RepoAI
Browse MCPs

Human Protein Atlas Database

88TrustedShips scripts

Access protein abundance and spatial data from the Human Protein Atlas repository.

What it does

Human Protein Atlas Database integrates immunohistochemistry-derived protein data directly into your environment. It bridges the gap between theoretical gene transcription and physical protein existence, allowing you to identify where a specific protein resides within a cell and its concentration levels across various human tissues.

The skill handles the technical translation between common gene symbols and required Ensembl identifiers. It automates the retrieval of standardized expression metadata, ensuring that researchers can quickly pull validated observations about protein distribution in both healthy and malignant human tissues without manually navigating external web interfaces.

When it earns its place

Reach for it when…

Apply this when your biological research requires confirmation of protein-level presence rather than just RNA transcripts. It is essential for determining subcellular localization, comparing expression across distinct tissue types, or validating markers in oncology studies where protein abundance in tissue samples is the critical variable.

Look elsewhere when…

Do not attempt to use this for genetic variant analysis, such as eQTL or pQTL mapping, as the source data is strictly limited to wild-type expression levels. It also lacks data for non-human organisms and is not intended for high-throughput gene expression profiling where purely transcriptional (RNA-seq) data is sufficient.

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 is the subcellular location for the protein encoded by TP53?
  • Find the protein expression levels of ERBB2 in thyroid and duodenum tissue.
  • Get the Ensembl ID and HPA entry for the BRAF gene.
  • Search for secreted proteins based on HPA criteria.

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/human_protein_atlas_database ~/.claude/skills/human-protein-atlas-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/human_protein_atlas_database .claude/skills/human-protein-atlas-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

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

How skills and MCP servers differ →