TY - JOUR T1 - BRANE Clust: Cluster-Assisted Gene Regulatory Network Inference Refinement JF - bioRxiv DO - 10.1101/114769 SP - 114769 AU - Aurélie Pirayre AU - Camille Couprie AU - Laurent Duval AU - Pesquet Jean-Christophe Y1 - 2017/01/01 UR - http://biorxiv.org/content/early/2017/03/07/114769.abstract N2 - Discovering meaningful gene interactions is crucial for the identification of novel regulatory processes in cells. Building accurately the related graphs remains challenging due to the large number of possible solutions from available data. Nonetheless, enforcing a priori on the graph structure, such as modularity, may reduce network indeterminacy issues. BRANE Clust (Biologically-Related A priori Network Enhancement with Clustering) refines gene regulatory network (GRN) inference thanks to cluster information. It works as a post-processing tool for inference methods (i.e. CLR, GENIE3). In BRANE Clust, the clustering is based on the inversion of a system of linear equations involving a graph-Laplacian matrix promoting a modular structure. Our approach is validated on DREAM4 and DREAM5 datasets with objective measures, showing significant comparative improvements. We provide additional insights on the discovery of novel regulatory or co-expressed links in the inferred Escherichia coli network evaluated using the STRING database. The comparative pertinence of clustering is discussed computationally (SIMoNe, WGCNA, X-means) and biologically (RegulonDB). BRANE Clust software will be available at: http://www-syscom.univ-mlv.fr/~pirayre/Codes-GRN-BRANE-clust.html Aurélie Pirayre Aurelie Pirayre received the State Engineering degree in biosciences from Institut Supérieur des Biosciences de Paris (ISBS) in 2013. She is completing a PhD student in signal processing at Université Paris-Est and IFP Energies nouvelles (IFPEN). Her research interests in bioinformatics include gene network inference problems from transcriptomic data. She focuses on aspects of graph theory, penalized criteria, discrete and continuous optimization. Camille Couprie Camille Couprie earned a PhD in computer science at the Université Paris Est and ESIEE Paris, advised by Professors Laurent Najman and Hugues Talbot in 2011, and awarded by the CNRS, DGA and EADS. Then she was postdoctoral researcher at the Courant Institute of Mathematical Sciences at New York University with Professor Yann LeCun, working on semantic segmentation. In 2013 she joined IFP Energies nouvelles in France to work on signal and image processing problems applied to energy problematics. Since 2015 she is a research scientist at Facebook Artificial Intelligence Research in Paris, focusing on the learning of image representations with limited supervision. Laurent Duval Laurent Duval (S’98-M’00) received the State Engineering degree in electrical engineering from Supélec, Gif-sur-Yvette, France, and the Master (DEA) in pure and applied mathematics from Universite de Metz, France, in 1996. He received in 2000 the Ph. D. degree from the Université Paris-Sud (XI), Orsay, France, in the area of seismic data compression. In 1998, he was a research assistant in the MDSP Lab in Boston University, MA, USA (Truong Q. Nguyen’s team). He now works on signal processing and image analysis research in several energy related fields (chemistry, geosciences, biotechnology and transportation) at IFP Energies nouvelles (IFPEN). Jean-Christophe Pesquet Jean-Christophe Pesquet received the engineering degree from Supelec, Gif-sur-Yvette, France, in 1987, the Ph.D. degree from the University Paris-Sud (XI), Paris, France, in 1990, and the Habilitation á Diriger des Recherches from the University Paris-Sud in 1999. From 1991 to 1999, he was a Maitre de Conferences at the University Paris-Sud, and a Research Scientist at the Laboratoire des Signaux et Systemes, Centre National de la Recherche Scientifique (CNRS), Gif-sur-Yvette. From 1999 to 2016, he was a Professor with the University Paris-Est Marne-la-Vallée, France and from 2012 to 2016, he was the Deputy Director of the Laboratoire d’Informatique of the university (UMR-CNRS 8049). He is currently a Professor (exceptional class) with CentraleSupelec, University Paris-Saclay and a Research Scientist at the Center for Visual Computing (INRIA). He is also a senior member of the Institut Universitaire de France and an IEEE Fellow. His research interests include multiscale analysis, statistical signal processing, inverse problems, imaging, and optimization methods with applications to data sciences. ER -