Integrating multiomics analysis and machine learning to refine the molecular subtyping and prognostic analysis of stomach adenocarcinoma DOI Creative Commons

Miaodong Wang,

Qin He,

Zeshan Chen

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 30, 2025

Stomach adenocarcinoma (STAD) is a common malignancy with high heterogeneity and lack of highly precise treatment options. We downloaded the multiomics data STAD patients in The Cancer Genome Atlas (TCGA)-STAD cohort, which included mRNA, microRNA, long non-coding RNA, somatic mutation, DNA methylation data, from sxdyc website. synthesized using 10 clustering methods, construct consensus machine learning-driven signature (CMLS)-related prognostic models by combining learning evaluated prognosis C-index. relationship between CMLS was assessed Kaplan-Meier curves, independent value determined univariate multivariate regression analyses. we also immune characteristics, immunotherapy response, drug sensitivity different groups. results analysis classified into three subtypes, CS1 resulting best survival outcome. In total, hub genes (CES3, AHCYL2, APOD, EFEMP1, CYP1B1, ASPN, CPE, CLIP3, MAP1B, DKK1) were screened constructed significantly correlated an factor for STAD. Using risk score, all divided group low group. Patients low-CMLS had better survival, more enriched cells, higher tumor mutation load scores, suggesting responsiveness possible "hot tumor" phenotype. high-CMLS poorer less sensitive to but likely benefit chemotherapy targeted therapy. this study, methods combined analyze STAD, classify CMLS-related model features, are important accurate management effective

Language: Английский

Integrating multiomics analysis and machine learning to refine the molecular subtyping and prognostic analysis of stomach adenocarcinoma DOI Creative Commons

Miaodong Wang,

Qin He,

Zeshan Chen

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 30, 2025

Stomach adenocarcinoma (STAD) is a common malignancy with high heterogeneity and lack of highly precise treatment options. We downloaded the multiomics data STAD patients in The Cancer Genome Atlas (TCGA)-STAD cohort, which included mRNA, microRNA, long non-coding RNA, somatic mutation, DNA methylation data, from sxdyc website. synthesized using 10 clustering methods, construct consensus machine learning-driven signature (CMLS)-related prognostic models by combining learning evaluated prognosis C-index. relationship between CMLS was assessed Kaplan-Meier curves, independent value determined univariate multivariate regression analyses. we also immune characteristics, immunotherapy response, drug sensitivity different groups. results analysis classified into three subtypes, CS1 resulting best survival outcome. In total, hub genes (CES3, AHCYL2, APOD, EFEMP1, CYP1B1, ASPN, CPE, CLIP3, MAP1B, DKK1) were screened constructed significantly correlated an factor for STAD. Using risk score, all divided group low group. Patients low-CMLS had better survival, more enriched cells, higher tumor mutation load scores, suggesting responsiveness possible "hot tumor" phenotype. high-CMLS poorer less sensitive to but likely benefit chemotherapy targeted therapy. this study, methods combined analyze STAD, classify CMLS-related model features, are important accurate management effective

Language: Английский

Citations

0