Skip to content

Inferring gene regression networks with model trees

by Isabel A Nepomuceno-Chamorro, Jesus S Aguilar-Ruiz, Jose C Riquelme, P Spellman, G Sherlock, M Zhang, V Iyer, K Anders, M Eisen, P Brown, D Botstein, B Futcher, MB Eisen, PT Spellman, PO Brown, D Botstein, P, X hou, M Kao, W Wong, J Stuart, E Segal, D Koller, S Kim, H Lee, A Hsu, J Sajdak, J Qin, P Pavlidis, C Wolfe, I Kohane, A Butte, A de la Fuente, N Bing, I Hoeschele, P Mendes, J Pearl, M Florian, S Rainer, T Matsuno, N Tominaga, K Arizono, T Iguchi, Y Kohara, O Banerjee, L El Ghaoui, A d, A Fitch, M Jones, J Chiquet, A Smith, G Grasseau, C Matias, C Ambroise, A Margolin, I Nemenman, K Basso, C Wiggins, G Stolovitzky, R Favera, A Califano, W Zhao, E Serpedin, ER Dougherty, P Qiu, A Gentles, S Plevritis, B Wilczynski, N Dojer, E Segal, M Shapira, A Regev, D Pe, A Joshi, R De Smet, K Marchal, Y Van de Peer, T Michoel, E Steele, A Tucker, PAC, S Mehra, W Hu, G Karypis, L Soinov, M Krestyaninova, A Brazma, I Ponzoni, F Azuaje, J Augusto, D Glass, Y Benjamini, D Yekutieli, D Malerba, F Esposito, M Ceci, J Morgan, J Sonquist, L Breiman, J Friedman, C Stone, R Olshen, J Quinlan, I Witten, E Frank, Y Pawitan, S Michiels, S Koscielny, A Gusnanto, A Ploner, D Sheskin, D Marbach, RJ Prill, T Schaffter, C Mattiussi, D Floreano, G Stolovitzky, D Marbach, T Schaffter, D Floreano, R Prill, G Stolovitzky, D Marbach, T Schaffter, C Mattiussi, D Floreano, J Schafer, K Strimmer, R Opgen-Rhein, K Strimmer, C Charbonnier, J Chiquet, C Ambroise, C Ambroise, J Chiquet, C Matias, SG Boettcher, C Dethlefsen, R Cho, M Campbell, E Winzeler, S L, A Conway, L Wodicka, T Wolfsberg, A Gabrielian, D Landsman, D Lockhart, G Berriz, O King, B Bryant, C Sander, F Roth, P Westfall, S Young, P Shannon, A Markiel, O Ozier, N Baliga, J Wang, D Ramage, N Amin, B Schwikowski, T Ideker show all authors
BMC Bioinformatics ()
Get full text at journal

Abstract

Novel strategies are required in order to handle the huge amount of data produced by microarray technologies. To infer gene regulatory networks, the first step is to find direct regulatory relationships between genes building the so-called gene co-expression networks. They are typically generated using correlation statistics as pairwise similarity measures. Correlation-based methods are very useful in order to determine whether two genes have a strong global similarity but do not detect local similarities. We propose model trees as a method to identify gene interaction networks. While correlation-based methods analyze each pair of genes, in our approach we generate a single regression tree for each gene from the remaining genes. Finally, a graph from all the relationships among output and input genes is built taking into account whether the pair of genes is statistically significant. For this reason we apply a statistical procedure to control the false discovery rate. The performance of our approach, named REG NET, is experimentally tested on two well-known data sets: Saccharomyces Cerevisiae and E.coli data set. First, the biological coherence of the results are tested. Second the E.coli transcriptional network (in the Regulon database) is used as control to compare the results to that of a correlation-based method. This experiment shows that REG NET performs more accurately at detecting true gene associations than the Pearson and Spearman zeroth and first-order correlation-based methods. REG NET generates gene association networks from gene expression data, and differs from correlation-based methods in that the relationship between one gene and others is calculated simultaneously. Model trees are very useful techniques to estimate the numerical values for the target genes by linear regression functions. They are very often more precise than linear regression models because they can add just different linear regressions to separate areas of the search space favoring to infer localized similarities over a more global similarity. Furthermore, experimental results show the good performance of REG NET.

Cite this document (BETA)

Readership Statistics

1 Reader on Mendeley
by Discipline
 
100% Computer Science
by Academic Status
 
100% Researcher

Sign up today - FREE

Mendeley saves you time finding and organizing research. Learn more

  • All your research in one place
  • Add and import papers easily
  • Access it anywhere, anytime

Start using Mendeley in seconds!

Sign up & Download

Already have an account? Sign in