Extracting gene regulation information from microarray time-series data using hidden Markov models. Yogurtcu, O. N., Erzin, E., & Gursoy, A. In Levi, A, Savas, E, Yenigun, H, Balcisory, S, & Saygin, Y, editors, Computer and Information Sciences - ISCIS 2006, Proceedings, volume 4263, of LECTURE NOTES IN COMPUTER SCIENCE, pages 144-153, 2006. Sabanci Univ, Fac Engn & Nat Sci; Sci & Technol Res Council Turkey; Sabanci Univ; Inst Elect & Elect Engineers, Turkey Sect; IFIP. 21st International Symposium on Computer and Information Sciences (ISCIS 2006), Istanbul, TURKEY, NOV 01-03, 2006
abstract   bibtex   
Finding gene regulation information from microarray time-series data is important to uncover transcriptional regulatory networks. Pearson correlation is the widely used method to find similarity between time-series data. However, correlation approach fails to identify gene regulations if time-series expressions do not have global similarity, which is mostly the case. Assuming that gene regulation time-series data exhibits temporal patterns other than global similarities, one can model these temporal patterns. Hidden Markov models (HMMs) are well established structures to learn and model temporal patterns. In this study, we propose a new method to identify regulation relationships from microarray time-series data using HMMs. We showed that the proposed HMM based approach detects gene regulations, which are not captured by correlation methods. We also compared our method with recently proposed gene regulation detection approaches including edge detection, event method and dominant spectral component analysis. Results on Spellman's alpha-synchronized yeast cell-cycle data clearly present that HMM approach is superior to previous methods.
@inproceedings{ ISI:000243130100017,
Author = {Yogurtcu, Osman N. and Erzin, Engin and Gursoy, Attila},
Editor = {{Levi, A and Savas, E and Yenigun, H and Balcisory, S and Saygin, Y}},
Title = {{Extracting gene regulation information from microarray time-series data
   using hidden Markov models}},
Booktitle = {{Computer and Information Sciences - ISCIS 2006, Proceedings}},
Series = {{LECTURE NOTES IN COMPUTER SCIENCE}},
Year = {{2006}},
Volume = {{4263}},
Pages = {{144-153}},
Note = {{21st International Symposium on Computer and Information Sciences (ISCIS
   2006), Istanbul, TURKEY, NOV 01-03, 2006}},
Organization = {{Sabanci Univ, Fac Engn \& Nat Sci; Sci \& Technol Res Council Turkey;
   Sabanci Univ; Inst Elect \& Elect Engineers, Turkey Sect; IFIP}},
Abstract = {{Finding gene regulation information from microarray time-series data is
   important to uncover transcriptional regulatory networks. Pearson
   correlation is the widely used method to find similarity between
   time-series data. However, correlation approach fails to identify gene
   regulations if time-series expressions do not have global similarity,
   which is mostly the case. Assuming that gene regulation time-series data
   exhibits temporal patterns other than global similarities, one can model
   these temporal patterns. Hidden Markov models (HMMs) are well
   established structures to learn and model temporal patterns. In this
   study, we propose a new method to identify regulation relationships from
   microarray time-series data using HMMs.
   We showed that the proposed HMM based approach detects gene regulations,
   which are not captured by correlation methods. We also compared our
   method with recently proposed gene regulation detection approaches
   including edge detection, event method and dominant spectral component
   analysis. Results on Spellman's alpha-synchronized yeast cell-cycle data
   clearly present that HMM approach is superior to previous methods.}},
ISSN = {{0302-9743}},
ISBN = {{3-540-47242-8}},
ResearcherID-Numbers = {{Erzin, Engin/H-1716-2011
   Gursoy, Attila/E-9565-2015}},
ORCID-Numbers = {{Erzin, Engin/0000-0002-2715-2368
   Gursoy, Attila/0000-0002-2297-2113}},
Unique-ID = {{ISI:000243130100017}},
}
Downloads: 0