Kernel methods for genomic data fusion

Abstract: Despite significant advances in omics techniques, the identification of genes causing rare genetic diseases and the understanding of the molecular networks underlying those disorders remains difficult. Gene prioritization attempts to integrate multiple, heterogeneous data sources to identify candidate genes most likely to be associated with or causative for a disorder. Such strategies are useful both to support clinical genetic diagnosis and to speed up biological discovery. Genomic data fusion algorithms are rapidly maturing statistical and machine learning techniques have emerged that integrate complex, heterogeneous information (such as sequence similarity, interaction networks, expression data, annotation, or biomedical literature) towards prioritization, clustering, or prediction. In this talk, we will focus in particular on kernel methods and will propose several strategies for prioritization and clustering in particular. We also go beyond learning methods as such by addressing how such strategies can be embedded into the daily practice of geneticists, mostly through collaborative knowledge bases that integrate tightly with prioritization and network analysis methods.

Bio: Yves Moreau does research on computational methods for systems biology, with the aim of understanding how variation in a personal genome leads to variation in risk and severity of genetic disease through differential perturbation of molecular networks. At the application level, he focuses on diagnosis and disease gene discovery in congenital genetic disorders. At the computational level, he focuses on kernel methods and probabilistic graphical models for fusion of multiple, heterogeneous sources of data to prioritize candidate disease genes. He also focuses on the computational infrastructure necessary to bring new technologies (array comparative genomic hybridization and next-generation sequencing) to routine clinical application in medical genetics. He coordinates SymBioSys "from variome to phenome", a large interfaculty effort within the university to leverage next-generation sequencing and data integration to understand molecular events flowing from genomic variation to phenotype variation in human genetic disorders. He is currently a professor of engineering at the University of Leuven. He is an associate editor for IEEE Transactions on Computational Biology and Bioinformatics. He is also a co-founder of two spin-off starts of the university (Data4s, now part of Detica / BAE Systems, specialized in data-mining for the banking industry, and Cartagenia, specialized in IT solutions for clinical genetic diagnosis). He chaired the 2010 edition of the European Conference on Computational Biology. He was a Fulbright scholar at Brown University, Providence, RI in 1992-1994 and a visiting researcher at the Center for Biological Sequence Analysis at the Technical University of Denmark in 2003-2004.