Paper Info
Title
Reconstruction of mammalian cell cycle regulatory network from microarray data using stochastic logical networks
Abstract
We present a novel algorithm for reconstructing the topology of regulatory networks based on the Stochastic Logical Network model. Our method, by avoiding the computation of the Markov model parameters is able to reconstruct the topology of the SLN model in polynomial time instead of exponential as in previous study [29]. To test the performance of the method, we apply it to different datasets (both synthetic and experimental) covering the expression of several cell cycle regulators which have been thoroughly studied [18,11]. We compare the results of our method with the popular Dynamic Bayesian Network approach in order to quantify the ability to reconstruct true dependencies. Although both methods able to recover only a part of the true dependencies from realistic data, our method gives consistently better results than Dynamic Bayesian Networks in terms of the number of correctly reconstructed edges, sensitivity and statistical significance.
Year
DOI
Venue
2007
10.1007/978-3-540-75140-3_9
CMSB
Keywords
Field
DocType
mammalian cell cycle,cell cycle regulator,stochastic logical network,regulatory network,microarray data,markov model parameter,stochastic logical network model,sln model,better result,different datasets,novel algorithm,popular dynamic bayesian network,true dependency,dynamic bayesian networks,statistical significance,network model,cell cycle regulation,markov model,polynomial time,gene network,dynamic bayesian network,cell cycle
Boolean network,Data mining,Variable-order Bayesian network,Computer science,Markov model,Minimum description length,Bayesian network,Time complexity,Computation,Dynamic Bayesian network
Conference
Volume
ISSN
ISBN
4695
0302-9743
3-540-75139-4
Citations 
PageRank 
References 
0
0.34
15
Authors
2
Name
Order
Citations
PageRank
Bartek Wilczynski141826.85
Jerzy Tiuryn21210126.00