Supervised Inference of Gene Regulatory Networks by Linear Programming

The development of algorithms for reverse-engineering gene regulatory networks is boosted by microarray technologies, which enable the simultaneous measurement of all RNA transcripts in a cell. Meanwhile the curated repository of regulatory associations between transcription factors (TF) and target genes is available based on bibliographic references. In this paper we propose a novel method to combine time-course microarray dataset and documented or potential known transcription regulators for inferring gene regulatory networks. The gene network reconstruction algorithm is based on linear programming and performed in the supervised learning framework. We have tested the new method using both simulated data and experimental data. The result demonstrates the effectiveness of our method which significantly alleviates the problem of data scarcity and remarkably improves the reliability.

[1]  K. Aihara,et al.  Stability of genetic regulatory networks with time delay , 2002 .

[2]  Neal S. Holter,et al.  Dynamic modeling of gene expression data. , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[3]  K. Aihara,et al.  Stability and bifurcation analysis of differential-difference-algebraic equations , 2001 .

[4]  A. Hartemink.  Reverse engineering gene regulatory networks , 2005, Nature Biotechnology.

[5]  J. Collins,et al.  Inferring Genetic Networks and Identifying Compound Mode of Action via Expression Profiling , 2003, Science.

[6]  David J. Galas,et al.  Dynamic models of gene expression and classification , 2001, Functional & Integrative Genomics.

[7]  Trupti Joshi,et al.  Inferring gene regulatory networks from multiple microarray datasets , 2006, Bioinform..

[8]  Jesper Tegnér,et al.  Reverse engineering gene networks using singular value decomposition and robust regression , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[9]  J. Hasty,et al.  Reverse engineering gene networks: Integrating genetic perturbations with dynamical modeling , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[10]  Marcel J. T. Reinders,et al.  ROBUST GENETIC NETWORK MODELING BY ADDING NOISY DATA , 2001 .

[11]  Diego di Bernardo,et al.  Inference of gene regulatory networks and compound mode of action from time course gene expression profiles , 2006, Bioinform..