Related Experiment Video
Updated: Jun 12, 2025
08:50
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
6.9K
OncoImmune machine-learning model predicts immune response and prognosis in leiomyosarcoma
Jingrong Deng1, Changfa Shu2, Dong Wang3
1Department of Obstetrics and Gynecology, The Third Xiangya Hospital of Central South University, Changsha, Hunan, China.
Biomolecules & Biomedicine
|June 11, 2025
Summary
This study identifies key genes influencing leiomyosarcoma (LMS) progression and immune responses. A machine learning model using these genes and ATRX status may improve prognosis prediction for aggressive LMS tumors.
Area of Science:
- Oncology
- Immunology
- Genetics
Background:
- Leiomyosarcoma (LMS) is an aggressive smooth muscle tumor with poor prognosis.
- Current therapies offer limited improvement for LMS patients.
- Understanding LMS immune microenvironment is crucial for novel treatment strategies.
Purpose of the Study:
- Identify OncoImmune differential expressed genes (DEGs) impacting LMS progression and monocyte differentiation.
- Develop a machine learning-based prognostic model for LMS risk stratification.
- Investigate the mechanistic link between ATRX mutation, CCDC69 expression, and immune unresponsiveness in LMS.
Main Methods:
- Differential gene expression analysis using OncoImmune data.
- Machine learning model development for prognostic prediction.
- Analysis of ATRX mutation and CCDC69 expression in relation to immune pathways.
Main Results:
- Identified OncoImmune DEGs associated with varying immune activation states in LMS.
- Developed a prognostic model with moderate accuracy based on seven OncoImmune hub DEGs and ATRX status.
- Found ATRX mutation may regulate CCDC69, affecting mast cell function and immune response.
Conclusions:
- A machine learning model integrating OncoImmune hub DEGs and ATRX status shows promise as a biomarker for LMS prognosis.
- These findings offer insights into LMS molecular characteristics and immune evasion mechanisms.
- Further validation is needed to establish clinical utility for predicting LMS patient outcomes.
