http://genome.cshlp.org/content/22/7/1334.abstract?etoc Predictive regulatory models in/Drosophila melanogaster/by integrative inference of transcriptional networks 1. Daniel Marbach <http://genome.cshlp.org/search?author1=Daniel+Marbach&sortspec=date&submit=Submit>1 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-1>,2 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-2>,7 <http://genome.cshlp.org/content/22/7/1334.abstract#fn-1>, 2. Sushmita Roy <http://genome.cshlp.org/search?author1=Sushmita+Roy&sortspec=date&submit=Submit>1 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-1>,2 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-2>,3 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-3>,7 <http://genome.cshlp.org/content/22/7/1334.abstract#fn-1>, 3. Ferhat Ay <http://genome.cshlp.org/search?author1=Ferhat+Ay&sortspec=date&submit=Submit>1 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-1>,2 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-2>,4 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-4>,5 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-5>, 4. Patrick E. Meyer <http://genome.cshlp.org/search?author1=Patrick+E.+Meyer&sortspec=date&submit=Submit>1 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-1>,2 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-2>,6 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-6>, 5. Rogerio Candeias <http://genome.cshlp.org/search?author1=Rogerio+Candeias&sortspec=date&submit=Submit>1 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-1>,2 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-2>, 6. Tamer Kahveci <http://genome.cshlp.org/search?author1=Tamer+Kahveci&sortspec=date&submit=Submit>5 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-5>, 7. Christopher A. Bristow <http://genome.cshlp.org/search?author1=Christopher+A.+Bristow&sortspec=date&submit=Submit>1 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-1>,2 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-2>and 8. Manolis Kellis <http://genome.cshlp.org/search?author1=Manolis+Kellis&sortspec=date&submit=Submit>1 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-1>,2 <http://genome.cshlp.org/content/22/7/1334.abstract#aff-2>,8 <http://genome.cshlp.org/content/22/7/1334.abstract#fn-2> + <http://genome.cshlp.org/content/22/7/1334.abstract#>Author Affiliations 1. ^1 Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), Cambridge, Massachusetts 02139, USA; 2. ^2 Broad Institute of MIT and Harvard, Cambridge, Massachusetts 02140, USA; 3. ^3 Biostatistics and Medical Informatics, University of Wisconsin, Madison, Wisconsin 53706, USA; 4. ^4 Department of Genome Sciences, University of Washington, Seattle, Washington 98195, USA; 5. ^5 Computer and Information Science and Engineering, University of Florida, Gainesville, Florida 32611, USA; 6. ^6 Machine Learning Group, Faculté des Sciences, FNRS, Université Libre de Bruxelles, Brussels 1050, Belgium 1. ? <http://genome.cshlp.org/content/22/7/1334.abstract#xref-fn-1-1>7These authors contributed equally to this work. Abstract Gaining insights on gene regulation from large-scale functional data sets is a grand challenge in systems biology. In this article, we develop and apply methods for transcriptional regulatory network inference from diverse functional genomics data sets and demonstrate their value for gene function and gene expression prediction. We formulate the network inference problem in a machine-learning framework and use both supervised and unsupervised methods to predict regulatory edges *by integrating transcription factor (TF) binding, evolutionarily conserved sequence motifs, gene expression, and chromatin modification data sets as input features*. Applying these methods to/Drosophila melanogaster,/we predict ?300,000 regulatory edges in a network of ?600 TFs and 12,000 target genes. We validate our predictions using known regulatory interactions, gene functional annotations, tissue-specific expression, protein--protein interactions, and three-dimensional maps of chromosome conformation. We use the inferred network *to identify putative functions for hundreds of previously uncharacterized genes*, including many in nervous system development, which are independently confirmed based on their tissue-specific expression patterns. Last, we use the regulatory network to predict target gene expression levels as a function of TF expression, and find significantly higher predictive power for integrative networks than for motif or ChIP-based networks. Our work reveals the complementarity between physical evidence of regulatory interactions (TF binding, motif conservation) and functional evidence (coordinated expression or chromatin patterns) and demonstrates the power of data integration for network inference and studies of gene regulation at the systems level. -- Prof. Dr. Klaas Vandepoele Tel. 32 (0)9 33 13822 VIB Department of Plant Systems Biology, Ghent University Technologiepark 927, 9052 Gent, Belgium E-mail: Klaas.Vandepoele@psb.vib-ugent.be Website: http://bioinformatics.psb.ugent.be/cig/ ---------------------------------------------------------