Reactome Database

88TrustedShips scripts

Pathway analysis, gene identifier mapping, and biological knowledge retrieval.

What it does

Reactome Database provides your assistant with direct access to comprehensive biological pathway data and statistical enrichment capabilities. By integrating this, the assistant gains the ability to process gene or protein lists to identify statistically relevant biological pathways, map complex identifiers, and retrieve structural details about biochemical reactions.

Beyond basic lookup, the skill allows for the navigation of hierarchical pathway structures and the extraction of visual diagrams. It serves as an specialized interface for researchers needing to ground their findings in standardized biological knowledge, ensuring that analysis reports and data cross-referencing remain accurate and consistent with the underlying database.

When it earns its place

Reach for it when…

Install this when you need to perform overrepresentation analysis on gene sets, map varied identifier formats like UniProt or Ensembl to human or model organism pathways, retrieve reaction participants, or export annotated pathway diagrams for reports.

Look elsewhere when…

Do not use this for general literature review or searching broad biomedical concepts that are not defined within the Reactome pathway hierarchy. It is not designed for primary sequence analysis, protein folding prediction, or searching non-pathway-related databases.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • run a pathway enrichment analysis on this list of genes
  • find which pathways contain these specific protein identifiers
  • export a diagram for the mitotic cell cycle pathway
  • map these gene symbols to their stable Reactome identifiers

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/reactome_database ~/.claude/skills/reactome-database

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/reactome_database .claude/skills/reactome-database

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server