Reverse Engineering of Gene Networks with LASSO and Nonlinear Basis Functions
2009 (English)In: CHALLENGES OF SYSTEMS BIOLOGY: COMMUNITY EFFORTS TO HARNESS BIOLOGICAL COMPLEXITY, ISSN 0077-8923 , Vol. 1158, 265-275 p.Article in journal (Refereed) Published
The quest to determine cause from effect is often referred to as reverse engineering in the context of cellular networks. Here we propose and evaluate an algorithm for reverse engineering a gene regulatory network from time-series kind steady-state data. Our algorithmic pipeline, which is rather standard in its parts but not in its integrative composition, combines ordinary differential equations, parameter estimations by least angle regression, and cross-validation procedures for determining the in-degrees and selection of nonlinear transfer functions. The result of the algorithm is a complete directed net-work, in which each edge has been assigned a score front it bootstrap procedure. To evaluate the performance, we submitted the outcome of the algorithm to the reverse engineering assessment competition DREAM2, where we used the data corresponding to the InSillico1 and InSilico2 networks as input. Our algorithm outperformed all other algorithms when inferring one of the directed gene-to-gene networks.
Place, publisher, year, edition, pages
2009. Vol. 1158, 265-275 p.
reverse engineering, network inference, nonlinear, DREAM conference, LARS, LASSO
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-18289DOI: 10.1111/j.1749-6632.2008.03764.xOAI: oai:DiVA.org:liu-18289DiVA: diva2:217864
This is the authors’ version of the following article:
Mika Gustafsson, Michael Hörnquist, Jesper Lundstrom, Johan Bjorkegren and Jesper Tegnér, Reverse Engineering of Gene Networks with LASSO and Nonlinear Basis Functions, 2009, Annals of the New York Academy of Sciences, Volume 1158 Issue, The Challenges of Systems Biology Community Efforts to Harness Biological Complexity, 265-275.
which has been published in final form at:
Copyright: Blackwell Publishing Ltd