Interpretable Multiomics Machine Learning Identifies GSDMB-Associated Epigenetic Repression and Reduced Immune Activity in Metastatic Colorectal Cancer
- 1Universidade de Sao Paulo
Abstract
Background: Colorectal cancer (CRC) is a major cause of cancer-related mortality, with distant metastasis strongly associated with poor clinical outcomes. Integrating transcriptomic and epigenomic data through machine learning may improve the molecular characterization of metastatic CRC. Methods: We analyzed 518 primary tumors from the TCGA-COAD/READ cohort (436 non-metastatic [M0] and 82 metastatic [M1]) with matched RNA-seq and DNA methylation data. Five machine learning classifiers were evaluated for discrimination of metastatic status using stratified nested cross-validation. Model explainability was assessed using model coefficients for linear classifiers and SHAP-based feature importance for tree-based models. Differential expression, functional enrichment, methylation-expression correlation, immune-related transcriptional scoring, statistical mediation, and survival analyses were subsequently performed. Results: Integrated RNA-seq and DNA methylation showed the strongest discrimination between M0 and M1 tumors, with SVM reaching a ROC-AUC of 0.787 +/- 0.047. Six features - ARC, ASPDH, C13orf15, C4orf23, GPATCH3, and cg12040555 - ranked among the top 20 predictors across four models with consistent directions. cg10057218 methylation was inversely correlated with GSDMB expression (Spearman rho = -0.589) and increased in M1 tumors. Statistical mediation indicated a significant indirect association between M1 status and reduced GSDMB expression through cg10057218 methylation (indirect effect = -0.370; 95% CI [-0.519, -0.224]; proportion mediated = 82.1%). M1 tumors also exhibited reduced immune-related transcriptional activity. A 20-feature canonical molecular score separated M1 from M0 tumors (in-sample ROC-AUC = 0.918), while the corresponding Logistic Regression model achieved a nested cross-validated ROC-AUC of 0.781 +/- 0.046. Higher scores were associated with shorter overall survival (log-rank p = 1.67 x 10^-7). Conclusions: Transcriptomic and DNA methylation integration identified a consistently prioritized multiomics feature set associated with metastatic CRC. The findings highlight coordinated molecular and immune-related differences between M0 and M1 tumors and identify cg10057218-associated GSDMB repression as a candidate epigenetic feature of metastatic disease.
Related
- Integrated methylome–transcriptome profiling reveals epigenetic regulation of immune activation pathways and CSN3-associated lactation repression in bovine subclinical mastitis
- Multiomics Characterization Identifies S1P-secreting USSHigh Skeletal Muscle Stem Cells as Essential Drivers of Niche Remodeling and Muscle Regeneration
- Multiomics Dissection of Early-Onset Colorectal Cancer (EOCRC) Reveals an Immunosuppressive Microenvironment and Identifies FAT3 Mutation as a Biomarker of Hot-Like Immune Features.
- Spatial multiomics identifies rheumatoid arthritis synovial niches and de-novo laminar histological patterns of fibroblasts subtypes
- Screening of epigenetic modifiers identifies novel host-directed agents that suppress HIV-1 replication in primary human macrophages
BibTeX
@misc{costa2026interpretable,
title = {{Interpretable Multiomics Machine Learning Identifies GSDMB-Associated Epigenetic Repression and Reduced Immune Activity in Metastatic Colorectal Cancer}},
author = {M. d. S. Costa and H. I. Marcelo and G. A. Kafouri and V. De Camargo},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.01.748124},
url = {https://www.biorxiv.org/content/10.64898/2026.09.01.748124v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Interpretable Multiomics Machine Learning Identifies GSDMB-Associated Epigenetic Repression and Reduced Immune Activity in Metastatic Colorectal Cancer
AU - M. d. S. Costa
AU - H. I. Marcelo
AU - G. A. Kafouri
AU - V. De Camargo
PY - 2026
DA - 2026/09/01
PB - bioRxiv
DO - 10.64898/2026.09.01.748124
UR - https://www.biorxiv.org/content/10.64898/2026.09.01.748124v1
AB - Background: Colorectal cancer (CRC) is a major cause of cancer-related mortality, with distant metastasis strongly associated with poor clinical outcomes. Integrating transcriptomic and epigenomic data through machine learning may improve the molecular characterization of metastatic CRC. Methods: We analyzed 518 primary tumors from the TCGA-COAD/READ cohort (436 non-metastatic [M0] and 82 metastatic [M1]) with matched RNA-seq and DNA methylation data. Five machine learning classifiers were evaluated for discrimination of metastatic status using stratified nested cross-validation. Model explainability was assessed using model coefficients for linear classifiers and SHAP-based feature importance for tree-based models. Differential expression, functional enrichment, methylation-expression correlation, immune-related transcriptional scoring, statistical mediation, and survival analyses were subsequently performed. Results: Integrated RNA-seq and DNA methylation showed the strongest discrimination between M0 and M1 tumors, with SVM reaching a ROC-AUC of 0.787 +/- 0.047. Six features - ARC, ASPDH, C13orf15, C4orf23, GPATCH3, and cg12040555 - ranked among the top 20 predictors across four models with consistent directions. cg10057218 methylation was inversely correlated with GSDMB expression (Spearman rho = -0.589) and increased in M1 tumors. Statistical mediation indicated a significant indirect association between M1 status and reduced GSDMB expression through cg10057218 methylation (indirect effect = -0.370; 95% CI [-0.519, -0.224]; proportion mediated = 82.1%). M1 tumors also exhibited reduced immune-related transcriptional activity. A 20-feature canonical molecular score separated M1 from M0 tumors (in-sample ROC-AUC = 0.918), while the corresponding Logistic Regression model achieved a nested cross-validated ROC-AUC of 0.781 +/- 0.046. Higher scores were associated with shorter overall survival (log-rank p = 1.67 x 10^-7). Conclusions: Transcriptomic and DNA methylation integration identified a consistently prioritized multiomics feature set associated with metastatic CRC. The findings highlight coordinated molecular and immune-related differences between M0 and M1 tumors and identify cg10057218-associated GSDMB repression as a candidate epigenetic feature of metastatic disease.
ER -