Information-Theoretic Inference of Large Transcriptional Regulatory Networks

1687-4153-2007-79879 1687-4153 Research Article Information-Theoretic Inference of Large Transcriptional Regulatory Networks MeyerEPatrickpmeyer@ulb.ac.be KontosKevinkkontos@ulb.ac.be LafitteFredericflafitte@ulb.ac.be BontempiGianlucagbonte@ulb.ac.be

ULB Machine Learning Group, Computer Science Department, Université Libre de Bruxelles, Brussels 1050, Belgium

EURASIP Journal on Bioinformatics and Systems Biology 1687-4153 2007 2007 1 79879 http://bsb.eurasipjournals.com/content/2007/1/79879 10.1155/2007/79879 261200712520072462007 2007Patrick E. Meyer et al.This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

The paper presents MRNET, an original method for inferring genetic networks from microarray data. The method is based on maximum relevance/minimum redundancy (MRMR), an effective information-theoretic technique for feature selection in supervised learning. The MRMR principle consists in selecting among the least redundant variables the ones that have the highest mutual information with the target. MRNET extends this feature selection principle to networks in order to infer gene-dependence relationships from microarray data. The paper assesses MRNET by benchmarking it against RELNET, CLR, and ARACNE, three state-of-the-art information-theoretic methods for large (up to several thousands of genes) network inference. Experimental results on thirty synthetically generated microarray datasets show that MRNET is competitive with these methods.

[12345678910111213141516171819202122232425262728]

Genetic network modelingvan SomerenEPWesselsLFABackerEReindersMJTPharmacogenomics20023450752510.1517/14622416.3.4.50712164774Reverse-engineering transcription control networksGardnerTSFaithJJPhysics of Life Reviews200521658810.1016/j.plrev.2005.01.001Approximating discrete probability distributions with dependence treesChowCLiuCIEEE Transactions on Information Theory196814346246710.1109/TIT.1968.1054142Mutual information relevance networks: functional genomic clustering using pairwise entropy measurementsButteAJKohaneISPacific Symposium on Biocomputing2000418429ARACNE: an algorithm for the reconstruction of gene regulatory networks in a mammalian cellular contextMargolinAANemenmanIBassoKBMC Bioinformatics200671S710.1186/1471-2105-7-S1-S7176448417254312Large-scale mapping and validation of <it>Escherichia coli</it> transcriptional regulation from a compendium of expression profilesFaithJJHayeteBThadenJTPLoS Biology200751e810.1371/journal.pbio.0050008176443817214507PearlJProbabilistic Reasoning in Intelligent Systems: Networks of PlausibleMorgan Kaufmann, San Fransisco, Calif, USA1988Learning Bayesian networks from data: an information-theory based approachChengJGreinerRKellyJBellDLiuWArtificial Intelligence20021371-2439010.1016/S0004-3702(02)00191-1Network information and connected correlationsSchneidmanEStillSBerryMJIIBialekWPhysical Review Letters200391234 pagesMultivariate dependence, and genetic network inferenceNemenmanITech. Rep. NSF-KITP-04-54KITP, UCSB, Santa Barbara, Calif, USA2004Application of the mutual information criterion for feature selection in computer-aided diagnosisTourassiGDFrederickEDMarkeyMKFloydCEJr.Medical Physics200128122394240210.1118/1.141872411797941Minimum redundancy feature selection from microarray gene expression dataDingCPengHJournal of Bioinformatics and Computational Biology20053218520510.1142/S021972000500100415852500On the use of variable complementarity for feature selection in cancer classificationMeyerPEBontempiGApplications of Evolutionary Computing: EvoWorkshops, Lecture Notes in Computer ScienceSpringer, Berlin, GermanyRothlauf F, Branke J, Cagnoniet S, et al.200639079110210.1007/11732242_9Biological network inference using redundancy analysisMeyerPEKontosKBontempiGProceedings of the 1st International Conference on Bioinformatics Research and Development (BIRD '07), Berlin, Germany, March 2007916927Discovering functional relationships between RNA expression and chemotherapeutic susceptibility using relevance networksButteAJTamayoPSlonimDGolubTRKohaneISProceedings of the National Academy of Sciences of the United States of America20009722121821218610.1073/pnas.2203921971731511027309CoverTMThomasJAElements of Information TheoryJohn Wiley & Sons, New York, NY, USA1990Greedy and local search heuristics for unconstrained binary quadratic programmingMerzPFreislebenBJournal of Heuristics20028219721310.1023/A:1017912624016A Bayesian regression approach to the inference of regulatory networks from gene expression dataRogersSGirolamiMBioinformatics200521143131313710.1093/bioinformatics/bti48715879452SynTReN: a generator of synthetic gene expression data for design and analysis of structure learning algorithmsvan den BulckeTvan LeemputKNaudtsBBMC Bioinformatics200674310.1186/1471-2105-7-43137360416438721Estimation of entropy and mutual informationPaninskiLNeural Computation20031561191125310.1162/089976603321780272Nonparametric entropy estimation: an overviewBeirlantJDudewicaEJGyofiLvan der MeulenEJournal of Statistics1997611739Supervised and unsupervised discretization of continuous featuresDoughertyJKohaviRSahamiMProceedings of the 12th International Conference on Machine Learning (ML '95), Lake Tahoe, Calif, USA, July 1995194202The case against accuracy estimation for comparing induction algorithmsProvostFJFawcettTKohaviRProceedings of the 15th International Conference on Machine Learning (ICML '98), Madison, Wis, USA, July 1998Morgan Kaufmann445453Markov networks for detecting overlapping elements in sequence dataBockhorstJCravenMAdvances in Neural Information Processing Systems 17MIT Press, Cambridge, Mass, USASaul LK, Weiss Y, Bottou L2005193200Approximate statistical tests for comparing supervised classification learning algorithmsDietterichTGNeural Computation19981071895192310.1162/0899766983000171979744903Construction of large-scale Bayesian networks by local to global searchHwangKBLeeJWChungS-WZhangB-TProceedings of the 7th Pacific Rim International Conference on Artificial Intelligence (PRICAI '02), Tokyo, Japan, August 2002375384Algorithms for large scale markov blanket discoveryTsamardinosIAliferisCStatnikovAProceedings of the 16th International Florida Artificial Intelligence Research Society Conference (FLAIRS '03), St. Augustine, Fla, USA, May 2003376381Towards principled feature selection: relevancy, filters and wrappersTsamardinosIAliferisCProceedings of the 9th International Workshop on Artificial Intelligence and Statistics (AI&Stats '03), Key West, Fla, USAJanuary 2003