About
Data science is an interdisciplinary field of inquiry in which quantitative and analytic approaches, processes, and systems are used to extract knowledge and insights from large and diverse sets of data.
About Informatics and Data Science at NCI
credit: iStock
NCI is poised to accelerate developments in cancer research through data science by empowering scientists and clinicians with the data and tools needed to drive their research. NCI embraces this charge and is committed to enhancing the data sharing and analysis infrastructure, creating a comprehensive data sharing vision and strategy, and strengthening the data science workforce for NCI and the cancer research community. This is done in collaboration across NCI’s divisions, offices, and centers (DOCs), and throughout the cancer research community.
- a new job within the cancer data science field? Visit our “Jobs & Fellowships” news section to explore NCI postings. NCI is committed to core values, allowing you to reach your potential and contribute to the institute’s mission.
- basic training on the comprehensive, team-science-oriented field of cancer data science? Visit our “Training” section to learn more!
About CBIIT
Our Mission:
CBIIT empowers NCI staff and the cancer research community with the data science, information technology, and data sharing tools they need to advance our knowledge of cancer.
Our Vision:
To accelerate ground-breaking research using data and technologies to minimize the burden of cancer.
Serving Researchers
NCI DOCs and the intramural and extramural research communities are important partners in defining the data science and informatics needs of their research programs, helping to shape CBIIT’s framework of data science and IT coordination and support.
Data Accessibility and Interoperability
The ability to manage and analyze large, multidimensional data sets is facilitating unprecedented insights into the molecular alterations that lead to cancer and sustain its progression. Such insights are providing new opportunities to develop treatments that target the specific molecular changes that characterize a patient’s disease. CBIIT is establishing the infrastructure and processes required to access such data sets for secondary use, through efforts such as the NCI Cancer Research Data Commons (CRDC).
A critical component for interoperability within the CRDC and between the CRDC and other data commons is a flexible semantics infrastructure and support services. The semantic infrastructure provides standard terminologies, common data elements, clinical case report forms, and data models.
Data Sharing
Beyond infrastructure and technical processes to ensure data accessibility, the appropriate policies and data access policies are crucial to support efficient and productive data sharing. NCI’s Office of Data Sharing (ODS) maintains a comprehensive data sharing vision and strategy for NCI and the cancer research community. This ensures NCI’s research and data adhere to all NCI and NIH data sharing policies. In addition, ODS advocates for broad and responsible data sharing for the research and participant (i.e., patient and advocate) communities.
Support for Next Generation Clinical Trials
In collaboration with the Division of Cancer Treatment and Diagnosis, CBIIT supports the evolving cancer clinical trial enterprise by providing clinical informatics support. Informatics for NCI’s next generation clinical trials includes the development of treatment arm assignments and actionable mutation to support precision medicine trials and development of infrastructure to support immune-oncology trials. CBIIT also provides support for open-source applications intended to ease clinical trial reporting burdens through the consolidation of mechanisms for reporting and harmonizing implementable data standards for next-generation study designs.
In addition to supporting the underlying informatics infrastructure for clinical trials, CBIIT is working with the NCI Coordinating Center for Clinical Trials to facilitate cancer clinical trial enrollment. Efforts include developing methods to make it easier for participants and their care givers to find the clinical trials for which they are eligible and to increase the relevancy of clinical trial searches.
Advancing Technology Development
In addition to developing the infrastructure, processes, and policies to ensure the accessibility of data, leading-edge technologies, tools, and computational infrastructure are important components of maximizing the insights that can be drawn from data. In this vein, CBIIT coordinates trans-NCI activities that are advancing technology development supporting data science and informatics. CBIIT also serves as the central coordination point for NCI collaborations with the Department of Energy (DOE) that aim to apply high-performance computing and artificial intelligence to address specific challenges in cancer research while informing the design of future DOE supercomputers.
Digital Workforce
CBIIT is committed to developing the digital workforce needed to support data-driven cancer research, both within NCI and in the extramural research community. This includes training NCI staff on administrative IT tools and applications, providing analytic support and training for NCI intramural researchers, and working with the Center for Cancer Training to develop data science training opportunities for the cancer research community.
NCI Enterprise IT Support
CBIIT manages the IT infrastructure for the NCI enterprise, which is critical to ensure NCI staff can conduct their work serving the cancer research community. This includes the hardware, software, network, labor, structures, and policies required to support the scientific and administrative activities of NCI. These services play a critical role in advancing the NCI mission.