Skip to content
FAIRSCAPE

FAIRSCAPE

FAIRSCAPE is a computational framework in Python that implements the Bridge2AI AI-readiness principles on biomedical datasets and provides ethical FAIRness1 with deep semantic provenance graphs across datasets, software, computations, runtime parameters, environment, and personnel involved in a computational analysis. FAIRSCAPE generates detailed human- and machine-readable biomedical Datasheets including Croissant and Croissant RAI metadata for direct interface to Kaggle and other AI/ML Ops packages, and provides a rich data commons environment for biomedical AI researchers.

FAIRSCAPE provides a command line client tool and a graphical user interface (GUI) to package and validate the components with metadata, a schema generation and validation component for the datasets, a REST API to perform various operations on the server-side, and a front-end web server to visualize the posted metadata.

Get Started Deploy locally and create your first RO-Crate.
Installation Docker Compose services, ports, and default credentials.

Key Components

FAIRSCAPE Server Python/FastAPI metadata management — package storage, metadata extraction, provenance tracking, REST API.
Command Line Client (CLI) A pip-installable utility for creating and managing RO-Crates with schema.org-vocabulary metadata.
Graphical User Interface (GUI) An Electron + React interface with visual forms, guided workflow, validation, and direct upload.
Web Client React-based interface for browsing RO-Crates, viewing metadata, and rendering provenance graphs.

Use Cases

FAIRSCAPE was initially created to support fully-provenanced complex computations in predictive analytics for clinical research2. The current version supports the NIH Bridge2AI program’s Functional Genomics Grand Challenge3, as well as ongoing clinical work in predictive analytics. We believe it is a useful tool for developing pre-model explainability in AI applications4, and plan to extend it further in this direction. It creates and provides rich, human-readable Datasheets in HTML, extending the basic conceptions of Gebru et al. 20215 to cover additional metadata required for biomedical AI-readiness.

Funding

FAIRSCAPE was developed with funding from the U.S. National Institutes of Health awards OT2OD032742, OT2OD032701, 5R01HD072071-10; and from the University of Virginia’s Frederick Thomas Fund.

Footnotes

  1. Wilkinson, M. D., Dumontier, M., Aalbersberg, I. J., et al. (2016). The FAIR Guiding Principles for scientific data management and stewardship. Scientific data, 3, 160018. doi:10.1038/sdata.2016.18. ↩

  2. Niestroy JC, Moorman JR, Levinson MA, et al. Discovery of signatures of fatal neonatal illness in vital signs using highly comparative time-series analysis. npj Digit Med. 2022;5(1):6. doi:10.1038/s41746-021-00551-z. ↩

  3. Clark T, Schaffer LV, Obernier K, et al. Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines. doi:10.1101/2024.05.21.589311. Published online May 6, 2024. ↩

  4. Clark T, Caufield H, Parker JA, et al. AI-readiness for Biomedical Data: Bridge2AI Recommendations. Published online October 25, 2024. doi:10.1101/2024.10.23.619844. ↩

  5. Al Manir S, Levinson MA, Niestroy J, Churas C, Parker JA, Clark T. FAIRSCAPE: An Evolving AI-readiness Framework for Biomedical Research. doi:10.1101/2024.12.23.629818. Published online May 6, 2025. ↩