Staging of colorectal cancer using lipid biomarkers and machine learning

Sanduru Thamarai Krishnan; David Winkler; Darren Creek; Dovile Anderson; Chandra Kirana; Guy J Maddern; Kevin Fenix; Ehud Hauben; David Rudd; Nicolas Hans Voelcker

doi:10.1007/s11306-023-02049-z

Staging of colorectal cancer using lipid biomarkers and machine learning

Metabolomics. 2023 Sep 20;19(10):84. doi: 10.1007/s11306-023-02049-z.

Authors

Sanduru Thamarai Krishnan^{1

2

3}, David Winkler^{4

5

6}, Darren Creek^{1

7}, Dovile Anderson^{1

7}, Chandra Kirana^{8

9}, Guy J Maddern^{8

9}, Kevin Fenix^{8

9}, Ehud Hauben^{8

9}, David Rudd^{10

11}, Nicolas Hans Voelcker^{12

13

14}

Affiliations

¹ Drug Delivery, Disposition and Dynamics, Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC, 3052, Australia.
² Department of Chemistry, University of Reading, Whiteknights, Reading, RG6 6DX, UK.
³ Melbourne Centre for Nanofabrication, Victorian Node of the Australian National Fabrication Facility, 151 Wellington Road, Clayton, VIC, 3168, Australia.
⁴ Department of Biochemistry and Chemistry, La Trobe Institute for Molecular Science, La Trobe University, Bundoora, 3086, Australia.
⁵ School of Medicinal Chemistry, Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC, 3052, Australia.
⁶ School of Pharmacy, University of Nottingham, Nottingham, NG7 2QL, UK.
⁷ Monash Proteomics and Metabolomics Facility, Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC, 3052, Australia.
⁸ Discipline of Surgery, Adelaide Medical School, The University of Adelaide, Adelaide, SA, 5005, Australia.
⁹ Basil Hetzel Institute for Translational Health Research, The Queen Elizabeth Hospital, Woodville, SA, 5011, Australia.
¹⁰ Drug Delivery, Disposition and Dynamics, Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC, 3052, Australia. david.rudd@monash.edu.
¹¹ Melbourne Centre for Nanofabrication, Victorian Node of the Australian National Fabrication Facility, 151 Wellington Road, Clayton, VIC, 3168, Australia. david.rudd@monash.edu.
¹² Drug Delivery, Disposition and Dynamics, Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC, 3052, Australia. nicolas.voelcker@monash.edu.
¹³ Melbourne Centre for Nanofabrication, Victorian Node of the Australian National Fabrication Facility, 151 Wellington Road, Clayton, VIC, 3168, Australia. nicolas.voelcker@monash.edu.
¹⁴ Commonwealth Scientific and Industrial Research Organization (CSIRO), Clayton, VIC, 3168, Australia. nicolas.voelcker@monash.edu.

Abstract

Introduction: Colorectal cancer (CRC) is the third most commonly diagnosed cancer worldwide. Alteration in lipid metabolism and chemokine expression are considered hallmark characteristics of malignant progression and metastasis of CRC. Validated diagnostic and prognostic biomarkers are urgently needed to define molecular heterogeneous CRC clinical stages and subtypes, as liver dominant metastasis has poor survival outcomes.

Objectives: The aim of this study was to integrate lipid changes, concentrations of chemokines, such as platelet factor 4 and interleukin 8, and gene marker status measured in plasma samples, with clinical features from patients at different CRC stages or who had progressed to stage-IV colorectal liver metastasis (CLM).

Methods: High-resolution liquid chromatography-mass spectrometry (HR-LC-MS) was used to determine the levels of candidate lipid biomarkers in each CRC patient's preoperative plasma samples and combined with chemokine, gene and clinical data. Machine learning models were then trained using known clinical outcomes to select biomarker combinations that best classify CRC stage and group.

Results: Bayesian neural net and multilinear regression-machine learning identified candidate biomarkers that classify CRC (stages I-III), CLM patients and control subjects (cancer-free or patients with polyps/diverticulitis), showing that integrating specific lipid signatures and chemokines (platelet factor-4 and interluken-8; IL-8) can improve prognostic accuracy. Gene marker status could contribute to disease prediction, but requires ubiquitous testing in clinical cohorts.

Conclusion: Our findings demonstrate that correlating multiple disease related features with lipid changes could improve CRC prognosis. The identified signatures could be used as reference biomarkers to predict CRC prognosis and classify stages, and monitor therapeutic intervention.

Keywords: Biomarker; Cancer Subtypes; Lipidomics; Machine learning; Metastatic colorectal cancer classification; Multi-omics.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Bayes Theorem
Biomarkers
Colorectal Neoplasms* / diagnosis
Colorectal Neoplasms* / genetics
Humans
Lipids
Liver Neoplasms* / diagnosis
Machine Learning
Metabolomics

Substances

Biomarkers
Lipids