Advertisement

Salivary metabolomics with alternative decision tree-based machine learning methods for breast cancer discrimination

  • Takeshi Murata
  • Takako Yanagisawa
  • Toshiaki Kurihara
  • Miku Kaneko
  • Sana Ota
  • Ayame Enomoto
  • Masaru Tomita
  • Masahiro SugimotoEmail author
  • Makoto Sunamura
  • Tetsu Hayashida
  • Yuko Kitagawa
  • Hiromitsu Jinno
Preclinical study

Abstract

Purpose

The aim of this study is to explore new salivary biomarkers to discriminate breast cancer patients from healthy controls.

Methods

Saliva samples were collected after 9 h fasting and were immediately stored at − 80 °C. Capillary electrophoresis and liquid chromatography with mass spectrometry were used to quantify hundreds of hydrophilic metabolites. Conventional statistical analyses and artificial intelligence-based methods were used to assess the discrimination abilities of the quantified metabolites. A multiple logistic regression (MLR) model and an alternative decision tree (ADTree)-based machine learning method were used. The generalization abilities of these mathematical models were validated in various computational tests, such as cross-validation and resampling methods.

Results

One hundred sixty-six unstimulated saliva samples were collected from 101 patients with invasive carcinoma of the breast (IC), 23 patients with ductal carcinoma in situ (DCIS), and 42 healthy controls (C). Of the 260 quantified metabolites, polyamines were significantly elevated in the saliva of patients with breast cancer. Spermine showed the highest area under the receiver operating characteristic curves [0.766; 95% confidence interval (CI) 0.671–0.840, P < 0.0001] to discriminate IC from C. In addition to spermine, polyamines and their acetylated forms were elevated in IC only. Two hundred each of two-fold, five-fold, and ten-fold cross-validation using different random values were conducted and the MLR model had slightly better accuracy. The ADTree with an ensemble approach showed higher accuracy (0.912; 95% CI 0.838–0.961, P < 0.0001). These prediction models also included spermine as a predictive factor.

Conclusions

These data indicated that combinations of salivary metabolomics with the ADTree-based machine learning methods show potential for non-invasive screening of breast cancer.

Keywords

Breast cancer Biomarker Saliva Polyamines Metabolomics Alternative decision tree 

Notes

Acknowledgements

We thank Editage (www.editage.jp) for English language editing.

Funding

This study was funded by JSPS KAKENHI Grant Numbers 16H05408 and 25461996, and research Grants from the Yamagata Prefectural Government and the City of Tsuruoka.

Compliance with ethical standards

Conflict of interest

The authors declare no competing financial interests. M. Sunamura and M. Sugimoto hold unpaid advisory positions in a commercial organization. No other author declares non-financial competing interests.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the ethics committees of Keio University (No.20120143), Teikyo University (No.15-047-2), and Kitasato University Kitasato Institutional Hospital (No.17006) and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

