Developing a Cloud-Based Platform Heart, Lung, Blood and Sleep Research
Institute or Center: National Heart, Lung, and Blood Institute (NHLBI)
Project: Developing a Cloud-Based Platform Heart, Lung, Blood and Sleep Research
- graduate level expertise in data science, biomedical informatics, and/or computer science
- interest and/or experience in oversight and management of a large consortium organized around building a new tool or platform
- familiarity with machine learning methods and applications
- experience developing strategies for data ingestion, harmonization, and secure computation across platforms
- experience with cloud computing on large datasets
- experience in data architecture, including data governance, requirements, and standardization
About the position: NHLBI seeks a DATA Scholar to work collaboratively with NHLBI and its external partners to help develop the BioData Catalyst ecosystem.
BioData Catalyst will store and enable computation on large-scale genomics, clinical, and imaging data generated by researchers. The Scholar will help develop this high-priority asset for NHLBI, gaining valuable experience in program oversight and management. The Scholar will have immediate impact on the program by bringing new ideas, expertise, and skills to help solve some of the many technological and data-related challenges involved in building this new resource:
- Machine learning: work with external collaborators and potential users of BioData Catalyst to identify opportunities to use machine learning with NHLBI data, experiment with tools, and develop appropriate educational support.
- Cross-platform computation: partner with researchers to design and conduct analyses across data from the Trans-Omics for Precision Medicine program, Million Veterans Program, UK Biobank, and other resources by implementing a “zero trust” model of computation where analytical tasks are sent to the source system for execution with only summary results leaving the source system.
- End-to-end testing: partner with our validation and verification team to develop testing strategies for common large-scale biomedical analyses, align testing with user needs, and ensure that the feedback loop is complete.
- Data harmonization: work with external collaborators to develop tools to support data harmonization and develop policies and procedures for ingesting new data.
About the work: The BioData Catalyst is a cloud-based platform where heart, lung, blood, and sleep researchers, and the broader research community, can find, search, access, share, store, crosslink, and compute on large scale datasets. It will provide controlled access to advanced cyberinfrastructure, FAIR data, leading-edge tools, applications, and workflows to enable these capabilities in secure workspaces.
- Trans-Omics for Precision Medicine
- Million Veterans Program
- UK Biobank
- Gabriella Miller Kids First Pediatric Research Program
- Datasets within the NHGRI Genomic Data Science Analysis, Visualization and Informatics Lab-space (AnVIL)
- The COPDGene® Study of Chronic Obstructive Pulmonary Disease
Why this project matters: BioData Catalyst will accelerate efficient biomedical research, democratize data and computational access, and maximize community engagement, productivity, and discovery to advance heart, lung, blood, and sleep science.
Work Location: Bethesda, MD
Work environment: The Scholar will work with a collegial, mission-driven, and multi-disciplinary team within NHLBI. The Scholar will also collaborate with leading data scientists from our academic and industry partners. The Scholar will collaborate with internationally recognized experts to solve critical challenges in this leading-edge data science project.
To apply to this or other DATA Scholar positions, please see instructions here: datascience.nih.gov/data-scholars
This page last reviewed on February 6, 2020