Journal article

Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation

Tathiane M Malta, Artem Sokolov, Andrew J Gentles, Tomasz Burzykowski, Laila Poisson, John N Weinstein, Bozena Kaminska, Joerg Huelsken, Larsson Omberg, Olivier Gevaert, Antonio Colaprico, Patrycja Czerwinska, Sylwia Mazurek, Lopa Mishra, Holger Heyn, Alex Krasnitz, Andrew K Godwin, Alexander J Lazar, Joshua M Stuart, Katherine A Hoadley Show all

CELL | CELL PRESS | Published : 2018

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 c..

View full abstract

Grants

Awarded by NIH


Awarded by NCI


Awarded by NIGMS


Awarded by Henry Ford Cancer Institute's Early Career Investigator Award


Awarded by Sao Paulo Research Foundation (FAPESP)


Awarded by FAPESP


Awarded by Henry Ford Hospital


Awarded by Spanish Institute of Health Carlos III


Awarded by CPRIT


Awarded by Polish Science Foundation Welcome grant


Awarded by NATIONAL CANCER INSTITUTE


Awarded by NATIONAL HUMAN GENOME RESEARCH INSTITUTE


Awarded by NATIONAL INSTITUTE OF BIOMEDICAL IMAGING AND BIOENGINEERING


Awarded by NATIONAL INSTITUTE OF DENTAL & CRANIOFACIAL RESEARCH


Awarded by NATIONAL INSTITUTE OF ENVIRONMENTAL HEALTH SCIENCES


Awarded by NATIONAL INSTITUTE OF GENERAL MEDICAL SCIENCES


Awarded by NATIONAL INSTITUTE ON ALCOHOL ABUSE AND ALCOHOLISM


Awarded by Veterans Affairs


Funding Acknowledgements

We thank Marcin Cieslik from Michigan Center for Translational Pathology at University of Michigan for providing the MTE500 dataset. This work was supported by the following grants: NIH grants U54 HG003273, U54 HG003067, U54 HG003079, U24 CA143799, U24 CA143835, U24 CA143840, U24 CA143843, U24 CA143845, U24 CA143848, U24 CA143858, U24 CA143866, U24 CA143867, U24 CA143882, U24 CA143883, U24 CA144025, and P30 CA016672; NCI grants 5R01CA180778, 3U24CA143858, 1U24CA210990, 5U54HG006097, 1U24CA210949, and 1U24CA210950; NIGMS grant 5R01GM109031; the Henry Ford Cancer Institute's Early Career Investigator Award grant A20054 to T.M.M; Sao Paulo Research Foundation (FAPESP) grants 2014/02245-3 and 2016/01975-3 to T.M.M. and H.N.; FAPESP grants 2014/08321-3, 2015/07925-5, 2016/01389-7, 2016/10436-9, 2016/06488-3, 2016/12329-5, and 2016/15485-8, and Henry Ford Hospital grant A30935 to H.N.; Spanish Institute of Health Carlos III grant CP14/00229; Mary K. Chapman Foundation gift "Chapman Foundation Fund for Bioinformatics,'' CPRIT grant RP13039, and the Michael & Susan Dell Foundation grant "The Lorraine Dell Program in Bioinformatics'' to J.N.W.; and the Polish Science Foundation Welcome grant 2010/3-3 to M.W.