References

  1. 1.
    International Agency for Research on Cancer. http://gco.iarc.fr/. Accessed 11 Jan 2019
  2. 2.
    Cancer Incidence in Five Continents, CI5plus. IARC Cancer Base No.9. Lyon, International Agency for Research on Cancer. http://ci5.iarc.fr. Accessed 11 Jan 2019
  3. 3.
    World Health Organization mortality database. http://www.who.int/healthinfo/mortality_data/en/. Accessed 11 Jan 2019
  4. 4.
    Matsuda A, Matsuda T, Shibata A, Katanoda K, Sobue T, Nishimoto H (2014) Cancer incidence and incidence rates in Japan in 2008: a study of 25 population-based cancer registries for the Monitoring of Cancer Incidence in Japan (MCIJ) project. Jpn J Clin Oncol 44(4):388–396CrossRefGoogle Scholar
  5. 5.
    Habbema JD, van Oortmarssen GJ, van Putten DJ, Lubbe JT, van der Maas PJ (1986) Age-specific reduction in breast cancer mortality by screening: an analysis of the results of the Health Insurance Plan of Greater New York study. J Natl Cancer Inst 77(2):317–320Google Scholar
  6. 6.
    OECD Health Statistics  https://doi.org/10.1787/health-data-en. Accessed 11 Jan 2019
  7. 7.
    Miller AB, Wall C, Baines CJ, Sun P, To T, Narod SA (2014) Twenty five year follow-up for breast cancer incidence and mortality of the Canadian National Breast Screening Study: randomised screening trial. BMJ 348:g366CrossRefGoogle Scholar
  8. 8.
    Shah TA, Guraya SS (2017) Breast cancer screening programs: review of merits, demerits, and recent recommendations practiced across the world. J Microsc Ultrastruct 5(2):59–69CrossRefGoogle Scholar
  9. 9.
    Johns LE, Coleman DA, Swerdlow AJ, Moss SM (2017) Effect of population breast screening on breast cancer mortality up to 2005 in England and Wales: an individual-level cohort study. Br J Cancer 116(2):246–252CrossRefGoogle Scholar
  10. 10.
    Johns LE, Swerdlow AJ, Moss SM (2018) Effect of population breast screening on breast cancer mortality to 2005 in England and Wales: a nested case-control study within a cohort of one million women. J Med Screen 25(2):76–81CrossRefGoogle Scholar
  11. 11.
    Kaczor-Urbanowicz KE, Martin Carreras-Presas C, Aro K, Tu M, Garcia-Godoy F, Wong DT (2017) Saliva diagnostics—Current views and directions. Exp Biol Med (Maywood) 242(5):459–472CrossRefGoogle Scholar
  12. 12.
    Wang X, Kaczor-Urbanowicz KE, Wong DT (2017) Salivary biomarkers in cancer detection. Med Oncol 34(1):7CrossRefGoogle Scholar
  13. 13.
    Zhang A, Sun H, Wang X (2012) Saliva metabolomics opens door to biomarker discovery, disease diagnosis, and treatment. Appl Biochem Biotechnol 168(6):1718–1727CrossRefGoogle Scholar
  14. 14.
    Ishikawa S, Sugimoto M, Kitabatake K, Sugano A, Nakamura M, Kaneko M et al (2016) Identification of salivary metabolomic biomarkers for oral cancer screening. Sci Rep 6:31520CrossRefGoogle Scholar
  15. 15.
    Rapado-Gonzalez O, Majem B, Muinelo-Romay L, Lopez-Lopez R, Suarez-Cunqueiro MM (2016) Cancer salivary biomarkers for tumours distant to the oral cavity. Int J Mol Sci 17(9):1531CrossRefGoogle Scholar
  16. 16.
    de Abreu PD, Areias VR, Franco MF, Benitez MC, do Nascimento CM, de Azevedo CM et al (2013) Measurement of HER2 in saliva of women in risk of breast cancer. Pathol Oncol Res 19(3):509–513CrossRefGoogle Scholar
  17. 17.
    Streckfus C, Bigler L, Tucci M, Thigpen JT (2000) A preliminary study of CA15-3, c-erbB-2, epidermal growth factor receptor, cathepsin-D, and p53 in saliva among women with breast carcinoma. Cancer Invest 18(2):101–109CrossRefGoogle Scholar
  18. 18.
    Navarro MA, Mesia R, Diez-Gibert O, Rueda A, Ojeda B, Alonso MC (1997) Epidermal growth factor in plasma and saliva of patients with active breast cancer and breast cancer patients in follow-up compared with healthy women. Breast Cancer Res Treat 42(1):83–86CrossRefGoogle Scholar
  19. 19.
    Brooks MN, Wang J, Li Y, Zhang R, Elashoff D, Wong DT (2008) Salivary protein factors are elevated in breast cancer patients. Mol Med Rep 1(3):375–378Google Scholar
  20. 20.
