Machine Learning Assistants Construct Oxidative Stress-Related Gene Signature and Discover Potential Therapy Targets for Acute Myeloid Leukemia

Abstract

Background. Oxidative stress (OS) is associated with the development of acute myeloid leukemia (AML). However, there is lack of relevant research to confirm that OS-related genes can guide patients in risk stratification and predict their survival probability. Method. First, we Data from three public databases, respectively. Then, we use batch univariate Cox regression and machine learning to select important characteristic genes; next, we build the model and use receiver operating characteristic curve (ROC) to evaluate the accuracy. Moreover, GSEAs were performed to discover the molecular mechanism and conduct nomogram visualization. In addition, the relative importance value was used to identify the hub gene, and GSE9476 was to validate hub gene difference expression. Finally, we use symptom mapping to predict the candidate herbs, targeting the hub gene, and put these candidate herbs into Traditional Chinese Medicine Systems Pharmacology (TCMSP) to identify the main small molecular ingredients and then docking hub proteins with this small molecular. Results. A total of 313 candidate oxidative stress-related genes could affect patients’ outcomes and machine learning to select six potential genes to construct a gene signature model to predict the overall survival (OS) of AML patients. Patients in a high group will obtain a short survival time when compared with the low-risk group ( HR = 3.97 , 95% CI: 2.48-6.36; p < 0.001 ). ROC results demonstrate the model has better prediction efficiency with AUC 0.873. GSEA suggests that this gene is enriched in several important signaling pathways. Nomogram is constructed and is robust. PLA2G4A is a hub gene of signature and associated with prognosis, and Nobiletin could target PLA2G4A for therapy AML. Conclusion. We use two different machine learning methods to build six oxidative stress-related gene signatures that could assist clinical decisions and identify PLA2G4A as a potential biomarker for AML. Nobiletin, targeting PLA2G4, may provide a third pathway for therapy AML.

A novel oxidative stress- and ferroptosis-related gene prognostic signature for distinguishing cold and hot tumors in colorectal cancer

“…It was also reported that the effects of nanomedicine in targeting ferroptosis and apoptosis can be enhanced by oxidative stress (26). In recent years, some studies focused on constructing oxidative stress or ferroptosis-related risk models for predicting patient survival and immune landscapes in various types of malignant tumors (27)(28)(29)(30)(31). However, few risk models were developed based on a combination of these two phenotypes.…”

Comprehensive analysis of prognosis of cuproptosis-related oxidative stress genes in multiple myeloma

“…A number of studies have shown that PLA2G4A (placental phospholipase A24A is involved in the biological procedure of stress response in various diseases (Brien et al, 2017;Zhang et al, 2018;Mishra et al, 2022). PLA2G4A is overexpressed in different solid cancers such as hepatocellular carcinoma (Fu et al, 2017), prostate cancer (Patel et al, 2008), breast cancer (Chen et al, 2017), cervical cancer (Xu et al, 2019), as well as malignant hematologic diseases, such as AML (acute myeloid leukemia) (Runarsson et al, 2007;Bai et al, 2020;Zhang et al, 2022) In multiple myeloma patients, expression of the PLA2G4A was higher compared to healthy individuals and high gene expression of PLA2G4A is associated with adverse outcomes Frontiers in Genetics frontiersin.org (Mahammad et al, 2021). A previous study showed that FOXO1 (Forkhead Box O1) activation could inhibit the tumor growth and induce cell autophagy and cell death.…”

Machine learning in TCM with natural products and molecules: current status and future perspectives

“…The continuous advancement of information technology and biotechnology has yielded substantial biomarker data for TCM investigations using machine learning. Zhang [ 89 ] used RF and least absolute shrinkage and selection operator (LASSO) regression to identify important characteristic genes of oxidative stress. The receiver operating characteristic results demonstrated that the model was better in prediction efficiency with an AUC of 0.873.…”