Medical Journal of The Islamic Republic of Iran (MJIRI)
Iran University of Medical Sciences
Sat, Jan 18, 2025
[Archive]
Volume 39, Issue 1 (1-2025)
Med J Islam Repub Iran 2025 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Valizadeh Laktarashi H, Rahimi M, Abrishamifar K, Mahmoudabadi A, Nazari E. Identification of Important Diagnostic Genes in the Uterine Using Bioinformatics and Machine Learning. Med J Islam Repub Iran 2025; 39 (1) :18-26
URL: http://mjiri.iums.ac.ir/article-1-9409-en.html
URL: http://mjiri.iums.ac.ir/article-1-9409-en.html
Department of Health Information Technology and Management, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran , Elham.Nazari@sbmu.ac.ir
Abstract: (62 Views)
Background: Uterine corpus endometrial cancer (UCEC) is known as the sixth most common cancer in the world. Advances in bioinformatics and deep learning have provided the 2 tools for screening large-scale genomic data and discovering potential biomarkers indicative of disease states. This study aimed to investigate the identification of important genes for diagnosis and prognosis in the uterus using bioinformatics and machine learning algorithms.
Methods: RNA expression profiles of UECE patients were analyzed to identify differentially expressed genes (DEGs) using deep learning techniques. Prognostic biomarkers were assessed through survival curve analysis utilizing COMBIO-ROC. Additionally, molecular pathways, protein-protein interaction (PPI) networks, co-expression patterns of DEGs, and their associations with clinical data were thoroughly examined. Ultimately, diagnostic markers were determined through deep learning-based analyses.
Results: According to our findings, MEX3B, CTRP2 (C1QTNF2), and AASS are new biomarkers for UCEC. The evaluation metrics demonstrate the deep learning model's (DNN) efficacy, with a minimal mean squared error (MSE) of 5.1096067E-5 and a root mean squared error (RMSE) of 0.007, indicative of accurate predictions. The R-squared value of 0.99 underscores the model's ability to explain a substantial portion of the variance in the data. Thus, the model achieves a perfect area under the curve (AUC) of 1, signifying exceptional discrimination ability, and an accuracy rate of 97%.
Conclusion: The GDCA database and deep learning algorithms identified 3 significant genes —MEX3B, CTRP2 (C1QTNF2), and AASS—as potential diagnosis biomarkers of UCEC. Thus, identifying new UCEC biomarkers has promise for effective care, improved prognosis, and early diagnosis.
Methods: RNA expression profiles of UECE patients were analyzed to identify differentially expressed genes (DEGs) using deep learning techniques. Prognostic biomarkers were assessed through survival curve analysis utilizing COMBIO-ROC. Additionally, molecular pathways, protein-protein interaction (PPI) networks, co-expression patterns of DEGs, and their associations with clinical data were thoroughly examined. Ultimately, diagnostic markers were determined through deep learning-based analyses.
Results: According to our findings, MEX3B, CTRP2 (C1QTNF2), and AASS are new biomarkers for UCEC. The evaluation metrics demonstrate the deep learning model's (DNN) efficacy, with a minimal mean squared error (MSE) of 5.1096067E-5 and a root mean squared error (RMSE) of 0.007, indicative of accurate predictions. The R-squared value of 0.99 underscores the model's ability to explain a substantial portion of the variance in the data. Thus, the model achieves a perfect area under the curve (AUC) of 1, signifying exceptional discrimination ability, and an accuracy rate of 97%.
Conclusion: The GDCA database and deep learning algorithms identified 3 significant genes —MEX3B, CTRP2 (C1QTNF2), and AASS—as potential diagnosis biomarkers of UCEC. Thus, identifying new UCEC biomarkers has promise for effective care, improved prognosis, and early diagnosis.
Keywords: Uterine Corpus Endometrial Carcinoma, Deep learning, Biomarker, Bioinformatic Analysis, UCEC
Type of Study: Original Research |
Subject:
Human Genetics
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
