Scigantic

Fetch one Scigantic dataset by id (from search): its description, storage location, source link, and schema card (format, columns, sample rows, caveats, and how to load it).

Get full metadata for one archive by id, including its schema card (structure summary) when one exists.

Get how to load a dataset in YOUR OWN environment: storage location plus copy-paste code snippets (from the dataset's schema card, or generated as a fallback). Use this after finding a dataset when you want to run analysis where you are, rather than in a hosted notebook.

Get the pre-executed starter notebook for an archive — a worked example of loading and exploring the data. Returns a cell-by-cell summary plus each cell's source (outputs are omitted to keep the payload small).

Get the compact schema card for an archive: file format, columns, sample rows/headers, sidecar docs (READMEs/data dictionaries) and a copy-paste starter cell. This is the fastest way to understand a dataset's structure without mounting it.

List a sample of the files/objects in an archive's storage (the cached file tree).

List the compute tiers available for launching a Scigantic notebook (CPU/GPU options and hourly cost).

Look up a research paper on arXiv, by bare arXiv id (e.g. "1706.03762") or by keywords/title, and return its metadata plus any Scigantic archives linked to or suggested by it. Useful for going from a paper an agent is reading to the underlying datasets. Lookup is arXiv-backed: DOIs, "arXiv:"-prefixed ids, and papers that are not on arXiv do not resolve.

Search the Scigantic catalog of public scientific datasets. Returns matching datasets as {results: [{id, title, url}]}; pass an id to fetch for the full description and schema card.

Search the Scigantic catalog of public scientific data archives by natural-language query. Matching considers both the archive's description AND a sample of its actual object/file names, so a distinctive filename or path pattern can surface a match even when the prose description never mentions it. Returns ranked matches with id, title, category, a short summary, and two payload-derived trust signals: probeStatus ("empty" means the archive's storage was probed and found to have no accessible objects despite being tagged public — likely credentialed, don't spend a turn on it) and objectCountEstimate (a real count/estimate from that probe, not the description's prose). Follow up with get_schema_card to understand a match's structure before doing any analysis.

Look up a compound in SureChEMBL, EMBL-EBI's database of chemistry extracted from patents, by any identifier, and report its structure, properties, cross-references (ChEMBL, PubChem, DrugBank, ChEBI, PDB) and how many patents mention it.

A patent document from SureChEMBL: title, dates, applicants, inventors, assignees, family, priority claims, number of compounds named in the text, abstract, and (optionally) the claims and description text. SureChEMBL no longer returns CPC codes, citations or legal events with a document.

The compounds SureChEMBL's text-mining finds named in a patent's text: SCHEMBL id, name, SMILES, InChIKey, formula, weight. Structures that appear only in images or MOL attachments are not included.

List the patents in which a compound was found (SureChEMBL). Accepts the same identifier forms as surechembl_compound. Aspirin is in ~700,000 documents, so read the total and narrow with surechembl_search_patents when it is large.

Full-text patent search over SureChEMBL with Solr syntax. Plain terms search all text; field prefixes narrow: ttl (title), ab (abstract), clm (claims), desc, asg (assignee), inv (inventor), pdyear, cpc, ic (IPCR), fam (family id). Quote publication numbers: pn:"US-10000000-B2". Combine with AND/OR/NOT. Only US, EP, WO, JP and CN publications are searchable.

Search SureChEMBL's 31 million patent compounds by chemical structure.