Urinary polyamine biomarker panels with machine-learning differentiated colorectal cancers, benign disease, and healthy controls

Tetsushi Nakajima, Kenji Katsumata, Hiroshi Kuwabara, Ryoko Soya, Masanobu Enomoto, Tetsuo Ishizaki, Akihiko Tsuchida, Masayo Mori, Kana Hiwatari, Tomoyoshi Soga, Masaru Tomita, Masahiro Sugimoto

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Colorectal cancer (CRC) is one of the most daunting diseases due to its increasing worldwide prevalence, which requires imperative development of minimally or non-invasive screening tests. Urinary polyamines have been reported as potential markers to detect CRC, and an accurate pattern recognition to differentiate CRC with early stage cases from healthy controls are needed. Here, we utilized liquid chromatography triple quadrupole mass spectrometry to profile seven kinds of polyamines, such as spermine and spermidine with their acetylated forms. Urinary samples from 201 CRCs and 31 non-CRCs revealed the N1,N12-diacetylspermine showing the highest area under the receiver operating characteristic curve (AUC), 0.794 (the 95% confidence interval (CI): 0.704–0.885, p < 0.0001), to differentiate CRC from the benign and healthy controls. Overall, 59 samples were analyzed to evaluate the reproducibility of quantified concentrations, acquired by collecting three times on three days each from each healthy control. We confirmed the stability of the observed quantified values. A machine learning method using combinations of polyamines showed a higher AUC value of 0.961 (95% CI: 0.937–0.984, p < 0.0001). Computational validations confirmed the generalization ability of the models. Taken together, polyamines and a machine-learning method showed potential as a screening tool of CRC.

Original languageEnglish
Article number756
JournalInternational Journal of Molecular Sciences
Volume19
Issue number3
DOIs
Publication statusPublished - 2018 Mar 7

Fingerprint

machine learning
biomarkers
Polyamines
Biomarkers
Learning systems
Colorectal Neoplasms
cancer
Screening
Area Under Curve
confidence
screening
Spermidine
Spermine
Confidence Intervals
Liquid chromatography
intervals
Pattern recognition
Mass spectrometry
liquid chromatography
ROC Curve

Keywords

  • Colorectal cancer
  • Liquid chromatography-mass spectrometry
  • Machine learning
  • Polyamine
  • Urine

ASJC Scopus subject areas

  • Catalysis
  • Molecular Biology
  • Spectroscopy
  • Computer Science Applications
  • Physical and Theoretical Chemistry
  • Organic Chemistry
  • Inorganic Chemistry

Cite this

Urinary polyamine biomarker panels with machine-learning differentiated colorectal cancers, benign disease, and healthy controls. / Nakajima, Tetsushi; Katsumata, Kenji; Kuwabara, Hiroshi; Soya, Ryoko; Enomoto, Masanobu; Ishizaki, Tetsuo; Tsuchida, Akihiko; Mori, Masayo; Hiwatari, Kana; Soga, Tomoyoshi; Tomita, Masaru; Sugimoto, Masahiro.

In: International Journal of Molecular Sciences, Vol. 19, No. 3, 756, 07.03.2018.

Research output: Contribution to journalArticle

Nakajima, T, Katsumata, K, Kuwabara, H, Soya, R, Enomoto, M, Ishizaki, T, Tsuchida, A, Mori, M, Hiwatari, K, Soga, T, Tomita, M & Sugimoto, M 2018, 'Urinary polyamine biomarker panels with machine-learning differentiated colorectal cancers, benign disease, and healthy controls', International Journal of Molecular Sciences, vol. 19, no. 3, 756. https://doi.org/10.3390/ijms19030756
Nakajima, Tetsushi ; Katsumata, Kenji ; Kuwabara, Hiroshi ; Soya, Ryoko ; Enomoto, Masanobu ; Ishizaki, Tetsuo ; Tsuchida, Akihiko ; Mori, Masayo ; Hiwatari, Kana ; Soga, Tomoyoshi ; Tomita, Masaru ; Sugimoto, Masahiro. / Urinary polyamine biomarker panels with machine-learning differentiated colorectal cancers, benign disease, and healthy controls. In: International Journal of Molecular Sciences. 2018 ; Vol. 19, No. 3.
@article{52853c270f8a43079d9f0f5107cfcd69,
title = "Urinary polyamine biomarker panels with machine-learning differentiated colorectal cancers, benign disease, and healthy controls",
abstract = "Colorectal cancer (CRC) is one of the most daunting diseases due to its increasing worldwide prevalence, which requires imperative development of minimally or non-invasive screening tests. Urinary polyamines have been reported as potential markers to detect CRC, and an accurate pattern recognition to differentiate CRC with early stage cases from healthy controls are needed. Here, we utilized liquid chromatography triple quadrupole mass spectrometry to profile seven kinds of polyamines, such as spermine and spermidine with their acetylated forms. Urinary samples from 201 CRCs and 31 non-CRCs revealed the N1,N12-diacetylspermine showing the highest area under the receiver operating characteristic curve (AUC), 0.794 (the 95{\%} confidence interval (CI): 0.704–0.885, p < 0.0001), to differentiate CRC from the benign and healthy controls. Overall, 59 samples were analyzed to evaluate the reproducibility of quantified concentrations, acquired by collecting three times on three days each from each healthy control. We confirmed the stability of the observed quantified values. A machine learning method using combinations of polyamines showed a higher AUC value of 0.961 (95{\%} CI: 0.937–0.984, p < 0.0001). Computational validations confirmed the generalization ability of the models. Taken together, polyamines and a machine-learning method showed potential as a screening tool of CRC.",
keywords = "Colorectal cancer, Liquid chromatography-mass spectrometry, Machine learning, Polyamine, Urine",
author = "Tetsushi Nakajima and Kenji Katsumata and Hiroshi Kuwabara and Ryoko Soya and Masanobu Enomoto and Tetsuo Ishizaki and Akihiko Tsuchida and Masayo Mori and Kana Hiwatari and Tomoyoshi Soga and Masaru Tomita and Masahiro Sugimoto",
year = "2018",
month = "3",
day = "7",
doi = "10.3390/ijms19030756",
language = "English",
volume = "19",
journal = "International Journal of Molecular Sciences",
issn = "1661-6596",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "3",

