Characterizing cancer subtypes as attractors of Hopfield networks

Maetschke, Stefan R. and Ragan, Mark A. (2014) Characterizing cancer subtypes as attractors of Hopfield networks. Bioinformatics, 30 9: 1273-1279. doi:10.1093/bioinformatics/btt773


Author Maetschke, Stefan R.
Ragan, Mark A.
Title Characterizing cancer subtypes as attractors of Hopfield networks
Journal name Bioinformatics   Check publisher's open access policy
ISSN 1460-2059
1367-4803
Publication date 2014-05-01
Year available 2014
Sub-type Article (original research)
DOI 10.1093/bioinformatics/btt773
Open Access Status DOI
Volume 30
Issue 9
Start page 1273
End page 1279
Total pages 7
Place of publication Oxford, United Kingdom
Publisher Oxford University Press
Language eng
Abstract Motivation: Cancer is a heterogeneous progressive disease caused by perturbations of the underlying gene regulatory network that can be described by dynamic models. These dynamics are commonly modeled as Boolean networks or as ordinary differential equations. Their inference from data is computationally challenging, and at least partial knowledge of the regulatory network and its kinetic parameters is usually required to construct predictive models.
Formatted abstract
Motivation: Cancer is a heterogeneous progressive disease caused by perturbations of the underlying gene regulatory network that can be described by dynamic models. These dynamics are commonly modeled as Boolean networks or as ordinary differential equations. Their inference from data is computationally challenging, and at least partial knowledge of the regulatory network and its kinetic parameters is usually required to construct predictive models.
Results: Here, we construct Hopfield networks from static geneexpression data and demonstrate that cancer subtypes can be characterized by different attractors of the Hopfield network. We evaluate the clustering performance of the network and find that it is comparable with traditional methods but offers additional advantages including a dynamic model of the energy landscape and a unification of clustering, feature selection and network inference. We visualize the Hopfield attractor landscape and propose a pruning method to generate sparse networks for feature selection and improved understanding of feature relationships.
Availability: Software and datasets are available at http://acb.qfab.org/acb/hclust/
Keyword Biochemical Research Methods
Biotechnology & Applied Microbiology
Computer Science, Interdisciplinary Applications
Mathematical & Computational Biology
Statistics & Probability
Biochemistry & Molecular Biology
Biotechnology & Applied Microbiology
Computer Science
Mathematical & Computational Biology
Mathematics
BIOCHEMICAL RESEARCH METHODS
BIOTECHNOLOGY & APPLIED MICROBIOLOGY
MATHEMATICAL & COMPUTATIONAL BIOLOGY
Q-Index Code C1
Q-Index Status Confirmed Code
Grant ID DP110103384
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: Official 2015 Collection
Institute for Molecular Bioscience - Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 8 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 7 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Mon, 19 May 2014, 18:02:16 EST by Professor Mark Ragan on behalf of Institute for Molecular Bioscience