Field of Vision
Copyright ©The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Oncol. Mar 15, 2023; 15(3): 372-388
Published online Mar 15, 2023. doi: 10.4251/wjgo.v15.i3.372
Machine learning algorithm to construct cuproptosis- and immune-related prognosis prediction model for colon cancer
Yuan-Yi Huang, Ting-Yu Bao, Xu-Qi Huang, Qi-Wen Lan, Ze-Min Huang, Yu-Han Chen, Zhi-De Hu, Xu-Guang Guo
Yuan-Yi Huang, Ting-Yu Bao, Xu-Qi Huang, Qi-Wen Lan, Ze-Min Huang, Yu-Han Chen, Xu-Guang Guo, Department of Clinical Laboratory Medicine, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou 510150, Guangdong Province, China
Yuan-Yi Huang, Department of Clinical Medicine, The First Clinical School of Guangzhou Medical University, Guangzhou 511436, Guangdong Province, China
Ting-Yu Bao, Ze-Min Huang, Yu-Han Chen, Xu-Guang Guo, Department of Clinical Medicine, The Third Clinical School of Guangzhou Medical University, Guangzhou 511436, Guangdong Province, China
Xu-Qi Huang, Department of Clinical Medicine, The Sixth Clinical School of Guangzhou Medical University, Guangzhou 511436, Guangdong Province, China
Qi-Wen Lan, Department of Medical Imageology, The Second Clinical School of Guangzhou Medical University, Guangzhou 511436, Guangdong Province, China
Zhi-De Hu, Department of Laboratory Medicine, The Affiliated Hospital of Inner Mongolia Medical University, Hohhot 010010, Inner Mongolia Autonomous Region, China
Xu-Guang Guo, Guangdong Provincial Key Laboratory of Major Obstetric Diseases, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou 510150, Guangdong Province, China
Xu-Guang Guo, Key Laboratory of Reproduction and Genetics of Guangdong Higher Education Institutes, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou 510150, Guangdong Province, China
Xu-Guang Guo, Guangzhou Key Laboratory for Clinical Rapid Diagnosis and Early Warning of Infectious Diseases, King Med School of Laboratory Medicine, Guangzhou Medical University, Guangzhou 511436, Guangdong Province, China
Author contributions: Huang YY collected and assessed the data; Huang YY, Bao TY, and Huang XQ wrote the manuscript; Lan QW and Huang ZM participated in revising the manuscript; Chen YH and Hu ZD worked together to finalize the submission; Guo XG proposed and designed the study; All authors contributed to the article and approved the submitted version.
Conflict-of-interest statement: The authors report having no conflict of interest.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Xu-Guang Guo, MD, PhD, Associate Professor, Department of Clinical Laboratory Medicine, The Third Affiliated Hospital of Guangzhou Medical University, No. 63 Duobao Road, Liwan District, Guangzhou 510150, Guangdong Province, China. gysygxg@gmail.com
Received: November 23, 2022
Peer-review started: November 23, 2022
First decision: December 9, 2022
Revised: December 22, 2022
Accepted: February 15, 2023
Article in press: February 15, 2023
Published online: March 15, 2023
Abstract
BACKGROUND

Over the past few years, research into the pathogenesis of colon cancer has progressed rapidly, and cuproptosis is an emerging mode of cellular apoptosis. Exploring the relationship between colon cancer and cuproptosis benefits in identifying novel biomarkers and even improving the outcome of the disease.

AIM

To look at the prognostic relationship between colon cancer and the genes associated with cuproptosis and the immune system in patients. The main purpose was to assess whether reasonable induction of these biomarkers reduces mortality among patients with colon cancers.

METHOD

Data obtained from The Cancer Genome Atlas and Gene Expression Omnibus and the Genotype-Tissue Expression were used in differential analysis to explore differential expression genes associated with cuproptosis and immune activation. The least absolute shrinkage and selection operator and Cox regression algorithm was applied to build a cuproptosis- and immune-related combination model, and the model was utilized for principal component analysis and survival analysis to observe the survival and prognosis of the patients. A series of statistically meaningful transcriptional analysis results demonstrated an intrinsic relationship between cuproptosis and the micro-environment of colon cancer.

RESULTS

Once prognostic characteristics were obtained, the CDKN2A and DLAT genes related to cuproptosis were strongly linked to colon cancer: The first was a risk factor, whereas the second was a protective factor. The finding of the validation analysis showed that the comprehensive model associated with cuproptosis and immunity was statistically significant. Within the component expressions, the expressions of HSPA1A, CDKN2A, and UCN3 differed markedly. Transcription analysis primarily reflects the differential activation of related immune cells and pathways. Furthermore, genes linked to immune checkpoint inhibitors were expressed differently between the subgroups, which may reveal the mechanism of worse prognosis and the different sensitivities of chemotherapy.

CONCLUSION

The prognosis of the high-risk group evaluated in the combined model was poorer, and cuproptosis was highly correlated with the prognosis of colon cancer. It is possible that we may be able to improve patients’ prognosis by regulating the gene expression to intervene the risk score.

Keywords: Cuproptosis, Immune, Colon cancer, Prognosis models, Immune infiltration analysis

Core Tip: We comprehensively analyzed the effect of cuproptosis and immunity on the prognosis of colon cancer based on the close association between the three. Scrupulously, a variety of algorithms were applied to analyze and construct a three-gene prognostic model whose efficacy was statistically significant in both the training set and the external validation set. Moreover, in order to provide help for prognosis assessment and personalized treatment of colon cancer, we performed immunoinfiltration analysis and immunocheckpoint inhibitor-related genes expression analysis in different risk groups according to the cuproptosis- and immune-related combination model.