AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

NCATS ARAX Biomedical Knowledge-Graph Lookup

Runs bounded one-hop and endpoint-pinned two-hop TRAPI queries against the NCATS Translator ARAX API and returns typed, provenance-rich biomedical relationships.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Sends TRAPI queries to the ARAX production API and saves request.json, response.json, and a bounded summary.json for reproducibility.
  • Performs entity normalization (free text → CURIE + Biolink category) as a separate, review-only step that never auto-chains into a graph query.
  • Restricts query shapes to typed one-hop (at least one endpoint pinned) and exactly two-hop with both endpoints pinned, with a single typed intermediate node.
  • Defaults to RTX-KG2 lookup; runs federated queries only when the user names 2–5 explicit providers.
  • