Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation

Tathiane M Malta; Artem Sokolov; Andrew J Gentles; Tomasz Burzykowski; Laila Poisson; John N Weinstein; Bożena Kamińska; Joerg Huelsken; Larsson Omberg; Olivier Gevaert; Antonio Colaprico; Patrycja Czerwińska; Sylwia Mazurek; Lopa Mishra; Holger Heyn; Alex Krasnitz; Andrew K Godwin; Alexander J Lazar; Joshua M Stuart; Katherine A Hoadley; Peter W Laird; Houtan Noushmehr; Maciej Wiznerowicz

doi:10.1016/j.cell.2018.03.034

Back

Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation

Journal article

Open access

Peer reviewed

Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation

Tathiane M Malta, Artem Sokolov, Andrew J Gentles, Tomasz Burzykowski, Laila Poisson, John N Weinstein, Bożena Kamińska, Joerg Huelsken, Larsson Omberg, Olivier Gevaert, …

Cell, Vol.173(2), pp.338-354.e15

04/05/2018

DOI: 10.1016/j.cell.2018.03.034

PMCID: PMC5902191

PMID: 29625051

Files and links (1)

url

https://doi.org/10.1016/j.cell.2018.03.034View

Published (Version of record) Open Access

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 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.

Machine Learning

Carcinogenesis

Cell Dedifferentiation - genetics

Databases, Genetic

DNA Methylation

Epigenesis, Genetic

Humans

MicroRNAs - metabolism

Neoplasm Metastasis

Neoplasms - genetics

Neoplasms - pathology

Stem Cells - cytology

Stem Cells - metabolism

Transcriptome

Tumor Microenvironment

Details

Title: Subtitle: Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation
Creators: Tathiane M Malta - Henry Ford Health System
Artem Sokolov - Harvard University
Andrew J Gentles - Stanford University
Tomasz Burzykowski - University of Hasselt
Laila Poisson - Henry Ford Health System
John N Weinstein - The University of Texas MD Anderson Cancer Center
Bożena Kamińska - Nencki Institute of Experimental Biology
Joerg Huelsken - École Polytechnique
Larsson Omberg - Sage Bionetworks
Olivier Gevaert - Stanford University
Antonio Colaprico - Université Libre de Bruxelles
Patrycja Czerwińska - Poznan University of Medical Sciences
Sylwia Mazurek - Poznan University of Medical Sciences
Lopa Mishra - George Washington University
Holger Heyn - Centre for Genomic Regulation
Alex Krasnitz - Cold Spring Harbor Laboratory
Andrew K Godwin - University of Kansas
Alexander J Lazar - The University of Texas MD Anderson Cancer Center
Joshua M Stuart - University of California, Santa Cruz
Katherine A Hoadley - University of North Carolina at Chapel Hill
Peter W Laird - Van Andel Institute
Houtan Noushmehr - Henry Ford Health System
Maciej Wiznerowicz - Poznan University of Medical Sciences
Contributors: Cancer Genome Atlas Research Network
Deqin Ma (Contributor) - University of Iowa, Pathology
Mohammed M Milhem (Contributor) - University of Iowa, Internal Medicine
Aaron D Bossler (Contributor) - University of Iowa, Pathology
Resource Type: Journal article
Publication Details: Cell, Vol.173(2), pp.338-354.e15
DOI: 10.1016/j.cell.2018.03.034
PMID: 29625051
PMCID: PMC5902191
ISSN: 0092-8674
eISSN: 1097-4172
Grant note: U24 CA143843 / NCI NIH HHS R01 GM109031 / NIGMS NIH HHS I01 BX003732 / BLRD VA R01 CA236591 / NCI NIH HHS P30 CA016086 / NCI NIH HHS U24 CA210957 / NCI NIH HHS R01 EB020527 / NIBIB NIH HHS U54 HG003079 / NHGRI NIH HHS P30 CA016672 / NCI NIH HHS P30 ES010126 / NIEHS NIH HHS U24 CA143883 / NCI NIH HHS U24 CA210990 / NCI NIH HHS U24 CA143799 / NCI NIH HHS R01 CA180778 / NCI NIH HHS U24 CA210988 / NCI NIH HHS R01 AA023146 / NIAAA NIH HHS U54 HG006097 / NHGRI NIH HHS R50 CA221675 / NCI NIH HHS U24 CA143867 / NCI NIH HHS U24 CA143858 / NCI NIH HHS U24 CA210974 / NCI NIH HHS U24 CA143882 / NCI NIH HHS U54 HG003067 / NHGRI NIH HHS U24 CA143845 / NCI NIH HHS U01 DE025188 / NIDCR NIH HHS U24 CA143835 / NCI NIH HHS U54 HG003273 / NHGRI NIH HHS U24 CA143840 / NCI NIH HHS U24 CA144025 / NCI NIH HHS U24 CA143866 / NCI NIH HHS U24 CA210950 / NCI NIH HHS U24 CA210949 / NCI NIH HHS U01 CA230690 / NCI NIH HHS U24 CA143848 / NCI NIH HHS R01 CA163722 / NCI NIH HHS
Language: English
Date published: 04/05/2018
Academic Unit: Hematology, Oncology, and Blood & Marrow Transplantation; Pathology; Internal Medicine
Record Identifier: 9984185171602771

Metrics

11 Record Views

1516 Times Cited - Web of Science

See more details