%0 Journal Article %T Machine Learning Patterns for Neuroimaging-Genetic Studies in the Cloud %+ Modelling brain structure, function and variability based on high-field MRI data (PARIETAL) %+ Scalable Storage for Clouds and Beyond (KerData) %+ Cloud Team %+ Institute of Psychiatry, Psychology & Neuroscience, King's College London %+ Adolescent psychopathology and Medicine %+ McConnell Brain Imaging Centre (MNI) %+ School of Psychology [Nottingham] %+ Department of Genetic Epidemiology in Psychiatry [Mannhein] %+ Service NEUROSPIN (NEUROSPIN) %+ Henry H. Wheeler Jr. Brain Imaging Center [Berkeley] %A da Mota, Benoit %A Tudoran, Radu %A Costan, Alexandru %A Varoquaux, Gaël %A Brasche, Goetz %A Conrod, Patricia J. %A Lemaitre, Hervé %A Paus, Tomáš %A Rietschel, Marcella %A Frouin, Vincent %A Poline, Jean-Baptiste %A Antoniu, Gabriel %A Thirion, Bertrand %Z Projet Digiteo 2012-051D Icogen %< avec comité de lecture %@ 1662-5196 %J Frontiers in Neuroinformatics %I Frontiers %S Recent advances and the future generation of neuroinformatics infrastructure %V 8 %8 2014-04-08 %D 2014 %R 10.3389/fninf.2014.00031 %K heritability %K machine learning %K neuroimaging-genetic %K cloud computing %K fMRI %K heritability. %Z Computer Science [cs]/Bioinformatics [q-bio.QM] %Z Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]Journal articles %X Brain imaging is a natural intermediate phenotype to understand the link between genetic information and behavior or brain pathologies risk factors. Massive efforts have been made in the last few years to acquire high-dimensional neuroimaging and genetic data on large cohorts of subjects. The statistical analysis of such data is carried out with increasingly sophisticated techniques and represents a great computational challenge. Fortunately, increasing computational power in distributed architectures can be harnessed, if new neuroinformatics infrastructures are designed and training to use these new tools is provided. Combining a MapReduce framework (TomusBLOB) with machine learning algorithms (Scikit-learn library), we design a scalable analysis tool that can deal with non-parametric statistics on high-dimensional data. End-users describe the statistical procedure to perform and can then test the model on their own computers before running the very same code in the cloud at a larger scale. We illustrate the potential of our approach on real data with an experiment showing how the functional signal in subcortical brain regions can be significantly fit with genome-wide genotypes. This experiment demonstrates the scalability and the reliability of our framework in the cloud with a two weeks deployment on hundreds of virtual machines. %G English %2 https://inria.hal.science/hal-01057325/document %2 https://inria.hal.science/hal-01057325/file/frontiers.pdf %L hal-01057325 %U https://inria.hal.science/hal-01057325 %~ CEA %~ INSTITUT-TELECOM %~ EC-PARIS %~ UNIV-RENNES1 %~ CNRS %~ INRIA %~ UNIV-UBS %~ INSA-RENNES %~ INRIA-RENNES %~ IRISA %~ APHP %~ INRIA-SACLAY %~ IRISA_SET %~ OPENAIRE %~ INRIA_TEST %~ TESTALAIN1 %~ IRISA-INSA-R %~ IRISA-D1 %~ INRIA2 %~ UR1-HAL %~ UR1-MATH-STIC %~ UR1-UFR-ISTIC %~ JOLIOT %~ CEA-DRF %~ TEST-UNIV-RENNES %~ NEUROSPIN %~ TEST-UR-CSS %~ UNIV-RENNES %~ INRIA-RENGRE %~ INRIA-300009 %~ INSTITUTS-TELECOM %~ ANR %~ UR1-MATH-NUM %~ INRIA-ETATSUNIS %~ INRIA-CANADA %~ INRIA-ROYAUMEUNI %~ INRIA-ALLEMAGNE