}

TY - JOUR

T1 - Urinary polyamine biomarker panels with machine-learning differentiated colorectal cancers, benign disease, and healthy controls

AU - Nakajima, Tetsushi

AU - Katsumata, Kenji

AU - Kuwabara, Hiroshi

AU - Soya, Ryoko

AU - Enomoto, Masanobu

AU - Ishizaki, Tetsuo

AU - Tsuchida, Akihiko

AU - Mori, Masayo

AU - Hiwatari, Kana

AU - Soga, Tomoyoshi

AU - Tomita, Masaru

AU - Sugimoto, Masahiro

PY - 2018/3/7

Y1 - 2018/3/7

N2 - Colorectal cancer (CRC) is one of the most daunting diseases due to its increasing worldwide prevalence, which requires imperative development of minimally or non-invasive screening tests. Urinary polyamines have been reported as potential markers to detect CRC, and an accurate pattern recognition to differentiate CRC with early stage cases from healthy controls are needed. Here, we utilized liquid chromatography triple quadrupole mass spectrometry to profile seven kinds of polyamines, such as spermine and spermidine with their acetylated forms. Urinary samples from 201 CRCs and 31 non-CRCs revealed the N1,N12-diacetylspermine showing the highest area under the receiver operating characteristic curve (AUC), 0.794 (the 95% confidence interval (CI): 0.704–0.885, p < 0.0001), to differentiate CRC from the benign and healthy controls. Overall, 59 samples were analyzed to evaluate the reproducibility of quantified concentrations, acquired by collecting three times on three days each from each healthy control. We confirmed the stability of the observed quantified values. A machine learning method using combinations of polyamines showed a higher AUC value of 0.961 (95% CI: 0.937–0.984, p < 0.0001). Computational validations confirmed the generalization ability of the models. Taken together, polyamines and a machine-learning method showed potential as a screening tool of CRC.

AB - Colorectal cancer (CRC) is one of the most daunting diseases due to its increasing worldwide prevalence, which requires imperative development of minimally or non-invasive screening tests. Urinary polyamines have been reported as potential markers to detect CRC, and an accurate pattern recognition to differentiate CRC with early stage cases from healthy controls are needed. Here, we utilized liquid chromatography triple quadrupole mass spectrometry to profile seven kinds of polyamines, such as spermine and spermidine with their acetylated forms. Urinary samples from 201 CRCs and 31 non-CRCs revealed the N1,N12-diacetylspermine showing the highest area under the receiver operating characteristic curve (AUC), 0.794 (the 95% confidence interval (CI): 0.704–0.885, p < 0.0001), to differentiate CRC from the benign and healthy controls. Overall, 59 samples were analyzed to evaluate the reproducibility of quantified concentrations, acquired by collecting three times on three days each from each healthy control. We confirmed the stability of the observed quantified values. A machine learning method using combinations of polyamines showed a higher AUC value of 0.961 (95% CI: 0.937–0.984, p < 0.0001). Computational validations confirmed the generalization ability of the models. Taken together, polyamines and a machine-learning method showed potential as a screening tool of CRC.

KW - Colorectal cancer

KW - Liquid chromatography-mass spectrometry

KW - Machine learning

KW - Polyamine

KW - Urine

UR - http://www.scopus.com/inward/record.url?scp=85043602029&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043602029&partnerID=8YFLogxK

U2 - 10.3390/ijms19030756

DO - 10.3390/ijms19030756

M3 - Article

VL - 19

JO - International Journal of Molecular Sciences

JF - International Journal of Molecular Sciences

SN - 1661-6596

IS - 3

M1 - 756

ER -