Marie-Laure Martin-Magniette

Researcher (CR) at the Institut National de la Recherche Agronomique

1. in the joint Research Unit UMR 518 of Applied Mathematics and Computer

Sciences (Stat & Genome Team)

1. in the joint Research Unit URGV (Bioinformatics group).
   

Phone: (3)(0)1 44 08 72 09 (Paris)
Phone: (3)(0)1 60 87 45 18 (Evry)
Fax: (3)(0)1 44 08 16 66

Mail : marie_laure.martin@agroparistech.fr

Member of the Statistics of Biological Sequences Group (SSB)
Member of the research group Select
Associated editor of BMC Genomics

• Statistical Methodology
  • Variable selection in Gaussian Mixture models
  • Mixture models
  • Model selection

• Statistical Applications in Molecular Biology
  • Microarray data (normalisation and differential analysis)
  • Tiling array analysis
  • ChIP-chip
  • Global analysis of microarray data

Co-supervisor with Gilles Celeux of the thesis of Cathy Maugis Variable selection for model-based clustering. Application for transcriptome data analysis.

Co-supervisor with Stéphane Robin of the thesis of Caroline Bérard Statistical and bioinformatic analysis of ChIP-chip data and transcriptome data from tiling array.

Co-supervisor with Stéphane Robin of the thesis of Stevenn Volant Statistical methods for transcriptome tiling-array data.

R packages

Anapuce: normalisation and differential analysis of transcriptome data

MixThres: mixture model of truncated gaussians to detect a hybridization threshold for microarray data

ChIPmix: mixture model of regression for chIP-chip data

Softwares

SelvarClust is a software implemented in C++ with object-oriented programming. It is devoted to the variable selection in model-based clustering. It is a greedy algorithm associated to the SR modeling proposed by Maugis et al. (2009) in Biometrics. This software allows us to study data where individuals are described by quantitative block variables. It returns a data clustering and the selected model, composed of the number of clusters, the mixture form and the variable partition.

SelvarClustMV is a software implemented in C++ with object-oriented programming. It is an extension of SelvarClust, it is devoted to the variable selection in model-based clustering allowing for missing value. Currently, this software is proposed for Gaussian mixtures whose variance matrices are assumed to be identical and free (m=[pkLC]).

SelvarClustIndep is a software implemented in C++ with object-oriented programming. It is devoted to the variable selection in model-based clustering. It is a greedy algorithm associated to the SRUW modeling proposed by Maugis et al. (2009) in CSDA. The SRUW modeling takes into account three possible roles for each variable: relevant, redundant and independent. This software allows to study datasets where observations are described by quantitative variables. It returns a data clustering and the selected model composed of the number of clusters, the mixture form, the variance matrix form for the linear regression and the independent Gaussian density, and the variable partition.

SONATA.Stat is a group of statisticians, biologists and bioinformaticians involved in the project SONATA (Stress Orphean Network and Transcriptome in Arabidopsis). This group received a financial support of the MIA department of INRA.

My publications