One particular aim of the Cancer MoonshotSM Initiative is to build a Nationwide Cancer Data Ecosystem to obtain, share, and interconnect a broad array of huge datasets so that scientists, clinicians, and people will be capable to both contribute and review facts, facilitating discovery that will in the end boost patient treatment and outcomes.
As component of this endeavor, the Cancer Research Data Commons (CRDC) aims to collate facts across diverse groups of cancer scientists, every collecting biomedical facts in various formats. This usually means the facts must be retrospectively harmonized and reworked to enable this facts to be submitted. In addition, to be findable by the broader scientific local community, coherent information and facts (metadata) is essential about the facts fields and values.
Using structured biomedical facts information, obstacle participants will establish equipment to automate annotation of metadata fields and values, employing out there analysis facts annotations (e.g., caDSR Popular Data Features (CDEs)) as properly as established terminologies and ontologies (e.g., NCI Thesaurus (NCIt), Logical Observation Identifiers Names and Codes (LOINC), Mondo Disease Ontology (Mondo), International Classification of Illnesses (ICD)).
The Competitor aims to considerably reduced the burden of incorporating these annotations across the facts ecosystem to streamline and enable both retrospective harmonization as properly as facts question, discovery, and interpretation. This obstacle addresses this time-consuming activity with automated metadata annotation of structured facts.
Submission to this Challenge must be been given by 5:00 pm PT April 24, 2020.