Abstract 7432: Improving FAIRness of computational approaches for cancer: The computational resources for cancer research portal

Abstract The Computational Resources for Cancer Research website is a public portal supported by NCI that democratizes access to available computational resources for the cancer research community. In supporting an emerging FAIR (Findable, Accessible, Interoperable, Reusable) data science ecosystem inclusive of software, models and data, the goals of the portal are to serve cancer data scientists by increasing understanding, access, and adoption of computational resources for cancer research, and to foster new collaborative research projects. Initially populated with resources developed in NCI supported collaborations with the US Department of Energy, the portal is serving as a unified reference and resource for computational resources developed broadly by the cancer community. These collaborative projects include CANDLE (the Cancer Distributed Learning Environment), IMPROVE (Innovative Methods and data for PRedictive Oncology model Validation and Evaluation), ADMIRRAL (AI Driven Multi-scale Investigation of Ras-Raf Activation Lifecycle), MOSSAIC (Model Outcomes using Surveillance Data and Scalable AI for Cancer) and ATOM (Accelerating Therapeutics for Opportunities in Medicine). The resources include software, models, and datasets as well as descriptive use cases and references to tutorials associated with many of the described resources. The portal also integrates content from the Predictive Oncology Model and Data Clearinghouse (modac. cancer. gov) which can be accessed through REST APIs. Ongoing development of the portal is driven by community insights and contributions including input from an interdisciplinary advisory committee, working groups, early users, and preliminary feedback received at AACR 2023. The portal will also support community contributions of computational resources. In addition, the portal highlights computational approaches in emerging and challenging areas, such as digital twins for cancer. The portal will enable the cancer research community to learn about new computational research methods through use cases and educational material, access cancer related software, datasets, and AI models, engage with peers and cross-disciplinary researchers at different career levels through an interactive forum, explore emerging areas, such as computational imaging, community-based standards for data management, predictive radiation oncology, and digital twin technologies, learn about in industry and community events, conferences, and workshops, and create new collaborative research projects. The presentation will deliver insights into key resources offered through the Computational Resources for Cancer Research Portal, how the portal will help the cancer research community identify and adopt computational resources of interest, and how researchers can join and participate in this growing community. Citation Format: Eric Stahlberg, Lynn Borkon, Ruth Frost, Sara Jones, Amar Khalsa, Lauren Lewis, Emily Greenspan, Sunita Menon. Improving FAIRness of computational approaches for cancer: The computational resources for cancer research portal abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts) ; 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84 (6Suppl): Abstract nr 7432.