The AI did the metadata cleanup behind a catalog of 500,000 gut samples
His Microbiome Repo catalogs every public human gut metagenome, more than 500,000 samples, with metadata pulled straight from sequence archives, papers and supplements. It was built with about $5,000 in an AI app API credits from the Anthropic AI for Science program, with AI taking on the metadata curation he calls the most tedious but critical part of microbiome research.
How it works
- AI pulls metadata from sequence archives, papers and supplements
- Curates it for more than 500,000 samples
- The catalog is published as a searchable site where researchers can check their own studies
Why it’s worth knowing
The dull part of the research, cleaning metadata for half a million samples, is the part the AI carried, and the result is a public catalog anyone can search.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