KEY TAKEAWAYS
- The study aimed to investigate the role of MPMφ subpopulations in metastatic UVM and develop a prognostic model based on their gene expression.
- Researchers found that MPMφ subpopulations shape the TME and developed a prognostic model for UVM.
Although there has been some progress in the treatment of primary uveal melanoma (UVM), distant metastasis remains the leading cause of death in patients. Monitoring, staging, and treatment of metastatic disease have not yet reached consensus.
More than half of metastatic tumors (62%) are diagnosed within 5 years after primary tumor treatment, the remainder are only detected in the following 25 years. The mechanisms of UVM metastasis and its impact on prognosis are not yet fully understood.
Yifang Sun and the team aimed to assess the impact of these macrophage subpopulations on the tumor immune microenvironment and use their findings to create a prognostic model for predicting UVM patient outcomes.
They performed an inclusive analysis using scRNA-seq data of UVM samples to identify and characterize macrophage subpopulations. High-dimensional weighted gene co-expression network analysis (HdWGCNA) was conducted to uncover key gene modules associated with metastatic protective macrophages (MPMφ) in primary samples, followed by functional analyses. Non-negative matrix factorization (NMF) clustering and immune cell infiltration analyses were carried out using the MPMφ gene signatures.
Machine learning models were developed to distinguish primary from metastatic patients based on identified metastatic protective macrophage-related genes (MPMRGs). A deep learning convolutional neural network (CNN) model was constructed using MPMRGs and cell type associations. Finally, a prognostic model based on MPMRGs was established and validated in independent patient cohorts.
About the results, single-cell RNA-seq analysis revealed a unique immune microenvironment landscape in primary samples compared to metastatic samples, with an enrichment of macrophage cells. Using HdWGCNA, MPMφ and marker genes were identified.
Functional analysis demonstrated an enrichment of genes related to antigen processing and immune response. Machine learning and deep learning models based on key genes proved highly effective in distinguishing between primary and metastatic patients. The prognostic model based on these key genes showed substantial predictive value for the survival of patients with UVM.
The study concluded that key macrophage subpopulations related to metastatic samples significantly influence the tumor immune microenvironment. Additionally, a prognostic model based on macrophage cell genes was developed, demonstrating its potential for predicting the prognosis of patients with UVM.
The study was funded by the Guangzhou Health Science and Technology Foundation and the Haizhu District Science and Technology Program.
Source: https://pubmed.ncbi.nlm.nih.gov/39075441/
Sun Y, Wu J, Zhang Q, et al. (2024). “Single-cell hdWGCNA reveals metastatic protective macrophages and development of deep learning model in uveal melanoma.” J Transl Med. 2024 Jul 29;22(1):695. doi: 10.1186/s12967-024-05421-2. PMID: 39075441; PMCID: PMC11287857.
