent tool for stratifying patients with benign breast alterations into well-defined risk groups, namely individuals at high versus low risk for breast cancer development.
Results and conclusions
The study resulted in identifying multi-omic signature specific for the premenopausal BC that can be used for stratifying patients with benign breast alterations. Our predictive model is capable of discriminating individually between high and low BC-risk with high confidence (>90%) and considered of potential clinical utility. Novel risk assessment approaches and advanced screening programmes—as the long-term target of this project—are of particular importance for predictive, preventive and personalised medicine as the medicine of the future, due to the expected health benefits for young subpopulations and the healthcare system as a whole.
KeywordsPredictive preventive personalised medicine Breast cancer Menopause Patient stratification Bioinformatics Machine learning Multi-level diagnostics Biomarker panel Laboratory medicine
Area under ROC (receiver operating characteristic) curve
- CA I, II, III
Comet classes I, II and III, respectively
Gradient Boosting Machine
Matrix-assisted laser desorption/ionisation time-of-flight
Non-negative matrix factorisation
Premenopausal breast cancer
Postmenopausal breast cancer
Reactive oxygen species
Two-dimensional poly-acrylamide gel electrophoresis
The authors thank Prof. Dr. H.J. Blom for measurements of homocysteine in blood plasma. The authors thank Dr. M. Fountoulakis and Dr. A. Papadopoulou for proteomic expertise strongly supported the project performance. Further, authors thank Ms. G. Windisch-Schuster for performing the Western blot analysis.
OG created the concepts of the project and drafted the article. HF established the approach of machine learning applied to the project, and SP implemented the approach. KY carried out molecular biological investigations. HF and OG made the results interpretation. CK provided expertise in breast cancer. WK supervised the project with clinical expertise in breast cancer management.
The study funding has been performed by the Breast Cancer Research Centre, University of Bonn, Germany. KY has been awarded a fellowship by the European Association for Predictive, Preventive and Personalised Medicine (EPMA, Belgium).
Compliance with ethical standards
The authors declare that they have no competing interests.
Consent for publication
All the patient investigations conformed to the principles outlined in the Declaration of Helsinki and have been performed with the permission (Nr. 148/05) released by the responsible Ethic’s Committee of the Medical Faculty, Rheinische Friedrich-Wilhelms-University of Bonn. Human rights have been obligatory protected during the entire duration of the project according to the European standards. All the patients were informed about the purposes of the study and have signed their “consent of the patient”. This article does not contain any studies with animals performed by any of the authors.
- 1.Golubnitschaja O, Debald M, Yeghiazaryan K, Kuhn W, Pešta M, Costigliola V, et al. Breast cancer epidemic in the early 21st century: evaluation of risk factors, cumulative questionnaires and recommendations for preventive measures. Tumor Biol. 2016;37(10):12941–57. https://doi.org/10.1007/s13277-016-5168-x.CrossRefGoogle Scholar
- 5.American Cancer Society. Global cancer facts & figures. 2nd ed. Atlanta: American Cancer Society; 2011.Google Scholar
- 7.Sung H, Rosenberg PS, Chen WQ et al. Female breast cancer incidence among Asian and Western populations: more similar than expected. J Natl Cancer Inst. 2015;107.Google Scholar
- 12.Bubnov R, Polivka J Jr, Zubor P, Koniczka K, Golubnitschaja O. “Pre-metastatic niches” in breast cancer: are they created by or prior to the tumour onset? “Flammer Syndrome” relevance to address the question. EPMA J 2017;8(2):141–157. https://doi.org/10.1007/s13167-017-0092-8.
