Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning
Abstract Background Acute Myeloid Leukemia (AML) is a highly heterogeneous hematologic malignancy influenced by various factors affecting prognosis. Recently, the role of coagulation-related genes in tumor biology has garnered increasing attention. This study aims to investigate the expression patte...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | European Journal of Medical Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40001-025-02975-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849345243789393920 |
|---|---|
| author | Liyun Ji Yanxia Yang Siyue Ma |
| author_facet | Liyun Ji Yanxia Yang Siyue Ma |
| author_sort | Liyun Ji |
| collection | DOAJ |
| description | Abstract Background Acute Myeloid Leukemia (AML) is a highly heterogeneous hematologic malignancy influenced by various factors affecting prognosis. Recently, the role of coagulation-related genes in tumor biology has garnered increasing attention. This study aims to investigate the expression patterns of coagulation-related genes in AML and their clinical relevance. Methods We obtained RNA-seq data and clinical information for AML patients from The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO), followed by data cleaning and normalization. Unsupervised consensus clustering was performed to identify molecular subtypes, and Kaplan–Meier survival analysis was utilized to assess survival differences. We further identified differentially expressed genes (DEGs) between groups and conducted functional enrichment analyses. Additionally, a prognostic model was constructed using machine learning techniques, and its prognostic ability was validated. Results Clustering analysis categorized 151 tumor samples into the high coagulation-related gene expression group (C1, high-expression) and the low coagulation-related gene expression group (C2, low-expression), revealing 1,747 DEGs. Functional enrichment analysis indicated that DEGs were mainly associated with leukocyte migration and cytokine signaling pathways. Immune landscape analysis showed that the high expression group had elevated immune and stromal scores, distinct immune cell infiltration patterns, and a higher ESTIMATE score. The constructed coagulation score risk model indicated that age, cytogenetics, and risk scores were significantly associated with AML prognosis. Furthermore, intersection analysis using three machine learning methods identified MMP7 and F12 as key biomarkers. Conclusion Our study demonstrates that coagulation-related genes play a crucial role in the molecular characteristics, prognostic assessment, and immune modulation in AML. MMP7 and F12 are highlighted as potential biomarkers that could aid in optimizing the diagnosis and treatment strategies for AML. These findings offer new insights into personalized therapies for AML. |
| format | Article |
| id | doaj-art-37b3b2bfa8d447c1938ad87c8e9e792d |
| institution | Kabale University |
| issn | 2047-783X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | European Journal of Medical Research |
| spelling | doaj-art-37b3b2bfa8d447c1938ad87c8e9e792d2025-08-20T03:42:30ZengBMCEuropean Journal of Medical Research2047-783X2025-08-0130111510.1186/s40001-025-02975-9Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learningLiyun Ji0Yanxia Yang1Siyue Ma2Department of Hematology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer HospitalDepartment of Hematology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer HospitalDepartment of General Surgery, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer HospitalAbstract Background Acute Myeloid Leukemia (AML) is a highly heterogeneous hematologic malignancy influenced by various factors affecting prognosis. Recently, the role of coagulation-related genes in tumor biology has garnered increasing attention. This study aims to investigate the expression patterns of coagulation-related genes in AML and their clinical relevance. Methods We obtained RNA-seq data and clinical information for AML patients from The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO), followed by data cleaning and normalization. Unsupervised consensus clustering was performed to identify molecular subtypes, and Kaplan–Meier survival analysis was utilized to assess survival differences. We further identified differentially expressed genes (DEGs) between groups and conducted functional enrichment analyses. Additionally, a prognostic model was constructed using machine learning techniques, and its prognostic ability was validated. Results Clustering analysis categorized 151 tumor samples into the high coagulation-related gene expression group (C1, high-expression) and the low coagulation-related gene expression group (C2, low-expression), revealing 1,747 DEGs. Functional enrichment analysis indicated that DEGs were mainly associated with leukocyte migration and cytokine signaling pathways. Immune landscape analysis showed that the high expression group had elevated immune and stromal scores, distinct immune cell infiltration patterns, and a higher ESTIMATE score. The constructed coagulation score risk model indicated that age, cytogenetics, and risk scores were significantly associated with AML prognosis. Furthermore, intersection analysis using three machine learning methods identified MMP7 and F12 as key biomarkers. Conclusion Our study demonstrates that coagulation-related genes play a crucial role in the molecular characteristics, prognostic assessment, and immune modulation in AML. MMP7 and F12 are highlighted as potential biomarkers that could aid in optimizing the diagnosis and treatment strategies for AML. These findings offer new insights into personalized therapies for AML.https://doi.org/10.1186/s40001-025-02975-9Acute Myeloid LeukemiaCoagulationConsensus Clustering AnalysisPrognostic ModelImmune Microenvironment |
| spellingShingle | Liyun Ji Yanxia Yang Siyue Ma Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning European Journal of Medical Research Acute Myeloid Leukemia Coagulation Consensus Clustering Analysis Prognostic Model Immune Microenvironment |
| title | Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning |
| title_full | Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning |
| title_fullStr | Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning |
| title_full_unstemmed | Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning |
| title_short | Unveiling the role of coagulation-related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning |
| title_sort | unveiling the role of coagulation related genes in acute myeloid leukemia prognosis and immune microenvironment through machine learning |
| topic | Acute Myeloid Leukemia Coagulation Consensus Clustering Analysis Prognostic Model Immune Microenvironment |
| url | https://doi.org/10.1186/s40001-025-02975-9 |
| work_keys_str_mv | AT liyunji unveilingtheroleofcoagulationrelatedgenesinacutemyeloidleukemiaprognosisandimmunemicroenvironmentthroughmachinelearning AT yanxiayang unveilingtheroleofcoagulationrelatedgenesinacutemyeloidleukemiaprognosisandimmunemicroenvironmentthroughmachinelearning AT siyuema unveilingtheroleofcoagulationrelatedgenesinacutemyeloidleukemiaprognosisandimmunemicroenvironmentthroughmachinelearning |