Constructing lactylation-related genes prognostic model to effectively predict the disease-free survival and treatment responsiveness in prostate cancer based on machine learning

• DOI: 10.3389/fgene.2024.1343140
• Publication Date: 2024-03-19T04:45:49Z
• Authors: Jinyou Pan; Jianpeng Zhang; Jingwei Lin; Yinxin Cai; Zhigang Zhao
• Keywords: Nomogram; Lasso

Background: Prostate cancer (PCa) is one of the most common malignancies in men with a poor prognosis. It therefore great clinical importance to find reliable prognostic indicators for PCa. Many studies have revealed pivotal role protein lactylation tumor development and progression. This research aims analyze effect lactylation-related genes on PCa Methods: By downloading mRNA-Seq data TCGA PCa, we obtained differential related Five machine learning algorithms were used screen key then five overlapping construct survival model by lasso cox regression analysis. Furthermore, relationships between pathways, mutation immune cell subpopulations, drug sensitivity explored. Moreover, two risk groups established according score calculated (LRGs). Subsequently, nomogram scoring system was predict disease-free (DFS) patients combining clinicopathological features scores. In addition, mRNA expression levels verified lines qPCR. Results: We identified 5 LRGs (ALDOA, DDX39A, H2AX, KIF2C, RACGAP1) constructed model. The AUC values 1 -, 3 5-year DFS dataset 0.762, 0.745, 0.709, respectively. found better predictor than traditional A that combined variables accurately predicted outcome patients. high-risk group higher proportion regulatory T cells M2 macrophage, burden, worse prognosis those low-risk group. had lower IC50 certain chemotherapeutic drugs, such as Docetaxel, Paclitaxel be highly expressed castration-resistant cells. Conclusion: can effectively therapeutic responses