abrain

This project finished in 2013, now continued by Z-CloudFlow and MediLearn.

Goals of the project

 

Joint acquisition of neuroimaging and genetic data on large cohorts of subjects is a new approach used to assess and understand the variability that exists between individuals, and that has remained poorly understood so far. As both neuroimaging- and genetic-domain observations represent a huge amount of variables (of the order of 106), performing statistically rigorous analyses on such amounts of data represents a computational challenge that cannot be addressed with conventional computational techniques. On one hand, sophisticated regression techniques need to be used in order to perform sensitive analysis on these large datasets; on the other hand, the cost entailed by parameter optimization and statistical validation procedures (e.g. permutation tests). However, the computational framework can easily by run in parallel.

 

In this project, researchers of the Parietal and KerData INRIA teams will jointly address address this computational problem using cloud computing techniques on Microsoft Azure cloud computing environment. The two teams bring their complementary expertise: KERDATA (Rennes) in the area of scalable cloud data management and PARIETAL (Saclay) in the field of neuroimaging and genetics data analysis. The Map-Reduce programming model has recently arisen as a very effective approach to develop high-performance applications over very large distributed systems such as grids and now clouds. KerData has recently proposed a set of algorithms for data management, combining versioning with decentralized metadata management to support scalable, efficient, fine-grain access to massive, distributed Binary Large OBjects (BLOBs) under heavy concurrency. The project investigates the benefits of integrating BlobSeer with Microsoft Azure storage services and aims to evaluate the impact of using BlobSeer on Azure with large-scale application experiments such as the genetics-neuroimaging data comparisons addressed by Parietal.

 

This project will thus bring together researchers from algorithmic and statistical analysis domain on the one hand, and researchers involved on the organization of data management in intensive computation on the other hand, to work on the Microsoft Azure platform in order to unveil the relationships between genes and brain characteristics.

  • Bertrand Thirion
    Bertrand Thirion
    Bertrand Thirion is Research director at Inria Saclay Ile de France, head of the PARIETAL Research group. Main research interests - Geometry – Statistical modelling, model selection, multivariate analysis – Application to anatomical ...
  • Gabriel Antoniu
    Gabriel Antoniu
    Relevant research topics: parallel and distributed computing, distributed data storage and management, cloud computing, grid computing, P2P systems, transparent data sharing, fault tolerance in distributed data systems, data consistency, ...

2015

Communication dans un congrès

titre
Towards Multi-site Metadata Management for Geographically Distributed Cloud Workflows
auteur
Luis Pineda-Morales, Alexandru Costan, Gabriel Antoniu
article
CLUSTER 2015 – IEEE International Conference on Cluster Computing, Sep 2015, Chicago, United States. 2015, <10.1109/CLUSTER.2015.49>
Accès au texte intégral et bibtex
http://hal.inria.fr/hal-01239150/file/cluster.pdf BibTex

Poster

titre
Scaling Smart Appliances for Spatial Data Synthesis
auteur
Luis Pineda-Morales, Balaji Subramaniam, Kate Keahey, Gabriel Antoniu, Alexandru Costan, Shaowen Wang, Anand Padmanabhan, Aiman Soliman
article
SC15 – ACM/IEEE International Conference in Supercomputing, Nov 2015, Austin, United States. 2015, <http://sc15.supercomputing.org/>
Accès au texte intégral et bibtex
http://hal.inria.fr/hal-01241718/file/Pineda-Morales_SC.pdf BibTex

2012

Communication dans un congrès

titre
A MapReduce Approach for Ridge Regression in Neuroimaging-Genetic Studies
auteur
Benoit Da Mota, Michael Eickenberg, Soizic Laguitton, Vincent Frouin, Gaël Varoquaux, Jean-Baptiste Poline, Bertrand Thirion
article
DCICTIA-MICCAI – Data- and Compute-Intensive Clinical and Translational Imaging Applications in conjonction with the 15th International Conference on Medical Image Computing and Computer Assisted Intervention – 2012, Oct 2012, Nice, France. 2012
Accès au texte intégral et bibtex
http://hal.inria.fr/hal-00730385/file/article.pdf BibTex
titre
A fast computational framework for genome-wide association studies with neuroimaging data
auteur
Benoit Da Mota, Vincent Frouin, Edouard Duchesnay, Soizic Laguitton, Gaël Varoquaux, Jean-Baptiste Poline, Bertrand Thirion
article
20th International Conference on Computational Statistics (COMPSTAT 2012), Aug 2012, Limassol, Cyprus. 2012
Accès au texte intégral et bibtex
http://hal.inria.fr/hal-00720265/file/article.pdf BibTex