Machine learning-based identification of proteomic markers in colorectal cancer using UK Biobank data

Aug 4, 2026

Upload by Asher

Colorectal cancer contributes substantially to cancer-related mortality worldwide, and rising incidence and mortality are expected over coming decades. Early detection improves outcomes through surgery and medications, making prognostic and diagnostic biomarker development essential. This study integrates machine learning with protein network analysis to identify protein biomarkers using proteome profiles from healthy and colorectal cancer participants. Three classifiers (LASSO, XGBoost, LightGBM) are evaluated with hyperparameter tuning, and SHapley Additive exPlanations values quantify protein contributions to predictions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

Study approach and rationale

Biomarker discovery pipeline

Models, tuning, and predictive performance

Model interpretability with SHAP

Key biomarkers and pathway evidence

Implications for diagnostics and therapeutics

University of Birmingham Machine learning-based identification of proteomic markers in colorectal cancer using UK Biobank data Kollampallath Radhakrishnan, Swarnima ; Nath, Dipanwita ; Russ, Dominic; Bravo Merodio, Laura; Lad, Priyani ; Kola Daisi, Folakemi ; Acharjee, Animesh DOI: 10.3389/fonc.2024.1505675 License: Creative Commons: Attribution (CC BY) Document Version Publisher's PDF, also known as Version of record Citation for published version (Harvard): Kollampallath Radhakrishnan, S, Nath, D, Russ, D, Bravo Merodio, L, Lad, P, Kola Daisi, F & Acharjee, A 2025,'Machine learning-based identification of proteomic markers in colorectal cancer using UK Biobank data', Frontiers in Oncology, vol. 14, 1505675. [https://doi.org/10.3389/fonc.2024.1505675](https://doi.org/10.3389/fonc.2024.1505675) Link to publication on Research at Birmingham portal General rights Unless a licence is specified above, all rights (including copyright and moral rights) in this document are retained by the authors and/or the copyright holders. The express permission of the copyright holder must be obtained for any use of this material other than for purposes permitted by law. •Users may freely distribute the URL that is used to identify this publication. •Users may download and/or print one copy of the publication from the University of Birmingham research portal for the purpose of private study or non-commercial research. •User may use extracts from the document in line with the concept of ‘fair dealing’ under the Copyright, Designs and Patents Act 1988 (?) •Users may not further distribute the material nor use it for the purposes of commercial gain. Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive. If you believe that this is the case for this document, [please contact UBIRA@lists.bham.ac.uk](please contact UBIRA@lists.bham.ac.uk) providing details and we will remove access to the work immediately and investigate. Download date: 03. Aug. 2026 TYPE Original Research PUBLISHED 07 January 2025 DOI 10.3389/fonc.2024.1505675 OPEN ACCESS EDITED BY Nemat Ali, King Saud University, Saudi Arabia REVIEWED BY Musalula Sinkala, University of Cape Town, South Africa Kang Qin, University of Texas MD Anderson Cancer Center, United States *CORRESPONDENCE Animesh Acharjee [a.acharjee@bham.ac.uk](a.acharjee@bham.ac.uk) RECEIVED 03 October 2024 ACCEPTED 02 December 2024 PUBLISHED 07 January 2025 CITATION Radhakrishnan SK, Nath D, Russ D, Merodio LB, Lad P, Daisi FK and Acharjee A (2025) Machine learning-based identiﬁcation of proteomic markers in colorectal cancer using UK Biobank data. Front. Oncol. 14:1505675 . doi: 10.3389/fonc.2024.1505675 COPYRIGHT © 2025 Radhakrishnan, Nath, Russ, Merodio, Lad, Daisi and Acharjee. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Machine learning-based identiﬁcation of proteomic markers in colorectal cancer using UK Biobank data Swarnima Kollampallath Radhakrishnan 1, Dipanwita Nath 1, Dominic Russ 1,2,3, Laura Bravo Merodio 1,2,3, Priyani Lad 1, Folakemi Kola Daisi 1 and Animesh Acharjee 1,2,3* 1College of Medicine and Health, School of Medical Sciences, Cancer and Genomic Sciences,

FAQs

How does the study identify proteomic biomarkers for colorectal cancer?

It combines machine learning models with protein network analysis and uses proteome profiles from healthy and colorectal cancer individuals to discover predictive protein biomarkers.

Which machine learning models are evaluated, and how are they optimized?

LASSO, XGBoost, and LightGBM are tested for predictive performance, and each model undergoes hyperparameter tuning using grid search.

How are the most important proteins determined and what biomarkers are highlighted?

SHapley Additive exPlanations (SHAP) values are used to quantify each protein’s contribution to predictions; TFF3, LCN2, and CEACAM5 are reported as key biomarkers.

Aug 4, 2026

Upload by Asher