    Cavaco C, Pereira JAM, Taunk K, Taware R, Rapole S, Nagarajaram H et al (2018) Screening of salivary volatiles for putative breast cancer discrimination: an exploratory study involving geographically distant populations. Anal Bioanal Chem 410(18):4459–4468CrossRefGoogle Scholar
  21. 21.
    Al-Muhtaseb SI (2014) Serum and saliva protein levels in females with breast cancer. Oncol Lett 8(6):2752–2756CrossRefGoogle Scholar
  22. 22.
    Liu X, Yu H, Qiao Y, Yang J, Shu J, Zhang J et al (2018) Salivary glycopatterns as potential biomarkers for screening of early-stage breast cancer. EBioMedicine 28:70–79CrossRefGoogle Scholar
  23. 23.
    Zhang L, Xiao H, Karlan S, Zhou H, Gross J, Elashoff D et al (2010) Discovery and preclinical validation of salivary transcriptomic and proteomic biomarkers for the non-invasive detection of breast cancer. PLoS ONE 5(12):e15573CrossRefGoogle Scholar
  24. 24.
    Sugimoto M, Wong DT, Hirayama A, Soga T, Tomita M (2010) Capillary electrophoresis mass spectrometry-based saliva metabolomics identified oral, breast and pancreatic cancer-specific profiles. Metabolomics 6(1):78–95CrossRefGoogle Scholar
  25. 25.
    Takayama T, Tsutsui H, Shimizu I, Toyama T, Yoshimoto N, Endo Y et al (2016) Diagnostic approach to breast cancer patients based on target metabolomics in saliva by liquid chromatography with tandem mass spectrometry. Clin Chim Acta 452:18–26CrossRefGoogle Scholar
  26. 26.
    Tsutsui H, Mochizuki T, Inoue K, Toyama T, Yoshimoto N, Endo Y et al (2013) High-throughput LC-MS/MS based simultaneous determination of polyamines including N-acetylated forms in human saliva and the diagnostic approach to breast cancer patients. Anal Chem 85(24):11835–11842CrossRefGoogle Scholar
  27. 27.
    Wang X, Zhao X, Chou J, Yu J, Yang T, Liu L et al (2018) Taurine, glutamic acid and ethylmalonic acid as important metabolites for detecting human breast cancer based on the targeted metabolomics. Cancer Biomark 23(2):255–268CrossRefGoogle Scholar
  28. 28.
    Zhong L, Cheng F, Lu X, Duan Y, Wang X (2016) Untargeted saliva metabonomics study of breast cancer based on ultra performance liquid chromatography coupled to mass spectrometry with HILIC and RPLC separations. Talanta 158:351–360CrossRefGoogle Scholar
  29. 29.
    Cheng F, Wang Z, Huang Y, Duan Y, Wang X (2015) Investigation of salivary free amino acid profile for early diagnosis of breast cancer with ultra performance liquid chromatography-mass spectrometry. Clin Chim Acta 447:23–31CrossRefGoogle Scholar
  30. 30.
    Asai Y, Itoi T, Sugimoto M, Sofuni A, Tsuchiya T, Tanaka R et al (2018) Elevated polyamines in saliva of pancreatic cancer. Cancers 10(2):43CrossRefGoogle Scholar
  31. 31.
    Asai Y, Itoi T, Sugimoto M, Sofuni A, Tsuchiya T, Tanaka R et al (2018) Elevated polyamines in saliva of pancreatic cancer. Cancers (Basel) 10(2):43CrossRefGoogle Scholar
  32. 32.
    Tomita A, Mori M, Hiwatari K, Yamaguchi E, Itoi T, Sunamura M et al (2018) Effect of storage conditions on salivary polyamines quantified via liquid chromatography-mass spectrometry. Sci Rep 8(1):12075CrossRefGoogle Scholar
  33. 33.
    Ishikawa S, Sugimoto M, Kitabatake K, Tu M, Sugano A, Yamamori I et al (2017) Effect of timing of collection of salivary metabolomic biomarkers on oral cancer detection. Amino Acids 49(4):761–770CrossRefGoogle Scholar
  34. 34.
    Sugimoto M, Saruta J, Matsuki C, To M, Onuma H, Kaneko M et al (2013) Physiological and environmental parameters associated with mass spectrometry-based salivary metabolomic profiles. Metabolomics 9(2):454–463CrossRefGoogle Scholar
  35. 35.
    Sugimoto M, Kawakami M, Robert M, Soga T, Tomita M (2012) Bioinformatics tools for mass spectroscopy-based metabolomic data processing and analysis. Curr Bioinform 7(1):96–108CrossRefGoogle Scholar
  36. 36.
    Freund Y, Mason L (1999) The alternating decision tree learning algorithm. Icml 1999:124–133Google Scholar
  37. 37.
    Wang Q, Gao P, Wang X, Duan Y (2014) Investigation and identification of potential biomarkers in human saliva for the early diagnosis of oral squamous cell carcinoma. Clin Chim Acta 427:79–85CrossRefGoogle Scholar
  38. 38.
