Forge Tools msigdb_genesets

msigdb_genesets read

scidex.forge.msigdb_genesets

Look up MSigDB molecular signature gene sets that overlap with a list of gene symbols via the Enrichr public API. Supports Hallmark (H), Curated canonical pathways (C2), Gene Ontology (C5), and Oncogenic signatures (C6) collections. Returns gene sets ranked by overlap fraction — fraction of set genes matched by the input. Essential for GSEA context in transcriptomics and hypothesis-grounding workflows.

HTTP: POST /api/scidex/forge/msigdb_genesets

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.msigdb_genesets``.",
  "properties": {
    "gene_symbols": {
      "description": "HGNC gene symbols to query (e.g. ``['BRCA1', 'TP53']``). Must contain at least one gene symbol.",
      "items": {
        "type": "string"
      },
      "title": "Gene Symbols",
      "type": "array"
    },
    "collection": {
      "default": "H",
      "description": "MSigDB collection to search. ``'H'`` = Hallmark gene sets, ``'C2'`` = Curated canonical pathways, ``'C5'`` = Gene Ontology gene sets, ``'C6'`` = Oncogenic signatures. Default: ``'H'``.",
      "title": "Collection",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "Maximum number of gene sets to return, ranked by overlap_fraction descending. Default 10.",
      "maximum": 100,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    }
  },
  "required": [
    "gene_symbols"
  ],
  "title": "ForgeMSigDBIn",
  "type": "object"
}
Output schema 
{
  "$defs": {
    "MSigDBGeneSet": {
      "description": "One MSigDB gene set in the enrichment response.",
      "properties": {
        "gene_set_id": {
          "description": "MSigDB gene set identifier (e.g. ``HALLMARK_APOPTOSIS``).",
          "title": "Gene Set Id",
          "type": "string"
        },
        "gene_set_name": {
          "description": "Human-readable gene set name.",
          "title": "Gene Set Name",
          "type": "string"
        },
        "collection": {
          "description": "MSigDB collection code (H, C2, C5, or C6).",
          "title": "Collection",
          "type": "string"
        },
        "matched_genes": {
          "description": "Input genes that overlap with this gene set.",
          "items": {
            "type": "string"
          },
          "title": "Matched Genes",
          "type": "array"
        },
        "gene_set_size": {
          "default": 0,
          "description": "Total number of genes in this MSigDB gene set.",
          "title": "Gene Set Size",
          "type": "integer"
        },
        "overlap_fraction": {
          "default": 0,
          "description": "Fraction of gene set genes matched: len(matched_genes) / gene_set_size.",
          "title": "Overlap Fraction",
          "type": "number"
        },
        "description": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Gene set description from MSigDB (when available).",
          "title": "Description"
        }
      },
      "required": [
        "gene_set_id",
        "gene_set_name",
        "collection"
      ],
      "title": "MSigDBGeneSet",
      "type": "object"
    }
  },
  "description": "Response shape for ``scidex.forge.msigdb_genesets``.",
  "properties": {
    "gene_sets": {
      "items": {
        "$ref": "#/$defs/MSigDBGeneSet"
      },
      "title": "Gene Sets",
      "type": "array"
    },
    "genes_queried": {
      "default": 0,
      "description": "Number of gene symbols submitted to the query.",
      "title": "Genes Queried",
      "type": "integer"
    },
    "collection": {
      "default": "",
      "description": "MSigDB collection used for the lookup.",
      "title": "Collection",
      "type": "string"
    }
  },
  "title": "ForgeMSigDBOut",
  "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/msigdb_genesets' \
  -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.