Advanced

New Probabilistic network models and algorithms for oncogenesis

Hjelm, M; Höglund, Mattias LU and Lagergren, J (2006) In Journal of Computational Biology 13(4). p.853-865
Abstract
Chromosomal aberrations in solid tumors appear in complex patterns. It is important to understand how these patterns develop, the dynamics of the process, the temporal or even causal order between aberrations, and the involved pathways. Here we present network models for chromosomal aberrations and algorithms for training models based on observed data. Our models are generative probabilistic models that can be used to study dynamical aspects of chromosomal evolution in cancer cells. They are well suited for a graphical representation that conveys the pathways found in a dataset. By allowing only pairwise dependencies and partition aberrations into modules, in which all aberrations are restricted to have the same dependencies, we reduce the... (More)
Chromosomal aberrations in solid tumors appear in complex patterns. It is important to understand how these patterns develop, the dynamics of the process, the temporal or even causal order between aberrations, and the involved pathways. Here we present network models for chromosomal aberrations and algorithms for training models based on observed data. Our models are generative probabilistic models that can be used to study dynamical aspects of chromosomal evolution in cancer cells. They are well suited for a graphical representation that conveys the pathways found in a dataset. By allowing only pairwise dependencies and partition aberrations into modules, in which all aberrations are restricted to have the same dependencies, we reduce the number of parameters so that datasets sizes relevant to cancer applications can be handled. We apply our framework to a dataset of colorectal cancer tumor karyotypes. The obtained model explains the data significantly better than a model where independence between the aberrations is assumed. In fact, the obtained model performs very well with respect to several measures of goodness of fit and is, with respect to repetition of the training, more or less unique. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
algorithm, learning, probabilistic model, cancer, chromosomal aberration, graphical representation
in
Journal of Computational Biology
volume
13
issue
4
pages
853 - 865
publisher
Mary Ann Liebert, Inc.
external identifiers
  • wos:000238488000001
  • pmid:16761915
  • scopus:33745296683
ISSN
1557-8666
DOI
10.1089/cmb.2006.13.853
language
English
LU publication?
yes
id
266ef0b3-6a81-47f5-862d-40649e4c2171 (old id 404896)
date added to LUP
2007-10-05 09:18:45
date last changed
2019-04-02 01:32:59
@article{266ef0b3-6a81-47f5-862d-40649e4c2171,
  abstract     = {Chromosomal aberrations in solid tumors appear in complex patterns. It is important to understand how these patterns develop, the dynamics of the process, the temporal or even causal order between aberrations, and the involved pathways. Here we present network models for chromosomal aberrations and algorithms for training models based on observed data. Our models are generative probabilistic models that can be used to study dynamical aspects of chromosomal evolution in cancer cells. They are well suited for a graphical representation that conveys the pathways found in a dataset. By allowing only pairwise dependencies and partition aberrations into modules, in which all aberrations are restricted to have the same dependencies, we reduce the number of parameters so that datasets sizes relevant to cancer applications can be handled. We apply our framework to a dataset of colorectal cancer tumor karyotypes. The obtained model explains the data significantly better than a model where independence between the aberrations is assumed. In fact, the obtained model performs very well with respect to several measures of goodness of fit and is, with respect to repetition of the training, more or less unique.},
  author       = {Hjelm, M and Höglund, Mattias and Lagergren, J},
  issn         = {1557-8666},
  keyword      = {algorithm,learning,probabilistic model,cancer,chromosomal aberration,graphical representation},
  language     = {eng},
  number       = {4},
  pages        = {853--865},
  publisher    = {Mary Ann Liebert, Inc.},
  series       = {Journal of Computational Biology},
  title        = {New Probabilistic network models and algorithms for oncogenesis},
  url          = {http://dx.doi.org/10.1089/cmb.2006.13.853},
  volume       = {13},
  year         = {2006},
}