    Irene LW, James JD, Bernard F, Eleftherios PM, Stewart JA, Thomas BJ et al (2011) Long-term outcome of invasive ipsilateral breast tumor recurrences after lumpectomy in NSABP B-17 and B-24 randomized clinical trials for DCIS. J Natl Cancer Inst 103(6):478–488CrossRefGoogle Scholar
  39. 39.
    Welch HG, Black WC (2010) Overdiagnosis in cancer. J Natl Cancer Inst 102(9):605–613CrossRefGoogle Scholar
  40. 40.
    Welch HG (2009) Overdiagnosis and mammography screening. BMJ 339:b1425CrossRefGoogle Scholar
  41. 41.
    Elshof LE, Tryfonidis K, Slaets L, van Leeuwen-Stok AE, Skinner VP, Dif N et al (2015) Feasibility of a prospective, randomised, open-label, international muticentre, phase III, non-inferiority trial to assess the saftey of active surveillance for low risk ductal carcinoma in site The LORD study. Eur J Cancer 51(12):1497–1510CrossRefGoogle Scholar
  42. 42.
    Francis A, Thomas J, Fallowfield L, Wallis M, Bartlett JM, Brookes C et al (2015) Addressing overtreatment of screen detected DCIS; the LORIS trial. Eur J Cancer 51(16):2296–2303CrossRefGoogle Scholar
  43. 43.
    Soda K (2011) The mechanisms by which polyamines accelerate tumor spread. J Exp Clin Cancer Res 30:95CrossRefGoogle Scholar
  44. 44.
    Dejure FR, Eilers M (2017) MYC and tumor metabolism: chicken and egg. EMBO J 36(23):3409–3420CrossRefGoogle Scholar
  45. 45.
    Gerner EW, Meyskens FL Jr (2004) Polyamines and cancer: old molecules, new understanding. Nat Rev Cancer 4(10):781–792CrossRefGoogle Scholar
  46. 46.
    Satoh K, Yachida S, Sugimoto M, Oshima M, Nakagawa T, Akamoto S et al (2017) Global metabolic reprogramming of colorectal cancer occurs at adenoma stage and is induced by MYC. Proc Natl Acad Sci USA 114(37):E7697–E7706CrossRefGoogle Scholar
  47. 47.
    Hiramatsu K, Takahashi K, Yamaguchi T, Matsumoto H, Miyamoto H, Tanaka S et al (2005) N(1), N(12)-Diacetylspermine as a sensitive and specific novel marker for early- and late-stage colorectal and breast cancers. Clin Cancer Res 11(8):2986–2990CrossRefGoogle Scholar
  48. 48.
    Takahashi Y, Sakaguchi K, Horio H, Hiramatsu K, Moriya S, Takahashi K et al (2015) Urinary N1, N12-diacetylspermine is a non-invasive marker for the diagnosis and prognosis of non-small-cell lung cancer. Br J Cancer 113(10):1493–1501CrossRefGoogle Scholar
  49. 49.
    Nakajima T, Katsumata K, Kuwabara H, Soya R, Enomoto M, Ishizaki T et al (2018) Urinary polyamine biomarker panels with machine-learning differentiated colorectal cancers, benign disease, and healthy controls. Int J Mol Sci 19(3):756CrossRefGoogle Scholar
  50. 50.
    Wikoff WR, Hanash S, DeFelice B, Miyamoto S, Barnett M, Zhao Y et al (2015) Diacetylspermine is a novel prediagnostic serum biomarker for non-small-cell lung cancer and has additive performance with pro-surfactant protein B. J Clin Oncol 33(33):3880–3886CrossRefGoogle Scholar
  51. 51.
    Vargas AJ, Ashbeck EL, Thomson CA, Gerner EW, Thompson PA (2014) Dietary polyamine intake and polyamines measured in urine. Nutr Cancer 66(7):1144–1153CrossRefGoogle Scholar
  52. 52.
    Park MH, Igarashi K (2013) Polyamines and their metabolites as diagnostic markers of human diseases. Biomol Ther (Seoul) 21(1):1–9CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Takeshi Murata
    • 1
  • Takako Yanagisawa
    • 2
  • Toshiaki Kurihara
    • 3
  • Miku Kaneko
    • 4
  • Sana Ota
    • 4
  • Ayame Enomoto
    • 4
  • Masaru Tomita
    • 4
  • Masahiro Sugimoto
    • 4
    • 5
    Email author
  • Makoto Sunamura
    • 6
  • Tetsu Hayashida
    • 3
  • Yuko Kitagawa
    • 3
  • Hiromitsu Jinno
    • 3
  1. 1.Department of Breast SurgeryNational Cancer Center HospitalTokyoJapan
  2. 2.Department of SurgeryTeikyo University School of MedicineTokyoJapan
  3. 3.Department of SurgeryKeio University School of MedicineTokyoJapan
  4. 4.Institute for Advanced BiosciencesKeio UniversityTsuruokaJapan
  5. 5.Health Promotion and Preemptive Medicine, Research and Development Center for Minimally Invasive TherapiesTokyo Medical UniversityTokyoJapan
  6. 6.Digestive Surgery and Transplantation SurgeryTokyo Medical University Hachioji Medical CenterTokyoJapan

Personalised recommendations