SAS Programmer/Biomarker Statistician Project Leader
Location: Bridgewater, New Jersey
Biomarker Statistician Project Leader
The role of Biomarkers in the clinical drug development process has an increasing importance because it can help to accelerate the clinical development process of a compound, to reduce R&D costs, and to bring better innovative drugs to patients. Therefore, the identification, analyses and use of Biomarkers in clinical studies become more and more important for informed decision making processes.
The Biomarker Statistician Project Leader is involved in the clinical development process early on to lead the statistical aspects of the Biomarker discussions as part of the project team regarding identification and use of diagnostic, prognostic and predictive Biomarkers.
Biomarker Statistician Project Leader include:
- Provide appropriate input for the definition of the translational plan of the clinical development plan (e.g., identification or validation of drug target, identification of treatment responders) in collaboration with project team members
- Lead all statistical aspects of the study related Biomarker discussion
- Planning, analyzing and reporting of high dimensional/omics data for official and exploratory Biomarker analyses
- Promote and implement machine learning approaches (e.g. clustering, SVM, random forest, deep learning) on biomarker omics datasets (transcriptomics, genomics, metabolomics …)
- Define Biomarker Statistical Analyses Plans using state-of-the-art methodology
- Support with statistical knowledge the implementation of standard tools for data analyses
- Keep knowledge about new technical, statistical and methodological developments and discuss use for internal clinical data/studies/projects
- Contribute to operation process optimization and provide inputs to statistics standards in biomarker field.
- MS or PhD in a Statistics, Mathematics, Computer Science or related field
- At least 3 years experiences in the pharmaceutical industry
- Strong knowledge of advanced statistical concepts and techniques in particular for high-dimensional data (cross-validation, multiple testing correction, feature selection)
- Expertise in omics data bioinformatics and statistical analysis
- Experience in Machine Learning algorithms: penalized regression, SVM, random forest …
- Strong knowledge of R
- Bioconductor and python would be a plus
- Demonstrated strong project management, interpersonal and communication skills