RepoAI
Browse MCPs

GTEx Database

88TrustedShips scripts

Access median RNA expression levels and eQTL variant data from 54 human tissue sites.

What it does

Gtex Database adds the capability to pull standardized transcriptomics data directly into your workspace. It handles the translation between common gene symbols and specific versioned identifiers, ensuring that your queries for baseline RNA abundance or genetic associations remain accurate and reproducible.

By integrating this resource, your assistant gains the ability to query non-diseased tissue profiles for gene expression in Transcripts Per Million (TPM). It also performs automated lookups for expression Quantitative Trait Loci (eQTLs), bridging the gap between genetic variants and potential regulatory effects in healthy human adults.

When it earns its place

Reach for it when…

Use this to establish a baseline for gene expression in healthy tissues when analyzing potential regulatory variants, investigating GWAS findings, or contextualizing genetic research within adult human biology.

Look elsewhere when…

Avoid this for any research involving diseased tissues, such as oncology samples or pathology reports, as the data strictly covers normal, non-pathological tissue. It is also unsuitable for developmental or prenatal studies, as the source material is limited to adult donors, and it cannot provide information on protein-level abundance.

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.

  • what are the top tissues for expression of the TNF gene
  • find the median TPM for ENSG00000232810 across all tissues
  • get eQTL associations for this gene
  • map the symbol JUN to its current GENCODE ID

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/gtex_database ~/.claude/skills/gtex-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/gtex_database .claude/skills/gtex-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

GTEx Database changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →