Curious about how the Advanced Research Projects Agency for Health’s (ARPA-H’s) BDF Toolbox program is progressing? You’ll be interested to know it just passed a major milestone.

ARPA-H has awarded contracts to nearly 20 teams who are tackling a broad range of projects, many of which are directly related to cancer research.

ARPA-H, in partnership with NCI, is creating the BDF Toolbox to speed scientific discovery—making it easier to share and integrate data, tools, and technology from across the country.

Below are short summaries of the newly awarded efforts and the teams behind the projects:

Advancing digital twins

• A University of Alabama team is looking at ways to collect, manage, and link data to create real-time digital simulations of patients, helping you predict outcomes and customize and monitor treatment for cancer and other disease types.

Examining data from electronic health records and clinical and imaging data

• A Boston Children’s Hospital team is using electronic health record data to enable you to rapidly and accurately detect adverse drug events in patients during treatment.
• A University of Chicago team is developing a medical imaging data hub with tools to help you measure bias and equity and integrate findings from both radiology and clinical data.
• Teams from the University of North Carolina and the Johns Hopkins University are harmonizing and linking data, making it easier for you to access clinical, claims, mortality, and imaging data, as well as other information to aid in clinical research.

Strengthening infrastructure and enhancing data access

• A team from DNA HIVE, a small business, is working on infrastructure and tools to enable you to access and query cancer health records and medical device data to investigate diseases and health outcomes.
• A team from Harvard Medical School is working to build a data-centric, visual user interface to help you explore and discover biomedical data resources on cancer research.
• A team from Insilicom LLC, another small business, is developing artificial intelligence (AI)-assisted tools to enable you to automatically make the data you collect from published scientific literature FAIR (Findable, Accessible, Interoperable, Reusable).
• The company ICF Incorporated LLC is working to break down data silos using intuitive, no-code, AI-enabled query tools, allowing you to easily explore proteomic, clinical, and other types of data.

Advancing AI-aided and machine learning tools

• A team at Stanford University is developing AI-augmented clinical decision support tools based on foundational multimodal models to help you better diagnose cancer, tailor treatment, and manage outcomes.
• A team from Netrias, a small business, is developing an AI-assisted data curation tool with standard ontology terms to build an intuitive user interface, making it easier for you to explore cancer data.
• A team from Jataware, another small business, is building an AI-assisted notebook environment to let you search and work with multimodal data, all within the same environment.
• A team from New York University is creating a new kind of AI search engine to help you find information on meta-analysis from published manuscripts, data, supplementary materials, and data repositories.
• A team led by Northeastern University is building tools to help you investigate cell signaling pathways while ensuring you’re kept “in-the-loop” when interpreting your research data.
• A team led by Renaissance Computing Institute and the University of North Carolina is combining Large Language Models with information about drugs so you can learn more about cancer therapies.
• A team led by the Massachusetts Institute of Technology is developing automated software to help you easily find existing data from scientific papers, medical images, and source code.

Ensuring quality control, testing, and data security

• A team from Charles River Analytics, another small business, will be testing and evaluating the BDF tools to ensure they meet your needs and the needs of other users.
• A team from Sage Bionetworks is building a toolset to automate and secure data collection and curation, ensuring privacy and attribution and fostering transparency.

“With these new teams in place, we’re one step closer to maximizing the use of biomedical data,” said CBIIT’s Erika Kim, Ph.D., BDF Transition and System Integration Lead at ARPA-H. 

Jill Barnholtz-Sloan, Ph.D., CBIIT’s acting director, added, “This multidisciplinary effort taps the expertise of teams from academia, nonprofits, and commercial organizations. Together, we can boost our efforts to find new and better ways of using data to improve the way we treat different diseases, starting with cancer.”

For additional information about the ARPA-H BDF Toolbox (and NCI’s role in supporting the ARPA-H agency), check out our webpage. You can also read our news article, “NCI Partners with ARPA-H on Data Fabric to Maximize Use of Research Data.”