OncoImmune machine-learning model predicts immune response and prognosis in leiomyosarcoma

Leiomyosarcoma (LMS) is one of the most aggressive tumors originating from smooth muscle cells, characterized by a high recurrence rate and frequent distant metastasis. Despite advancements in targeted therapies and immunotherapies, these interventions have failed to significantly improve the long-...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingrong Deng, Changfa Shu, Dong Wang, Richard Nimbona, Xingping Zhao, Dabao Xu
Format: Article
Language:English
Published: Association of Basic Medical Sciences of Federation of Bosnia and Herzegovina 2025-06-01
Series:Biomolecules & Biomedicine
Subjects:
Online Access:https://www.bjbms.org/ojs/index.php/bjbms/article/view/12342
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Leiomyosarcoma (LMS) is one of the most aggressive tumors originating from smooth muscle cells, characterized by a high recurrence rate and frequent distant metastasis. Despite advancements in targeted therapies and immunotherapies, these interventions have failed to significantly improve the long-term prognosis for LMS patients. Here, we identified OncoImmune differential expressed genes (DEGs) that influence monocytes differentiation and the progression of LMS, revealing varied immune activation states of LMS patients. Using a machine learning approach, we developed a prognostic model based on OncoImmune hub DEGs, which offers a moderate accuracy in predicting risk levels among LMS patients. Mechanistically, we found that ATRX mutation may regulate coiled-coil domain-containing protein 69 (CCDC69) expression, leading to functional alterations in mast cells and immune unresponsiveness through the modulation of various immune-related signaling pathways. This machine learning-based prognostic model, centered on seven OncoImmune hub DEGs, along with ATRX gene status, represents promising biomarkers for predicting prognosis, molecular characteristics, and immune features in LMS.
ISSN:2831-0896
2831-090X