2021
DOI: 10.1093/bib/bbab032
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning revealed stemness features and a novel stemness-based classification with appealing implications in discriminating the prognosis, immunotherapy and temozolomide responses of 906 glioblastoma patients

Abstract: Glioblastoma (GBM) is the most malignant and lethal intracranial tumor, with extremely limited treatment options. Immunotherapy has been widely studied in GBM, but none can significantly prolong the overall survival (OS) of patients without selection. Considering that GBM cancer stem cells (CSCs) play a non-negligible role in tumorigenesis and chemoradiotherapy resistance, we proposed a novel stemness-based classification of GBM and screened out certain population more responsive to immunotherapy. The one-clas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

3
73
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 95 publications
(76 citation statements)
references
References 76 publications
3
73
0
Order By: Relevance
“…Recently, several novel prognostic markers for GBM patients have been identified through multiomic analysis and differential expression profiles. However, most of these studies are mathematical analyses based on whole-scale genetic or transcriptomic data, and there is still a lack of specific research on multiple biological pathways [ 27 29 ]. Therefore, comprehensive recognition of the characteristics of TME cell infiltration mediated by multiple cell death pathways is needed to deepen our understanding of TME immune regulation and help design enhanced treatment for GBM patients.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, several novel prognostic markers for GBM patients have been identified through multiomic analysis and differential expression profiles. However, most of these studies are mathematical analyses based on whole-scale genetic or transcriptomic data, and there is still a lack of specific research on multiple biological pathways [ 27 29 ]. Therefore, comprehensive recognition of the characteristics of TME cell infiltration mediated by multiple cell death pathways is needed to deepen our understanding of TME immune regulation and help design enhanced treatment for GBM patients.…”
Section: Introductionmentioning
confidence: 99%
“…Afterward, the high-MATH group and low-MATH group were generated, and differential gene expression analysis was performed to find DEGs differentially between the two groups. Unsupervised consensus clustering (kmeans, “ConsensusClusterPlus” package in R) ( Wang et al, 2021 ) based on these DEGs was conducted to explore a novel classification of lung adenocarcinoma: the MATH-based subtypes. This procedure was repeated 1,000 times and sampled 80% in each iteration to ensure classification stability.…”
Section: Methodsmentioning
confidence: 99%
“…Intratumor heterogeneity refers to the subclones of diverse genetic background within a tumor, and it is increasingly identified as a key factor in the treatment failure of human cancers. With the rise of next-generation sequencing and machine learning applications in oncology ( Cho et al, 2020 ; Li et al, 2021 ; Wang et al, 2021 ), computational approaches (such as ABSOLUTE) were developed to quantify intratumor heterogeneity based on biological information ( Thorsson et al, 2018 ). MATH (mutant-allele tumor heterogeneity) is a quantitative approach to depict ITH based on variant allele frequency information.…”
Section: Introductionmentioning
confidence: 99%
“…In the RNA-seq datasets (TCGA-LIHC and ICGC LIRI-JP), we took the read counts to log2-transformation for normalization ( Lian et al, 2018 ). In order to make the gene expression profiling comparable between different platforms, we then normalized with the scale method by using the limma package in R ( Wang et al, 2021 ). Patients with follow-up time 0 or without follow-up were excluded from datasets.…”
Section: Methodsmentioning
confidence: 99%