FreeHow credits work →
ST
InteractionsSTRING API interaction_partners

STRING

STRING is a database of known and predicted protein-protein interactions that gives each pair a confidence score built from several kinds of evidence. Through ScholarMuse, an agent calls lookup_gene_protein with a gene symbol or UniProt accession and gets the 15 highest-scoring STRING partners of that protein, each with its combined score and the experimental, database and text-mining scores.

ScholarMuse tools: lookup_gene_protein. Each successful call uses credits.

Use in my agent

Ask your agent

Which proteins interact most strongly with human TP53 according to STRING?
Does STRING list MDM2 among the top partners of CDKN2A, and what is the experimental score?
Give me the top STRING interaction partners of mouse Stat3.

What your agent gets back

Every record carries id, source, title, url, license, attribution and retrievedAt. The fields below are the data that comes from STRING.

lookup_gene_protein

STRING fills the `interactions` list of the merged record. It is fetched when `include` contains interactions (the default) and a gene symbol or UniProt accession was resolved.

interactions[].partner
Preferred name of the partner protein
interactions[].score
STRING combined score
interactions[].experimentalScore
Score from experimental evidence
interactions[].databaseScore
Score from curated database evidence
interactions[].textminingScore
Score from text-mining evidence
links.string
URL of the protein's network page at STRING

What it covers

  • The highest-scoring interaction partners of one protein in one organism (human by default).
  • For each partner: the combined score and the experimental, database and text-mining scores.
  • A link to the queried protein's network page at STRING for the full picture.

Limits

  • 15 partners per call. The number cannot be changed, and there is no paging.
  • The tool sets no score cut-off of its own. It takes STRING's top 15 as returned, so low-confidence partners can appear for a protein with few interactions.
  • One protein per call. No network between several proteins, no enrichment analysis and no network image.
  • Co-expression, neighbourhood, fusion and co-occurrence scores are not included in the output.

How ScholarMuse reaches STRING

The connector calls the STRING API at string-db.org directly, using the interaction_partners method with the gene symbol (or the UniProt accession when there is no symbol) and the NCBI taxon id. No API key is sent. Requests to STRING are spaced one second apart.

Responses are cached for up to 7 days, so a new STRING version can take that long to appear.

API key: the upstream API can be called without one, so you do not add one.

Licence and attribution

Licence: CC BY 4.0

Protein–protein interaction data from STRING (string-db.org), CC BY 4.0.

Records that come from STRING carry this licence and attribution. When you cite the data in a paper, follow STRING's own citation guidance.

Capabilities that use STRING

Gene & protein lookupNew

Gene & protein lookup

Life sciences & medicine · NCBI Gene, Ensembl, UniProt +5

Related sources

NCBI GeneEnsemblUniProtInterProReactomeGTExNCBI GEO

FAQ

ScholarMuse is not an official STRING product. It is one MCP server for academic data, and its lookup_gene_protein tool queries STRING. An agent connected to ScholarMuse can use STRING without a separate server.

No. The STRING API can be called without a key, and ScholarMuse does not ask you for one. You sign in to ScholarMuse once and your agent calls the tool.

The connector calls the STRING API at string-db.org directly, using the interaction_partners method with the gene symbol (or the UniProt accession when there is no symbol) and the NCBI taxon id. No API key is sent. Requests to STRING are spaced one second apart. Responses are cached for up to 7 days, so a new STRING version can take that long to appear.

CC BY 4.0. Attribution: Protein–protein interaction data from STRING (string-db.org), CC BY 4.0. Records that come from STRING carry this licence and attribution.

Yes. Each successful call to lookup_gene_protein uses credits, and a call that fails is not charged. Current price: Gene & protein lookup, 1 credit / call.