Ghent University Academic Bibliography

Advanced

Simultaneous discovery of cancer subtypes and subtype features by molecular data integration

Thanh Le Van, Matthijs van Leeuwen, Ana Carolina Elisa Fierro Gutierrez, Dries De Maeyer, Jimmy Van den Eynden, Lieven Verbeke UGent, Luc De Raedt, Kathleen Marchal UGent and Siegfries Nijssen (2016) BIOINFORMATICS. 32(17). p.445-454
abstract
Motivation: Subtyping cancer is key to an improved and more personalized prognosis/treatment. The increasing availability of tumor related molecular data provides the opportunity to identify molecular subtypes in a data-driven way. Molecular subtypes are defined as groups of samples that have a similar molecular mechanism at the origin of the carcinogenesis. The molecular mechanisms are reflected by subtype-specific mutational and expression features. Data-driven subtyping is a complex problem as subtyping and identifying the molecular mechanisms that drive carcinogenesis are confounded problems. Many current integrative subtyping methods use global mutational and/or expression tumor profiles to group tumor samples in subtypes but do not explicitly extract the subtype-specific features. We therefore present a method that solves both tasks of subtyping and identification of subtype-specific features simultaneously. Hereto our method integrates' mutational and expression data while taking into account the clonal properties of carcinogenesis. Key to our method is a formalization of the problem as a rank matrix factorization of ranked data that approaches the subtyping problem as multi-view bi-clustering. Results: We introduce a novel integrative framework to identify subtypes by combining mutational and expression features. The incomparable measurement data is integrated by transformation into ranked data and subtypes are defined as multi-view bi-clusters. We formalize the model using rank matrix factorization, resulting in the SRF algorithm. Experiments on simulated data and the TCGA breast cancer data demonstrate that SRF is able to capture subtle differences that existing methods may miss.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
IBCN, IDENTIFICATION, BREAST-CANCER, GLIOBLASTOMA, MUTATIONS, CYTOSCAPE, COPY-NUMBER ALTERATION, PATTERNS, TUMORS, INTERACTION NETWORKS, GENOMIC DATA
journal title
BIOINFORMATICS
Bioinformatics
volume
32
issue
17
pages
445 - 454
conference name
15th European Conference on Computational Biology (ECCB)
conference location
The Hague, The Netherlands
conference start
2016-09-03
conference end
2016-09-07
Web of Science type
Article; Proceedings Paper
Web of Science id
000384666800008
JCR category
MATHEMATICAL & COMPUTATIONAL BIOLOGY
JCR impact factor
7.307 (2016)
JCR rank
2/57 (2016)
JCR quartile
1 (2016)
ISSN
1367-4803
DOI
10.1093/bioinformatics/btw434
project
Bioinformatics: from nucleotids to networks (N2N)
language
English
UGent publication?
yes
classification
A1
copyright statement
I have transferred the copyright for this publication to the publisher
id
8173869
handle
http://hdl.handle.net/1854/LU-8173869
date created
2016-11-28 09:04:53
date last changed
2017-04-27 08:10:32
@article{8173869,
  abstract     = {Motivation: Subtyping cancer is key to an improved and more personalized prognosis/treatment. The increasing availability of tumor related molecular data provides the opportunity to identify molecular subtypes in a data-driven way. Molecular subtypes are defined as groups of samples that have a similar molecular mechanism at the origin of the carcinogenesis. The molecular mechanisms are reflected by subtype-specific mutational and expression features. Data-driven subtyping is a complex problem as subtyping and identifying the molecular mechanisms that drive carcinogenesis are confounded problems. Many current integrative subtyping methods use global mutational and/or expression tumor profiles to group tumor samples in subtypes but do not explicitly extract the subtype-specific features. We therefore present a method that solves both tasks of subtyping and identification of subtype-specific features simultaneously. Hereto our method integrates' mutational and expression data while taking into account the clonal properties of carcinogenesis. Key to our method is a formalization of the problem as a rank matrix factorization of ranked data that approaches the subtyping problem as multi-view bi-clustering. 
Results: We introduce a novel integrative framework to identify subtypes by combining mutational and expression features. The incomparable measurement data is integrated by transformation into ranked data and subtypes are defined as multi-view bi-clusters. We formalize the model using rank matrix factorization, resulting in the SRF algorithm. Experiments on simulated data and the TCGA breast cancer data demonstrate that SRF is able to capture subtle differences that existing methods may miss.},
  author       = {Van, Thanh Le and van Leeuwen, Matthijs and Fierro Gutierrez, Ana Carolina Elisa and De Maeyer, Dries and Van den Eynden, Jimmy and Verbeke, Lieven and De Raedt, Luc and Marchal, Kathleen and Nijssen, Siegfries},
  issn         = {1367-4803},
  journal      = {BIOINFORMATICS},
  keyword      = {IBCN,IDENTIFICATION,BREAST-CANCER,GLIOBLASTOMA,MUTATIONS,CYTOSCAPE,COPY-NUMBER ALTERATION,PATTERNS,TUMORS,INTERACTION NETWORKS,GENOMIC DATA},
  language     = {eng},
  location     = {The Hague, The Netherlands},
  number       = {17},
  pages        = {445--454},
  title        = {Simultaneous discovery of cancer subtypes and subtype features by molecular data integration},
  url          = {http://dx.doi.org/10.1093/bioinformatics/btw434},
  volume       = {32},
  year         = {2016},
}

Chicago
Van, Thanh Le, Matthijs van Leeuwen, Ana Carolina Elisa Fierro Gutierrez, Dries De Maeyer, Jimmy Van den Eynden, Lieven Verbeke, Luc De Raedt, Kathleen Marchal, and Siegfries Nijssen. 2016. “Simultaneous Discovery of Cancer Subtypes and Subtype Features by Molecular Data Integration.” Bioinformatics 32 (17): 445–454.
APA
Van, T. L., van Leeuwen, M., Fierro Gutierrez, A. C. E., De Maeyer, D., Van den Eynden, J., Verbeke, L., De Raedt, L., et al. (2016). Simultaneous discovery of cancer subtypes and subtype features by molecular data integration. BIOINFORMATICS, 32(17), 445–454. Presented at the 15th European Conference on Computational Biology (ECCB).
Vancouver
1.
Van TL, van Leeuwen M, Fierro Gutierrez ACE, De Maeyer D, Van den Eynden J, Verbeke L, et al. Simultaneous discovery of cancer subtypes and subtype features by molecular data integration. BIOINFORMATICS. 2016;32(17):445–54.
MLA
Van, Thanh Le, Matthijs van Leeuwen, Ana Carolina Elisa Fierro Gutierrez, et al. “Simultaneous Discovery of Cancer Subtypes and Subtype Features by Molecular Data Integration.” BIOINFORMATICS 32.17 (2016): 445–454. Print.