DATA SCIENTIST – MACHINE LEARNING FOR BIOMEDICAL DATA ANALYSIS | GenomeWeb

DATA SCIENTIST – MACHINE LEARNING FOR BIOMEDICAL DATA ANALYSIS

Organization
BIOASTER
Job Location
69007 Lyon
France
Job Description

Bioaster is a Technological Research Institute (TRI), the only health-related TRI in France dedicated to innovation in infectious diseases & microbiology. Fields of expertises include antimicrobials, vaccines, diagnostics, microbiota.

I - MISSIONS

The “Data management and analysis” Technological Unit is developing technologies and solutions to collect, follow, analyze, visualize and exploit the experimental data generated by the BIOASTER units: genomics, transcriptomics, proteomics, metabolomics, cytometry, imaging, and data from preclinical and clinical studies, or public databases.

The candidate will :

Propose a methodological jump for the statistical analysis of high dimensional data – from multi-omics, phenotypic and/or clinical origin - to provide strong and innovative answers to translational sciences issues of the Technology Research Institute, e.g the identification of biomarkers or the characterization of mechanisms of action, by taking more particularly into account the duality and the complexity of host-pathogen systems.

Develop the processes for a global integration and analysis of data from different sources (public, internal or generated in collaborative projects)

Contribute to the automation and the integration of these processes at the heart of the Scientific Information system and the bio-computing platforms of BIOASTER.

II - ACTIVITIES

Evaluate the technologies for the structuration and the analysis of complex or large data and perform scientific watch in this area,

In collaboration with the bioinformatics and biologists community of BIOASTER:

- identify the relevant sources of information for each project, set-up their collection, curation and delivery to the bioinformatics analysis pipelines,

- contribute to the evaluation of statistical methods for the transformation, the standardization and the integrative analyses of omics, phenotypic, preclinical and clinical data, as well as to their developments,

-        Contribute to the evolution of the bioinformatics platform, and of the processes and methods governing data storage, cloud computing, and visualization.

 

 

 

 

 

 

Requirements

PROFILE

Skills :

PhD and / or Master degree level , engineering school or equivalent in  statistics, signal processing or bioinformatics, with at least 3 - 5 years of experience in a similar function in an academic or biotech/industrial Life Sciences environment,

Expertise of supervised, non-supervised or semi supervised learning (support vector machine, decision tree and random forest, artificial neural network),

 Expertise of the multivariate statistical methods (principal component analysis, independent component analysis, correspondence analysis, correspondence canonical analysis and associates regularization methods, partial least square regression, clustering),

General knowledge of the new generation of data storage systems (graph database, NoSQL) ; 

General knowledge of data processing and analysis in the bioinformatics area,

Good knowledge of script and programming languages (BASH, Python, R)

Scientific and technological English language proficiency

Personal qualities

  • Autonomy, thoroughness, reactivity,
  • Initiative Spirit and creativity,
  • Team spirit in project mode,
  • Good communication and interpersonal skills,
  • Confidentiality and regulatory compliance
  • Quality and GxP oriented 

A trio of editors from the Nature family of journals describes what make a peer review a good one.

Spots in genetic counseling training programs are competitive, Maclean's reports.

Bitesize Bio offers some tips to make PubMed searches more efficient.

Regeneron Pharmaceuticals comes out on top of Science Careers' ranking of best biotech and pharma employers.