Forge Tools ncbi_gene

ncbi_gene read

scidex.forge.ncbi_gene

Look up gene summaries and cross-database references from NCBI Gene. Returns gene_id, official symbol, full name, chromosomal location, gene type, organism, summary (≤1000 chars), aliases, RefSeq mRNA accession, OMIM IDs, and Ensembl ID. NCBI Gene is the canonical gene identifier database used across PubMed, ClinVar, dbSNP, and GTEx. Complements forge_ensembl_xref with richer official summaries. Set NCBI_API_KEY for 10 rps (default 3 rps anonymous).

HTTP: POST /api/scidex/forge/ncbi_gene

Invoke

Calls scidex.tool.invoke on the substrate with this tool name. Edit the JSON below — it must match the input schema. The substrate runs the tool, records the call in substrate_tool_calls, and returns a structured envelope.

Sign in to invoke this tool. Schema and curl snippet are visible to anyone.

Schemas

Input schema 
{
  "additionalProperties": false,
  "description": "Input schema for ``scidex.forge.ncbi_gene``.",
  "properties": {
    "gene_symbols": {
      "description": "HGNC gene symbols to look up (e.g. ``['TP53', 'BRCA1']``). Each symbol is queried via NCBI Gene esearch.",
      "items": {
        "type": "string"
      },
      "title": "Gene Symbols",
      "type": "array"
    },
    "species": {
      "default": "Homo sapiens",
      "description": "Species filter passed to NCBI as ``[orgn]`` qualifier. Default ``'Homo sapiens'``. Use ``'Mus musculus'`` for mouse, etc.",
      "maxLength": 128,
      "title": "Species",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "Maximum total gene records to return across all queried symbols.",
      "maximum": 100,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    }
  },
  "required": [
    "gene_symbols"
  ],
  "title": "ForgeNCBIGeneIn",
  "type": "object"
}
Output schema 
{
  "$defs": {
    "NCBIGene": {
      "description": "One NCBI Gene record.",
      "properties": {
        "gene_id": {
          "description": "NCBI Gene numeric ID.",
          "title": "Gene Id",
          "type": "integer"
        },
        "symbol": {
          "default": "",
          "description": "Official HGNC gene symbol.",
          "title": "Symbol",
          "type": "string"
        },
        "name": {
          "default": "",
          "description": "Official gene name (same as full_name).",
          "title": "Name",
          "type": "string"
        },
        "full_name": {
          "default": "",
          "description": "Official full gene name from Gene-ref_desc.",
          "title": "Full Name",
          "type": "string"
        },
        "chromosome": {
          "default": "",
          "description": "Chromosome (e.g. ``'17'``, ``'X'``, ``'MT'``), extracted from location.",
          "title": "Chromosome",
          "type": "string"
        },
        "location": {
          "default": "",
          "description": "Cytogenetic map location (e.g. ``'17p13.1'``).",
          "title": "Location",
          "type": "string"
        },
        "gene_type": {
          "default": "",
          "description": "Gene biotype (e.g. ``'protein-coding'``, ``'ncRNA'``).",
          "title": "Gene Type",
          "type": "string"
        },
        "organism": {
          "default": "",
          "description": "Organism name from Org-ref_taxname.",
          "title": "Organism",
          "type": "string"
        },
        "summary": {
          "default": "",
          "description": "Official gene summary (up to 1000 chars).",
          "title": "Summary",
          "type": "string"
        },
        "aliases": {
          "description": "Gene synonyms from Gene-ref_syn.",
          "items": {
            "type": "string"
          },
          "title": "Aliases",
          "type": "array"
        },
        "refseq_id": {
          "default": "",
          "description": "First RefSeq mRNA accession (NM_/NR_) from the locus products.",
          "title": "Refseq Id",
          "type": "string"
        },
        "omim_ids": {
          "description": "OMIM MIM IDs cross-referenced to this gene.",
          "items": {
            "type": "string"
          },
          "title": "Omim Ids",
          "type": "array"
        },
        "ensembl_id": {
          "default": "",
          "description": "Ensembl gene ID (e.g. ``'ENSG00000141510'``).",
          "title": "Ensembl Id",
          "type": "string"
        }
      },
      "required": [
        "gene_id"
      ],
      "title": "NCBIGene",
      "type": "object"
    }
  },
  "description": "Response shape for ``scidex.forge.ncbi_gene``.",
  "properties": {
    "genes": {
      "description": "NCBI Gene records, one per gene found.",
      "items": {
        "$ref": "#/$defs/NCBIGene"
      },
      "title": "Genes",
      "type": "array"
    },
    "total_found": {
      "default": 0,
      "description": "Total gene IDs returned by esearch before the limit was applied.",
      "title": "Total Found",
      "type": "integer"
    },
    "took_ms": {
      "description": "Wall-clock time for the upstream calls.",
      "title": "Took Ms",
      "type": "integer"
    }
  },
  "required": [
    "took_ms"
  ],
  "title": "ForgeNCBIGeneOut",
  "type": "object"
}

curl snippet

Replace $SCIDEX_JWT with a valid bearer token. Read verbs are usually accessible without auth in dev; production requires a JWT.

curl -sS -X POST '/api/scidex/forge/ncbi_gene' \
  -H 'authorization: Bearer $SCIDEX_JWT' \
  -H 'content-type: application/json' \
  -d '{
  "gene_symbols": []
}'

Discussion

Posting anonymously. Sign in for attribution.

No comments yet — be the first.