License the engine that builds the graph.
Point MapForge at a domain. It ingests the sources, links the entities, scores its own confidence on every connection, and serves the result through a production API — in days. You license the engine, not a static dataset someone else froze.
Any format. Any biological domain.
Biological data rarely arrives as a clean spreadsheet. MapForge ingests structured data regardless of format. CSV, TSV, JSON, Parquet, and SQL dumps are the common cases — not a fixed list.
Every link is scored, then reviewed.
Every entity link MapForge proposes is scored for confidence and queued for human review before it enters the graph. Illustrative example below — not live production data.
— produces →
Butyrate
Not a script. An endpoint your systems can call.
Federation runs at the graph layer, so one query can span multiple constituent graphs with unified provenance. Microbiome is what's loaded today; more domains come online as they're built.
MicroMap is what MapForge built first.
A microbiome knowledge graph with 1.7M+ entities, built from raw sources — not a static export. See the numbers.
See the proof →Runs where your data already lives.
Ready to build your own graph?