Sage Bionetworks is recruiting a Data Scientist to support our open science initiatives in computational oncology. Sage is a non-profit research organization in Seattle, WA that seeks to develop predictors of disease and accelerate health research through the creation of open systems, incentives, and standards. We create strategies and platforms that empower researchers to share and interpret data on a colossal scale, crowdsource tests for new hypotheses, and contribute to knowledge through community challenges. At the base of all of these efforts is the need to create globally coherent biological data sets that are Findable, Accessible, Interoperable, and Re-usable.
We are seeking someone to join in the development of an open knowledge portal in oncology who understands the complexities of working with dozens of scientific laboratories to combine and manage heterogeneous biological data sources, including the difficulties of standardizing metadata, and the value that standardization can provide to support reproducible research.
Specific Responsibilities Include:
- Working with a team of bioinformaticians, statisticians, and software developers at Sage to coordinate and manage resource and data sharing efforts among a large consortium of cancer researchers
- Leading a team of scientists from collaborating biomedical research labs to identify or develop standards and protocols for storing, describing, and sharing heterogeneous data (including clinical, genomic, and imaging datasets) and tools
- Creating tools to use or build on existing APIs to manage data, implement standards, apply metadata, and enable facile upload of curated data to publicly funded repositories
- Interacting with collaborators to identify data management needs, respond to requests for data and programmatic support, generate reports, and provide training
- Communicating research findings including organizing web sites and the design/creation of dashboards, visualizations, and other resources for experimental and clinical biologists to explore and leverage data and analysis results
- PhD computer science, bioinformatics or MS in information and/or library sciences with 2+ years working in research data management in the biological sciences
- Experience with R and/or Python programming, particularly with data visualization libraries
- Experience managing data and computing within distributed compute environments and interacting with SQL-like databases
- Experience with genomic data and familiarity with collaborative development and version control systems (e.g., git)