How to Use Human Protein Atlas protein search in opencode
Finds genes by protein location and tissue or cell type RNA enrichment in the Human Protein Atlas. Use it to build a research shortlist before examining individual genes in detail.
Prompts to try with Human Protein Atlas protein search in opencode
Copy an example into opencode, or ask in your own words.
Use Human Protein Atlas protein search to find liver-enriched genes and create a CSV of the returned candidates for my analysis.
Use Human Protein Atlas protein search to find mitochondrial oxidoreductases and build a candidate table in my notebook.
Use Human Protein Atlas protein search to look this up and give me the result as a table. Save the result in ./assets.
Pull the latest numbers from Human Protein Atlas protein search and tell me what changed since last week.
Check Human Protein Atlas protein search and summarize what you find in three bullet points.
How to set up Human Protein Atlas protein search in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Human Protein Atlas protein search
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "alexandria", "model": "proteinatlas-org/proteins/search", "input": { "limit": 20 } }'
Then paste one of the prompts above: opencode finds Human Protein Atlas protein search on Spiral, shows the price and runs it.
Human Protein Atlas protein search providers and prices
Spiral runs Human Protein Atlas protein search through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Limit | 1 to 100 | 20 | limit |
| Offset | 0 to 25000 | 0 | Results to skip; pass the previous page's next_offset. |
| Location | Acrosome, Actin filaments, Aggresome, Annulus, Basal body, Calyx, Cell Junctions, Centriolar satellite and 41 more | Subcellular location term exactly as HPA names it. | |
| Min reliability | Enhanced, Supported, Approved, or Uncertain | Lowest reliability of location to include; default Uncertain (all). Supported keeps Enhanced and Supported. | |
| Main location only | on or off | Only genes with location as a main location. |
Every API field of Human Protein Atlas · Search is on its tool page: open its card above.
What can you do with Human Protein Atlas protein search in opencode?
Build an HPA annotation table for a research gene list, with tissue RNA specificity beside protein location. Keep localization reliability scores attached to the location claims in downstream analysis.
Choose liver expression candidates
Find genes with liver-enriched RNA expression, then inspect their tissue and cell type annotations. Build a shortlist that distinguishes tissue enrichment from protein localization.
Review mitochondrial enzyme candidates
Search for enzymes annotated to mitochondria, then review each candidate's reported locations and reliability scores before selecting genes for a research panel.
Plan a nucleolar imaging panel
Find proteins assigned to nucleoli and examine the location evidence for individual candidates. Use the annotations to choose which proteins warrant closer experimental review.
Annotate a research gene list
Find the genes in a research shortlist and assemble their tissue RNA classifications, cell type expression annotations, and protein locations into a comparison table.
Review T-cell expression candidates
Identify genes with elevated RNA expression in T-cells, then inspect their broader expression and localization annotations. Compare candidates before choosing markers for further study.
Maintain an Atlas-based research shortlist
Repeat a saved biological search and review individual genes when the shortlist changes. Compare available RNA classifications and localization reliability scores with earlier results.
More on Human Protein Atlas protein search and opencode
Overview
Human Protein Atlas protein search in other agents
Questions about Human Protein Atlas protein search in opencode
Can opencode use Human Protein Atlas protein search?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Human Protein Atlas protein search like any built-in tool.
How much does Human Protein Atlas protein search cost in opencode?
$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need an Alexandria account to use Human Protein Atlas protein search in opencode?
No. Spiral runs Human Protein Atlas protein search on its own Alexandria account. You sign in to Spiral once and never paste a key.
How long does it take to set up Human Protein Atlas protein search in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Human Protein Atlas protein search runs?
Human Protein Atlas protein search runs in the background. opencode starts the run, checks on it and gives you the json when it's ready.
Does HPA have measured protein locations for every human gene?
The downloadable subcellular location dataset covers 13,658 genes across 49 location categories. That coverage is narrower than the Atlas's goal of mapping all human proteins.
Where does the tissue RNA expression data come from?
HPA combines its own RNA sequencing data with GTEx. For each gene and tissue type, the consensus nTPM uses the higher normalized value from the two sources.
What does RNA enriched mean?
HPA requires at least four times higher RNA expression than in every other tissue, cell type, or cell type group being compared. This is an RNA expression classification, not a measurement of protein location.
How broadly are protein locations tested?
The standard assay tests up to three cell lines selected from a panel of 42, using immunofluorescence and confocal microscopy. A reported location therefore reflects those experimental cell contexts.
What does an Uncertain protein location mean?
HPA assigns Uncertain when antibody staining contradicts experimental evidence or expression is not detected at the RNA level. Supported locations have backing in external literature.
Start using Human Protein Atlas protein search in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


