Scientist-Computational Biology, Biomarker Platform Development
Location: San Francisco (On-site Post Covid)
1 Contract with Extension Possibilities
Summary
The Clinical Biomarkers & Diagnostics (CBD) department is looking for a highly motivated Computational Biologist with expertise in clinical bioinformatics, biomarker development, assay development, data ETL and application development. This role will operate within a multi-disciplinary setting, working closely with computational biologists, biomarker scientists and data scientists to develop data ingestion, platform analysis and applications for analyzing and visualizing clinical trial datasets with a focus on clinical biomarkers. Candidate must be familiar with verbiage and meanings of data entities in the context of clinical trials. Familiarity with diagnostics and common analytes utilized within clinical trials is required. A strong handle on clinical metadata and expected values as well as analytes and their dynamic ranges & units is needed for this role. Experience in the clinical domain with data ETL and application development in Python is a must have. Expertise in data visualization and familiarity with full-stack development is needed for this role. Excellent communication skills and great attention to details are required. Experience with clinical trial datasets and statistical analysis is a plus. Experience in DASH/AngularJS/Flask/R shiny is a plus.
Core Responsibilities
- Development of data ETL, QC, data store architecture, schema definitions, ingestion, transformation and QC logic
- Full-stack application development & deployment, integration with analysis modules, data visualization
Top 3 Must Have Skill Sets:
- Ability to analyze and interpret clinical biomarker data
- Expert level knowledge of machine learning and analytical techniques
- Experience/ interest in application development (DASH)
Day to Day Responsibilities
- Partner with Clinical Data Management, Study Management and Statistical Programming on development and standardization of data ingestion processes
- Define acceptance standards for data generated using a number of diagnostic technologies such as flow cytometry, Nanostring, NGS diagnostic assays and imaging platforms
- Perform residual data QC as needed
- Document acceptance standards, socialize them and educate stakeholders
- Author code/scripts to perform automatic quality control, formatting and transformation of data to adhere to defined standards
- Document values, dynamic ranges, controlled vocabulary and obtain organization-wide approval for this intellectual property
- Ensure that QCed data for active programs is delivered in an analyzable format in a timely manner
- Ensure that data is stored in a manner that adheres to internal standards for storage
- Make recommendations for process improvements
- Support the development of the web application through integration with backend database, and development of front end user interfaces and visualizations
- Support the deployment of the web application
- Work with computational biologists, biomarker scientists and data scientists to develop new features and visualizations
- Monitor usage of the web application and provide operational support
- Optimize the design and performance of the web application
- Write unit tests, user manual, best practices and internal documentations of the web application
