Medical Data Laboratory (MDLab)
The MDLab: A Data Science Center supporting medical research
The MDLab aims to answer medical research questions focused on bioinformatics, mathematical modeling and bio-statistics, resulting in the processing of large medical and environmental databases.
Faced with the major challenges involved in processing these data (namely their storage and heterogeneity, as well as ethical and legislative issues), the MDLab complies with the new European Data Protection Regulation (RGSP), which came into force on 25 May 2018.
The activity of the MDLab, supported by the collaboration between the Université Côte d'Azur and the Centre Hospitalier de Nice - CHUN, is part of the Data Science core program of the UCAJEDI project.
- Objectives
-
The MDLab is currently running two "proof of concept" projects ("Genetics" and "Health and Environment"), aimed at addressing very different issues in terms of interoperability, heterogeneity or massive data security. Once this pilot phase is completed in 2020, the MDLab will support medical research on other health issues within the Université Côte d'Azur.
Whether you are a CHUN practitioner with a medical question requiring massive data analysis, or a UCA researcher with an innovative methodology requiring applicable medical data, the MDLab will assist you in writing a protocol or a research project before submitting it to a call for proposals, assessed by the MDLab’s strategic committee. Under the responsibility of this strategic committee, the MDLab will also help to carry out projects that have already been scientifically evaluated by the Université Côte d'Azur, and which may involve private partners. In addition, the MDLab will also offer training programs focused on the new skills required to address the application of data sciences to the medical field.
If you wish to apply for national or European funding (ANR, ERC,...) and your project involves recruiting a data scientist, you can contact the MDLab executive director who will help you to write the section of the project that describes the engineer's tasks. Once the project has been accepted, the MSI will also help you to recruit the engineer and let him/her benefit from MSI start-up funds.
- Training
-
The MDLab is currently contributing to the deployment of a cycle of short training courses, organized as seminars and workshops, on data science, artificial intelligence, and data integration applied to several domains, held at the MSI site in Sophia Antipolis.
Find out more about the MSI's short training courses and subscribe to the MSI’s newsletter! - Team
-
A UCA strategic committee chaired by Professor Véronique Paquis-Flucklinger (PU-PH at the Nice University Hospital), and consisting of Université Côte d’Azur representatives, is in charge of the decisions relating to the MDLab’s activity, in consultation with the UCAJEDI project governance.
As the MDLab is an MSI expertise center, its staff works under the hierarchical authority of the Director of the MSI, Prof. Stéphane Descombes. Since January 2019, Dr. Silvia Bottini, (MDLab Operational Director), has been ensuring the proper functioning and she is currently coordinating the work carried out by Kevin Dsouza (PhD Scholarship funded by the BoostUrCareer project). Dr. Marco Milanesio is in charge of the IT infrastructure.
The MDLab also relies on a vast pool of resources, represented by CHUN medical researchers and practitioners and Université Côte d'Azur researchers in modeling, statistics and artificial intelligence.
- Areas of research
-
Genetics and rare diseases, cancer, health and environment are the current and developing research areas of the MDLab, which can particularly benefit from the databases of the following entities:
the Nice University Hospital (CHUN); the Université Côte d'Azur laboratories; the Métropôle Nice Côte d'Azur (data made available by IMREDD); the National Health Data System (SNDS), which, since April 2017, has made a national medico-administrative database available that exhaustively and permanently covers the essential health aspects of the population living in France. - Publications
-
D. Pratella, V. Duboc, M. Milanesio, J. Boudjarane, S. Descombes, V. Paquis-Flucklinger, S. Bottini. GenomeMixer and TRUST: novel bioinformatics tools to improve reliability of Non-Invasive Prenatal Testing (NIPT) for fetal aneuploidies, in Computational and Structural Biotechnology Journal, in press, 2022. https://doi.org/10.1016/j.csbj.2022.02.014.
V. Duboc, D. Pratella, M. Milanesio, J. Boudjarane, S. Descombes, V. Paquis-Flucklinger, S. Bottini. NiPTUNE: an automated pipeline for noninvasive prenatal testing in an accurate, integrative and flexible framework, in Briefings in Bioinformatics, Volume 23, Issue 1, January 2022, bbab380, https://doi.org/10.1093/bib/bbab380.
F. Simões, C. Bouveyron, D. Piga, et al. Cardiac dyspnea risk zones in the South of France identified by geo-pollution trends study, in Scientific Reports 12, 1900 (2022). https://doi.org/10.1038/s41598-022-05827-2.
C. Bouveyron, J. Jacques, A. Schmutz, F. Simões and S. Bottini, Co-Clustering of Multivariate Functional Data for the Analysis of Air Pollution in the South of France, in The Annals of Applied Statistics, in press, 2021. - Infrastructure
-
Following a needs assessment, the UCAJEDI IT equipment is a rack platform by Dell, hosted by the CHUN, in the machine room of the Pasteur site. This equipment consists of 2 computing servers and a storage server, on top of which a cloud infrastructure (VMware WSPHERE) has been deployed.
The two computing servers are the DELL R740 models, with (cumulatively) 1 TB of memory and 16 TB of storage. The storage server (DELL R740XD) contains about 90 TB of disks, of which about 70 TB are reserved for data storage. It is possible to add additional storage and CPU/GPU bricks, depending on the projects that will be carried out in the future.
The virtualization infrastructure allows us to create as many servers as necessary in the form of virtual machines. Each project has its own allocated (one for each project), dedicated and reserved storage space: data from different projects cannot be merged.
Although MDLab is not intended to store data, this may be the case for well-identified research projects during the processing of these data (by the MDLab or an external entity), and until the publication of scientific articles related to the projects.
- Contacts
-
Dr. Silvia Bottini : +33(0)630566999 ; silvia.bottini@univ-cotedazur.fr
Pilot Projects
Former Research Projects
Role of the MDLab in health research projects
