2018
DOI: 10.1016/j.cell.2018.03.034
|View full text |Cite
|
Sign up to set email alerts
|

Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation

Abstract: Cancer progression involves the gradual loss of a differentiated phenotype and acquisition of progenitor and stem-cell-like features. Here, we provide novel stemness indices for assessing the degree of oncogenic dedifferentiation. We used an innovative one-class logistic regression (OCLR) machine-learning algorithm to extract transcriptomic and epigenetic feature sets derived from non-transformed pluripotent stem cells and their differentiated progeny. Using OCLR, we were able to identify previously undiscover… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

55
1,368
3
1

Year Published

2018
2018
2022
2022

Publication Types

Select...
9

Relationship

1
8

Authors

Journals

citations
Cited by 1,436 publications
(1,427 citation statements)
references
References 84 publications
55
1,368
3
1
Order By: Relevance
“…We then related our findings on BRG1‐regulated gene expression in GICs to gene expression patterns of GBM patient tumor specimens in the TCGA database. Among the molecular features defined by the PanCancer Atlas molecular classification , we found that BRG1 gene expression levels were positively correlated to the stemness index defined by mRNA expression patterns (mRNAsi) and to the IFN‐score (Fig. ), which assess the degree of oncogenic dedifferentiation and activation of IFN response pathway, respectively .…”
Section: Resultsmentioning
confidence: 96%
“…We then related our findings on BRG1‐regulated gene expression in GICs to gene expression patterns of GBM patient tumor specimens in the TCGA database. Among the molecular features defined by the PanCancer Atlas molecular classification , we found that BRG1 gene expression levels were positively correlated to the stemness index defined by mRNA expression patterns (mRNAsi) and to the IFN‐score (Fig. ), which assess the degree of oncogenic dedifferentiation and activation of IFN response pathway, respectively .…”
Section: Resultsmentioning
confidence: 96%
“…Recent studies have shown that chromatin‐modifying enzymes (e.g., KDM family) are sensitive to environmental factors such as metabolic state, hypoxia and stress response, and that these KDM enzymes induce chromatin modifications that regulate genes associated with pluripotency and drug resistance . The resulting methylation and transcriptional patterns have been used to derive predictive “stemness‐index” signatures that correctly classified more aggressive and metastatic tumors . However, whether epigenetic alterations can drive rapid phenotypic state transitions between cancer subpopulations without involvement of mutations is not well studied.…”
Section: Discussionmentioning
confidence: 99%
“…The last two decades of research have harnessed enormous forces to define and deeply characterize the specific population of cancer cells termed cancer stem cells (CSCs). Originally, CSCs were defined as a population with the capability to self‐renew and differentiate, and they are highly responsible for tumor growth and progression . CSCs are endowed with intrinsic resistance to chemo‐ and radiotherapy, possessing a high metastatic potential, and providing tumor relapse after treatment.…”
Section: Mechanisms Providing Stem Cell Self‐renewalmentioning
confidence: 99%