Forge Tools mygene_info

mygene_info read

scidex.forge.mygene_info

Look up aggregated gene metadata from MyGene.info for a list of gene symbols. MyGene.info reconciles annotations from Entrez, Ensembl, UniProt, UCSC, RefSeq, GO, KEGG, WikiPathways, Reactome, ClinVar, PharmGKB, OMIM, and 20+ other sources into a single cross-database record per gene. Batch POST endpoint — free, no auth required.

HTTP: POST /api/scidex/forge/mygene_info

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.mygene_info``.",
  "properties": {
    "gene_symbols": {
      "description": "HGNC gene symbols to look up (e.g. ``['BRCA1', 'EGFR']``). Queried via MyGene.info batch POST endpoint. 1–50 symbols per call.",
      "items": {
        "type": "string"
      },
      "title": "Gene Symbols",
      "type": "array"
    },
    "species": {
      "default": "human",
      "description": "Species filter for MyGene.info. Default 'human'. Also accepts 'mouse', 'rat', or NCBI taxonomy IDs.",
      "maxLength": 64,
      "title": "Species",
      "type": "string"
    },
    "fields": {
      "default": "symbol,name,taxid,ensembl.gene,uniprot.Swiss-Prot,entrezgene,go.BP,pathway.kegg,refseq.rna,genomic_pos",
      "description": "Comma-separated MyGene.info fields to return. Default: 'symbol,name,taxid,ensembl.gene,uniprot.Swiss-Prot,entrezgene,go.BP,pathway.kegg,refseq.rna,genomic_pos'.",
      "maxLength": 512,
      "title": "Fields",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "Maximum results per gene symbol. Default 10.",
      "maximum": 1000,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    }
  },
  "required": [
    "gene_symbols"
  ],
  "title": "ForgeMyGeneIn",
  "type": "object"
}
Output schema
{
  "$defs": {
    "MyGeneResult": {
      "description": "One MyGene.info gene record.",
      "properties": {
        "query_symbol": {
          "description": "The gene symbol that was queried.",
          "title": "Query Symbol",
          "type": "string"
        },
        "mygene_id": {
          "default": "",
          "description": "MyGene.info internal gene ID (maps to '_id').",
          "title": "Mygene Id",
          "type": "string"
        },
        "entrezgene": {
          "default": "",
          "description": "NCBI Entrez Gene ID.",
          "title": "Entrezgene",
          "type": "string"
        },
        "ensembl_gene_id": {
          "default": "",
          "description": "Ensembl stable gene ID (e.g. 'ENSG00000139618').",
          "title": "Ensembl Gene Id",
          "type": "string"
        },
        "symbol": {
          "default": "",
          "description": "Official gene symbol.",
          "title": "Symbol",
          "type": "string"
        },
        "name": {
          "default": "",
          "description": "Official gene full name.",
          "title": "Name",
          "type": "string"
        },
        "taxid": {
          "default": 0,
          "description": "NCBI taxonomy ID (9606 for human).",
          "title": "Taxid",
          "type": "integer"
        },
        "uniprot_swiss_prot": {
          "description": "UniProt Swiss-Prot accession(s).",
          "items": {
            "type": "string"
          },
          "title": "Uniprot Swiss Prot",
          "type": "array"
        },
        "go_bp_terms": {
          "description": "GO Biological Process term names.",
          "items": {
            "type": "string"
          },
          "title": "Go Bp Terms",
          "type": "array"
        },
        "kegg_pathway_ids": {
          "description": "KEGG pathway IDs (e.g. 'hsa:05200').",
          "items": {
            "type": "string"
          },
          "title": "Kegg Pathway Ids",
          "type": "array"
        },
        "refseq_rna": {
          "description": "RefSeq RNA accession(s) (NM_/NR_).",
          "items": {
            "type": "string"
          },
          "title": "Refseq Rna",
          "type": "array"
        },
        "genomic_pos": {
          "anyOf": [
            {
              "additionalProperties": true,
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Genomic coordinates: {chr, start, end, strand}.",
          "title": "Genomic Pos"
        }
      },
      "required": [
        "query_symbol"
      ],
      "title": "MyGeneResult",
      "type": "object"
    }
  },
  "description": "Response shape for ``scidex.forge.mygene_info``.",
  "properties": {
    "gene_symbols": {
      "description": "The gene symbols that were queried.",
      "items": {
        "type": "string"
      },
      "title": "Gene Symbols",
      "type": "array"
    },
    "genes": {
      "description": "MyGene.info gene records, one per queried symbol.",
      "items": {
        "$ref": "#/$defs/MyGeneResult"
      },
      "title": "Genes",
      "type": "array"
    },
    "total_found": {
      "default": 0,
      "description": "Number of genes with cross-ref data populated (not notfound).",
      "title": "Total Found",
      "type": "integer"
    },
    "took_ms": {
      "description": "Wall-clock time for the upstream call.",
      "title": "Took Ms",
      "type": "integer"
    }
  },
  "required": [
    "gene_symbols",
    "took_ms"
  ],
  "title": "ForgeMyGeneOut",
  "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/mygene_info' \
  -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.