About Sugi Atlas

Sugi Atlas is a biomedical reference atlas: one canonical, structured page for every gene, drug, and disease (more than 52,000 in all), assembled from around seventy primary databases through BioBTree and published as static, citable HTML.

Every page is built deterministically. A fixed plan of graph queries traverses BioBTree, and the records it returns are rendered into tables and prose by template, with every record traceable to its source. The same inputs produce the same page on every build, so the catalog is reproducible and inexpensive to refresh as its sources release updates. Where a section has no data, the page says so rather than guessing.

Genes, drugs, and diseases are linked to one another by a curated cross-entity mesh: a relationship recorded once (a drug’s target, a disease’s gene) is navigable from every page it touches. Each page also carries machine-readable structured data, so both researchers and the AI agents that increasingly consume reference data can use it as a grounded, current source.

Sugi Atlas is open source and the full methodology is in the preprint. The underlying databases are listed on the Sources page. Sugi Atlas data pipeline lives at github.com/tamerh/sugi-atlas and BioBTree, at github.com/tamerh/biobtree. It is part of the broader sugi.bio project. Found an issue? Open one on the pipeline repo or contact.