String Database
88TrustedShips scriptsProtein-protein interaction data retrieval and functional enrichment analysis via CLI.
What it does
String Database integrates a command-line interface to access biological interaction information directly from the STRING repository. It enables the retrieval of protein network data, homology information, and functional pathway annotations by utilizing specific NCBI Taxon IDs.
When it earns its place
Reach for it when…
Use this to programmatically verify physical or functional associations between proteins, perform pathway enrichment studies, or retrieve confidence scores for interaction networks across defined species.
Look elsewhere when…
Do not attempt to use this for general biological research questions that do not require protein interaction data, or for tasks involving large-scale genome sequencing alignments, as it does not perform sequence analysis or experimental data generation.
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.
- Find all proteins that interact with TP53 in mice
- Show me the pathway enrichment results for these human proteins
- List interaction partners for this gene with high confidence scores
- Retrieve functional annotation data for the provided list of proteins
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.
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/string_database ~/.claude/skills/string-databaseInstall 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.
cp -r /tmp/science-skills/skills/string_database .claude/skills/string-databaseIf 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
String Database changes how the work is done. These servers change what Claude can reach while doing it.