Skip to main content

ORIGINAL RESEARCH article

Front. Immunol.
Sec. Cancer Immunity and Immunotherapy
Volume 15 - 2024 | doi: 10.3389/fimmu.2024.1489171
This article is part of the Research Topic Application of Bioinformatics, Machine Learning, and Artificial Intelligence to Improve Diagnosis, Prognosis and Treatment of Cancer View all 7 articles

Prediction of Acute Myeloid Leukemia Prognosis based on Autophagy Features and Characterization of its Immune Microenvironment

Provisionally accepted
Xiao Zhu Xiao Zhu 1*Chaoqun Zhu Chaoqun Zhu 1Xiangyan Feng Xiangyan Feng 2*Lanxin Tong Lanxin Tong 3Peizheng Mu Peizheng Mu 1Fei Wang Fei Wang 1Wei Quan Wei Quan 1Yucui Dong Yucui Dong 4*
  • 1 Yantai University, Yantai, China
  • 2 Department of Hematology, Yantai Yuhuangding Hospital Affiliated to Qingdao University, Yantai, Shandong, China, Yantai, China
  • 3 South China Agricultural University, Guangzhou, Guangdong Province, China
  • 4 Department of Immunology, Binzhou Medical University, Yantai, Shandong, China, Yantai, China

The final, formatted version of the article will be published soon.

    Autophagy promotes the survival of acute myeloid leukemia (AML) cells by removing damaged organelles and proteins and protecting them from stress-induced apoptosis. Although many studies have identified candidate autophagy genes associated with AML prognosis, there are still great challenges in predicting the survival prognosis of AML patients. Therefore, it is necessary to identify more novel autophagy gene markers to improve the prognosis of AML by utilizing information at the molecular level. In this study, the Random Forest, SVM and XGBoost algorithms were utilized to identify autophagy genes linked to prognosis, respectively. Subsequently, six autophagy genes (TSC2, CALCOCO2, BAG3, UBQLN4, ULK1 and DAPK1) that were significantly associated with patients' overall survival (OS) were identified using Lasso-Cox regression analysis. A prediction model incorporating these autophagy genes was then developed. In addition, the immunological microenvironment analysis of autophagy genes was performed in this study. The experimental results showed that the predictive model had good predictive ability. After adjusting for clinicopathologic parameters, this feature proved an independent prognostic predictor and was validated in an external AML sample set.Analysis of differentially expressed genes in patients in the high-risk and low-risk groups showed that these genes were enriched in immune-related pathways such as humoral immune response, T cell differentiation in thymus and lymphocyte differentiation. Then immune infiltration analysis of autophagy genes in patients showed that the cellular abundance of T cells CD4 + memory activated, NK cells activated and T cells CD4 + in the high-risk group was significantly lower than that in the low-risk group. This study systematically analyzed autophagy-related genes (ARGs) and developed prognostic predictors related to OS for patients with AML, thus more accurately assessing the prognosis of AML patients. This not only helps to improve the prognostic assessment and therapeutic outcome of patients, but may also provide new help for future research and clinical applications.

    Keywords: Autophagy gene, Immune infiltration, random forest, Acute Myeloid Leukemia, prognosis

    Received: 31 Aug 2024; Accepted: 04 Nov 2024.

    Copyright: © 2024 Zhu, Zhu, Feng, Tong, Mu, Wang, Quan and Dong. 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:
    Xiao Zhu, Yantai University, Yantai, China
    Xiangyan Feng, Department of Hematology, Yantai Yuhuangding Hospital Affiliated to Qingdao University, Yantai, Shandong, China, Yantai, China
    Yucui Dong, Department of Immunology, Binzhou Medical University, Yantai, Shandong, China, Yantai, 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.