How to Use Open Targets target-disease evidence in Claude Code
Returns the evidence records behind a gene-disease relationship, including genetic findings, clinical reports, and literature evidence. Use it to inspect the support for a research hypothesis beyond an overall association score.
Prompts to try with Open Targets target-disease evidence in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Open Targets target-disease evidence for PCSK9 and hypercholesterolemia, then create a report in this project that groups the returned evidence by source.
Use Open Targets target-disease evidence for BRAF and melanoma, then add a clinical precedence table to this project's research report using only details in the returned records.
Use Open Targets target-disease evidence for NOD2 and inflammatory bowel disease twice, with and without descendant conditions, then save a comparison of the returned records in this project.
Use Open Targets target-disease evidence for LRRK2 and Parkinson disease, then build a publication reading list in this project from the returned Europe PMC records.
Use Open Targets target-disease evidence for TREM2 and Alzheimer disease, then compare the returned records with this project's saved baseline and write a change report.
How to set up Open Targets target-disease evidence in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code 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 Open Targets target-disease evidence
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": "platform-opentargets-org/evidence/list_evidence", "input": { "url": "<url>" } }'
Then paste one of the prompts above: Claude Code finds Open Targets target-disease evidence on Spiral, shows the price and runs it.
Open Targets target-disease evidence providers and prices
Spiral runs Open Targets target-disease evidence through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Limit | 1 to 50 | 25 | Rows per page, 1 to 50. |
| Indirect | on or off | Include evidence on the disease's descendants, as the evidence page does. |
Every API field of Open Targets Platform · List evidence is on its tool page: open its card above.
What can you do with Open Targets target-disease evidence in Claude Code?
Build a source-by-source evidence report for a gene-disease hypothesis in your project. A coding agent can turn Open Targets records into review tables and compare saved results after quarterly updates.
Prepare a target review
Collect evidence for PCSK9 and hypercholesterolemia, then organize the returned records by source for a drug discovery review.
Inspect clinical precedent
Review the clinical reports returned for BRAF and melanoma to identify the drug-development evidence supporting the relationship.
Build a literature reading list
Extract publication references from the Europe PMC evidence returned for LRRK2 and Parkinson disease. Use the list to choose papers for manual review.
Review rare variant support
Inspect gene burden evidence returned for TREM2 and Alzheimer disease, keeping the contributing studies separate in a research summary.
Check disease subtype contributions
Compare NOD2 evidence for inflammatory bowel disease with evidence restricted to that exact disease term. Identify which support comes from descendant conditions.
Refresh a research portfolio
Recheck selected gene-disease pairs after quarterly Platform updates and compare the returned records with a saved baseline to flag changes for review.
More on Open Targets target-disease evidence and Claude Code
Overview
Open Targets target-disease evidence in other agents
Questions about Open Targets target-disease evidence in Claude Code
Can Claude Code use Open Targets target-disease evidence?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Open Targets target-disease evidence like any built-in tool.
How much does Open Targets target-disease evidence cost in Claude Code?
$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.
Do I need an Alexandria account to use Open Targets target-disease evidence in Claude Code?
No. Spiral runs Open Targets target-disease evidence on its own Alexandria account. You sign in to Spiral once and never paste a key.
How long does it take to set up Open Targets target-disease evidence in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Open Targets target-disease evidence runs?
Open Targets target-disease evidence runs in the background. Claude Code starts the run, checks on it and gives you the json when it's ready.
How often does Open Targets update its evidence?
The Platform receives quarterly updates. Evidence reflects those releases, so checking every day does not mean new source findings will appear every day.
Can evidence for a broad disease include its subtypes?
Yes. Open Targets evidence pages include records annotated to descendant diseases or phenotypes in the ontology. RNA expression evidence is an exception: it is not propagated to parent terms.
Why might a published genetic finding be missing?
Open Targets applies study validation and fine-mapping filters, and it does not display Locus-to-Gene assignments below 0.05. Changes to the model or available studies can also change which findings appear.
What does a Europe PMC evidence record represent?
It represents gene-disease co-occurrences within a publication, starting from mentions in the same sentence. Repeated mentions of that pair in the publication are aggregated into one record; this rule alone does not establish causation.
What does clinical precedence evidence include?
It includes target-disease relationships inferred from a drug's indication and mechanism of action. Each record corresponds to a clinical report with a source and development stage, including approved drugs and drugs in clinical development.
Start using Open Targets target-disease evidence in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


