Robust Cluster Prediction Across Data Types Validates Association of Sex and Therapy Response in GBM
Language
English
Publication Date
1-28-2025
Journal
Cancers
DOI
10.3390/cancers17030445
PMID
39941811
PMCID
PMC11815886
PubMedCentral® Posted Date
1-28-2025
PubMedCentral® Full Text Version
Post-print
Abstract
Background: Previous studies have described sex-specific patient subtyping in glioblastoma. The cluster labels associated with these "legacy data" were used to train a predictive model capable of recapitulating this clustering in contemporary contexts.
Methods: We used robust ensemble machine learning to train a model using gene microarray data to perform multi-platform predictions including RNA-seq and potentially scRNA-seq.
Results: The engineered feature set was composed of many previously reported genes that are associated with patient prognosis. Interestingly, these well-known genes formed a predictive signature only for female patients, and the application of the predictive signature to male patients produced unexpected results.
Conclusions: This work demonstrates how annotated "legacy data" can be used to build robust predictive models capable of multi-target predictions across multiple platforms.
Keywords
clustering, disease subtyping, machine learning, glioblastoma multiforme, GBM, feature engineering, gene expression signatures, female
Published Open-Access
yes
Recommended Citation
Gibbs, David L; Cioffi, Gino; Aguilar, Boris; et al., "Robust Cluster Prediction Across Data Types Validates Association of Sex and Therapy Response in GBM" (2025). Faculty and Staff Publications. 5260.
https://digitalcommons.library.tmc.edu/baylor_docs/5260