DNA methylation-based classification and prognosis in soft tissue sarcomas

Abstract

Background: Soft tissue sarcomas (STS) comprise a heterogeneous group of malignancies with diverse histological subtypes and variable clinical behavior. We investigated whether DNA methylation profiling can improve classification and prognostic stratification. Methods: Genome-wide methylation analysis was performed on 186 STS samples. Machine learning classifiers were trained for histotype prediction and survival analysis. Results: DNA methylation accurately classified STS histotypes and identified novel prognostic subgroups within established histological categories. Conclusions: Methylation profiling enhances diagnostic accuracy and prognostic assessment in soft tissue sarcomas.

Kristian Unger

Professor of AI assisted therapy decisions in oncology

Multi-omics integration and prediction