Identification of Potential Molecular Mechanisms and Machine Learning Classification Model in Prostate Cancer Progression Based on GEO Datasets and TCGA Dataset

Jiarui Zhang

doi:10.54097/ad876e59

Authors

Jiarui Zhang

DOI:

https://doi.org/10.54097/ad876e59

Keywords:

Prostate Cancer, Machine Learning, Molecular Mechanisms

Abstract

Prostate cancer is a leading cause of cancer-related morbidity and mortality. Identifying key genes involved in its progression is crucial for improving clinical outcomes.This paper used transcriptomic data from the GEO database to analyze differential expression and employed machine learning techniques to identify critical progression genes and develop a grading model. And the results were validated by TCGA dataset. This paper identified 802 key genes associated with prostate cancer progression. The molecular mechanisms are involving immune and cell growth pathways. The developed machine learning grading model demonstrated high AUCs, indicating its potential utility in clinical settings. Those key genes play important roles in prostate cancer.

Downloads

Download data is not yet available.

References

[1] Jemal, A., Siegel, R., Xu, J., Ward, E., 2010. Cancer statistics, 2010.CA Cancer J. Clin. 60, 277e300.

[2] White MC, Holman DM, Boehm JE, Peipins LA, Grossman M, Henley J. Age and cancer risk: a potentially modifiable relationship. Am J Prev Med. 2014;46(3 Suppl 1):S7–15. doi: 10. 1016/j.amepre.2013.10.029.

[3] Fenton JJ, Weyrich MS, Durbin S, Liu Y, Bang H, Melnikow J. Prostate-specific antigen–based screening for prostate cancer. JAMA. 2018 May 8;319(18):1914. doi:10.1001/ jama. 2018. 3712.

[4] Tolkach Y, Kristiansen G. The heterogeneity of prostate cancer: A practical approach. Pathobiology. 2018;85(1–2):108–16. doi:10.1159/000477852.

[5] Viegas S, Ladeira C, Costa-Veiga A, Perelman J, Gajski G. Forgotten public health impacts of cancer – an overview. Archives of Industrial Hygiene and Toxicology. 2017 Dec 20;68(4):287–97. doi:10.1515/aiht-2017-68-3005.

[6] Lim J, Kurzrock R, Nishizaki D, Miyashita H, Adashek JJ, Lee S, et al. Pan‐Cancer analysis of tim‐3 transcriptomic expression reveals high levels in pancreatic cancer and interpatient heterogeneity. Cancer Medicine. 2023 Dec 22;13(1). doi:10. 1002/ cam4.6844.

[7] Vitelli V, Fleischer T, Ankill J, Arjas E, Frigessi A, Kristensen VN, et al. Transcriptomic Pan‐Cancer Analysis using rank‐based bayesian inference. Molecular Oncology. 2023 Jan 23;17(4):548–63. doi:10.1002/1878-0261.13354.

[8] Schrijver WAME, Selenica P, Lee JY, et al. Mutation profiling of key cancer genes in primary breast cancers and their distant metastases. Cancer Res. 2018;78(12):3112–21. doi:10.1158/ 0008-5472.CAN-17-2310.

[9] Barrett T, Edgar R. [19] gene expression omnibus: Microarray data storage, submission, retrieval, and analysis. Methods in Enzymology. 2006;352–69. doi:10.1016/s0076-6879(06) 110 19-8.

[10] Cornford P, van den Bergh RCN, Briers E, Van den Broeck T, Cumberbatch MG, De Santis M, et al. Eau-EANM-ESTRO-ESUR-SIOG guidelines on prostate cancer. part II—2020 update: Treatment of relapsing and metastatic prostate cancer. European Urology. 2021 Feb;79(2):263–82. doi:10.1016/j. eururo. 2020.09.046.

[11] Jung E, Moon H, Cho BI, et al. Galectin-1 expression in cancer-associated stromal cells correlates with tumor invasiveness and progression in breast cancer. Int J Cancer. 2007;120(11):2331–8. doi:10.1002/ijc.22434.

[12] Rosenstein BS, Rattay T, Kang J, eds. Machine learning and artificial intelligence in radiation oncology: a guide for clinicians. 1st ed. Stacy Masucci; 2024.