Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation

The Cancer Genome Atlas Research Network

Research output: Contribution to journalArticlepeer-review

1244 Scopus citations


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 undiscovered biological mechanisms associated with the dedifferentiated oncogenic state. Analyses of the tumor microenvironment revealed unanticipated correlation of cancer stemness with immune checkpoint expression and infiltrating immune cells. We found that the dedifferentiated oncogenic phenotype was generally most prominent in metastatic tumors. Application of our stemness indices to single-cell data revealed patterns of intra-tumor molecular heterogeneity. Finally, the indices allowed for the identification of novel targets and possible targeted therapies aimed at tumor differentiation. Stemness features extracted from transcriptomic and epigenetic data from TCGA tumors reveal novel biological and clinical insight, as well as potential drug targets for anti-cancer therapies.

Original languageEnglish (US)
Pages (from-to)338-354.e15
Issue number2
StatePublished - Apr 5 2018


  • The Cancer Genome Atlas
  • cancer stem cells
  • dedifferentiation
  • epigenomic
  • genomic
  • machine learning
  • pan-cancer
  • stemness

ASJC Scopus subject areas

  • General Biochemistry, Genetics and Molecular Biology


Dive into the research topics of 'Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation'. Together they form a unique fingerprint.

Cite this