ORIGINAL RESEARCH article
Front. Toxicol.
Sec. Environmental Toxicology
Volume 7 - 2025 | doi: 10.3389/ftox.2025.1657251
Integrating 113 Machine Learning Methods to Decipher the Toxicological Mechanisms of Perfluorooctanoic acid in Bladder Cancer
Provisionally accepted
- 1Shenzhen University, Shenzhen, China
- 2Shenzhen Second People's Hospital, Shenzhen, China
- 3Shenzhen Yantian District People's Hospital, Shenzhen, China
- 4Shenzhen Luohu Hospital Group Luohu People's Hospital Medical Laboratory Center, Shenzhen, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Objective: This study aims to investigate the molecular mechanisms by which perfluorooctanoic acid (PFOA) contributes to bladder carcinogenesis, focusing on identifying molecular targets, exploring their roles, and establishing predictive biomarkers for clinical use. Methods: Bioinformatics analysis identified 9,591 potential PFOA targets using five databases. Differential expression and WGCNA were applied to bladder cancer data from five cohorts to identify tumor-associated genes. Functional enrichment, machine learning, SHAP analysis, and molecular docking were used to assess biological pathways and predictive models. Results: Sixty-nine core genes involved in cell cycle regulation and DNA repair were identified. A nine-gene signature achieved an AUC of 0.986 in the training cohort, with validation across independent cohorts (AUC: 0.944-1.000). SHAP analysis highlighted MCM7 as crucial for risk prediction. Molecular docking showed high binding affinity between PFOA and IGFBP2 (-13.0 kcal/mol). Conclusion: This study provides a molecular framework for PFOA-induced bladder cancer and a robust six-gene signature for clinical risk prediction. Molecular docking supports PFOA's interaction with key tumor-associated proteins, offering insights into potential diagnostic and therapeutic strategies.
Keywords: pfoa, Bladder cancer, machine learning, biomarkers, Network toxicology
Received: 01 Jul 2025; Accepted: 10 Sep 2025.
Copyright: © 2025 Wang, Liu and Tang. 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) or licensor 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.
* Correspondence: Han Wang, Shenzhen University, Shenzhen, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.