Machine learning-driven mast cell gene signatures for prognostic and therapeutic prediction in prostate cancer

Sep 21, 2026

Uploaded by Ezra

Mast cells’ role remains insufficiently clarified in prostate cancer’s unpredictable prognosis and heterogeneous immunotherapy responses. This research builds a computational framework to derive mast cell marker gene signatures (MCMGS) from a global cohort of 1091 prostate cancer patients, aiming to identify a robust predictive biomarker for prognosis and treatment selection. The study identifies mast cell-associated biomarkers across six international cohorts and develops MCMGS using multiple machine learning approaches. Immunological profiling, survival evaluation, and gene set and pathway analyses are applied to link the signature to therapeutic response mechanisms.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Background

Methods

Results

Marker genes and risk stratification

Conclusion

Heliyon 10 (2024) e35157 Contents lists available at ScienceDirect Heliyon journal [homepage:](homepage: www.cell.com/heliyon)[ www.cell.com/heliyon](homepage: www.cell.com/heliyon) Research article Machine learning-driven mast cell gene signatures for prognostic and therapeutic prediction in prostate cancer Abudukeyoumu Maimaitiyiminga, b, 1 , Hengqing Ana, b, c, **, 1 , Chen Xinga, b, c , Xiaodong Lia, b, c , Zhao Lid , Junbo Baie, Cheng Luo a, b, Tao Zhuo a, b, Xin Huanga, b , Aierpati Maimaitia, f, Abudushalamu Aikemug, Yujie Wanga, b, c, * a The First Affiliated Hospital, Xinjiang Medical University, Urumqi, China b Department of Urological, Urology Centre, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China c Xinjiang Clinical Research Center of Urogenital Diseases, Urumqi, China d Department of Abdominal Ultrasonography, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China e Department of Pediatric Urology, Urology Centre, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China f Department of Neurosurgery, Neurosurgery Centre, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China g Department of Emergency Medicine, Youai Hospital, Urumqi, Xinjiang, China A R T I C L E I N F O Keywords: Prostate cancer Mast cell markers Transcriptomics analysis Computational biology Patient stratification Predictive biomarker A B S T R A C T Background: The role of Mast cells has not been thoroughly explored in the context of prostate cancer’s (PCA) unpredictable prognosis and mixed immunotherapy outcomes. Our research aims to employs a comprehensive computational methodology to evaluate Mast cell marker gene signatures (MCMGS) derived from a global cohort of 1091 PCA patients. This approach is designed to identify a robust biomarker to assist in prognosis and predicting responses to immunotherapy. Methods: This study initially identified mast cell-associated biomarkers from prostate adenocarcinoma (PRAD) patients across six international cohorts. We employed a variety of machine learning techniques, including Random Forest, Support Vector Machine (SVM), Lasso regression, and the Cox Proportional Hazards Model, to develop an effective MCMGS from candidate genes. Subsequently, an immunological assessment of MCMGS was conducted to provide new insights into the evaluation of immunotherapy responses and prognostic assessments. Additionally, we utilized Gene Set Enrichment Analysis (GSEA) and pathway analysis to explore the biological pathways and mechanisms associated with MCMGS. Results: MCMGS incorporated 13 marker genes and was successful in segregating patients into distinct high- and low-risk categories. Prognostic efficacy was confirmed by survival analysis Abbreviations: PCA, Prostate Cancer; TCGA, The Cancer Genome Atlas; LASSO, The least absolute shrinkage and selection operator; MCMGS, Mast cell marker gene signature; BCR, Biochemical recurrence; CRPC, Castration-resistant prostate cancer; PSA, Prostate-specific antigen; AUC, Area under the curve; GEO, Gene Expression Omnibus; GO, Gene Ontology; KEGG, Kyoto Encyclopedia of Genes and Genomes; RSF, random survival forests; GBM, Generalized boosted regression modeling; GSEA, Gene Set Enrichment Analysis; TME, Tumor microenvironment; PFS, progression-free survival; TMB, tumor mutation burden. * Corresponding author. Department of Urology, Urology Centre, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China. ** Corresponding author. An Department of Urology, Urology Centre, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China. E-mail addresses: [9269735@qq.com](9269735@qq.com) (H. An), [wangyjmn@163.com](wangyjmn@163.com) (Y. Wang). 1 These authors have contributed equally to this work. [https://doi.org/10.1016/j.heliyon.2024.e35157](https://doi.org

FAQs

What problem does the study address in prostate cancer research?

The study addresses the limited understanding of mast cells in prostate cancer prognosis and the inconsistent outcomes of immunotherapy. It focuses on the need for predictive biomarkers that can support risk assessment and treatment response estimation.

How was the mast cell gene signature (MCMGS) developed?

MCMGS was constructed from candidate genes in prostate adenocarcinoma patients across six international cohorts. Multiple machine learning methods were used, including Random Forest, SVM, Lasso regression, and the Cox proportional hazards model, followed by immunological assessment.

What were the main findings regarding patient stratification and prognosis?

The final MCMGS contained 13 marker genes and successfully separated patients into distinct high- and low-risk groups. Prognostic performance was validated through survival analysis, and the signature was further analyzed alongside clinical variables.

Sep 21, 2026

Uploaded by Ezra