The National Cancer Institute (NCI) will be hosting the NCI Cancer Research Data Commons (CRDC) Artificial Intelligence Data-Readiness (AIDR) Challenge from March 4 through March 22, 2024, on the Seven Bridges Cancer Genomics Cloud (SB-CGC) powered by Velsera.  

This AI Data-Readiness (AIDR) Challenge seeks to engage the research community in assessing the AI readiness of CRDC data to inform NCI on how future data can be generated to be compatible with downstream AI algorithms, including the level of standardization and curation necessary to make data AI-ready, and how to efficiently share CRDC-hosted data for use by the community. This is part of a year-long assessment process to ensure that CRDC data and resources meet the needs of AI-based research.  

In this Challenge participants will:

1. Select an AI/ML use case (from a provided list of AI/ML use cases) and identify applicable data from one or more of the components within the CRDC.  
2. Preprocess the CRDC data and present it in an AI-ready format (a format that enables the AI/ML applications without extensive additional processing).  
3. Develop AI/ML models for the previously selected use cases.
4. Provide feedback and recommendations on ways to improve the AI data readiness of CRDC data based on the results of this Challenge.  

Registration remains open through March 1, 2024.  Find the registration page here.

1. The Challenge is open to all U.S. citizens or permanent residents who are not federal employees of the Department of Health and Human Services (HHS). 
2. Participants may register as an individual, a team, or a U.S. entity (such as an academic institution or company). 
3. Several prizes will be awarded based on different types of CRDC data and resource utilization. More details to come when registration opens.