- 13.Polivka J Jr, Kralickova M, Polivka J Jr, Kaiser C, Kuhn W, Golubnitschaja O. Mystery of the brain metastatic disease in breast cancer patients: improved patient stratification, disease prediction and targeted prevention on the horizon? EPMA J. 2017;8(2):119–27. https://doi.org/10.1007/s13167-017-0087-59. CrossRefPubMedPubMedCentralGoogle Scholar
- 16.Colleoni M, Rotmensz N, Peruzzotti G, Maisonneuve P, Orlando L, Ghisini R, et al. Role of endocrine responsiveness and adjuvant therapy in very young women (below 35 years) with operable breast cancer and node negative disease. Ann Oncol. 2006;17(10):1497–503. https://doi.org/10.1093/annonc/mdl145.CrossRefPubMedGoogle Scholar
- 17.Ahn SH, Son BH, Kim SW, Kim SI, Jeong J, Ko SS, et al. Poor outcome of hormone receptor-positive breast cancer at very young age is due to tamoxifen resistance: nationwide survival data in Korea—a report from the Korean Breast Cancer Society. J Clin Oncol. 2007;25(17):2360–8. https://doi.org/10.1200/JCO.2006.10.3754. CrossRefPubMedGoogle Scholar
- 19.Engmann NJ, Golmakani MK, Miglioretti DL, Sprague BL, Kerlikowske K. Population-attributable risk proportion of clinical risk factors for breast cancer. Breast Cancer Surveillance Consortium. JAMA Oncol 2017. https://doi.org/10.1001/jamaoncol.2016.6326.
- 20.Fabian CJ, Kimler BF, Phillips TA, Box JA, Kreutzjans AL, Carlson SE, et al. Modulation of breast cancer risk biomarkers by high-dose omega-3 fatty acids: phase II pilot study in premenopausal women. Cancer Prev Res (Phila). 2015;8(10):912–21. https://doi.org/10.1158/1940-6207.CAPR-14-0335.CrossRefPubMedCentralGoogle Scholar
- 23.Golubnitschaja O, Yeghiazaryan K, Costigliola V, Trog D, Braun M, Debald M, et al. Risk assessment, disease prevention and personalised treatments in breast cancer: is clinically qualified integrative approach in the horizon? EPMA J. 2013;4(1):6. https://doi.org/10.1186/1878-5085-4-6.CrossRefPubMedPubMedCentralGoogle Scholar
- 27.Golubnitschaja O, Yeghiazaryan K, Abraham JA, Schild HH, Costigliola V, Debald D, et al. Breast cancer risk assessment: a non-invasive multiparametric approach to stratify patients by MMP-9 serum activity and RhoA expression patterns in circulating leucocytes. Amino Acids. 2017;49(2):273–81. https://doi.org/10.1007/s00726-016-2357-2.CrossRefPubMedGoogle Scholar
- 28.Golubnitschaja O, Mönkemann H, Kim K, Mozaffari MS. Depletion of taurine induces DNA damage and expression of checkpoint genes p21WAF1/CIP1 and 14-3-3 σ in rat cardiomyocytes. Biochem Pharmacol 2003;66:511–517Google Scholar
- 34.Benjamini Y, Yekutieli D. The control of the false discovery rate in multiple testing under dependency. Ann Stat. 2001;29:1164–88.Google Scholar
- 35.Guldberg TL, Christensen S, Zachariae R, Jensen AB. Prognostic factors in early breast cancer associated with body mass index, physical functioning, physical activity, and comorbidity: data from a nationwide Danish cohort. Breast Cancer Res Treat. 2017;162(1):159–67. https://doi.org/10.1007/s10549-016-4099-y.CrossRefPubMedGoogle Scholar
- 43.Ranogajec I, Jakić-Razumović J, Puzović V, Gabrilovac J. Prognostic value of matrix metalloproteinase-2 (MMP-2), matrix metalloproteinase-9 (MMP-9) and aminopeptidase N/CD13 in breast cancer patients. Med Oncol. 2012;29(2):561–9. https://doi.org/10.1007/s12032-011-9984-y.CrossRefPubMedGoogle Scholar
- 44.Gari HH, DeGala GD, Ray R, Lucia MS, Lambert JR. PRL-3 engages the focal adhesion pathway in triple-negative breast cancer cells to alter actin structure and substrate adhesion properties critical for cell migration and invasion. Cancer Lett. 2016;380(2):505–12. https://doi.org/10.1016/j.canlet.2016.07.017.CrossRefPubMedPubMedCentralGoogle Scholar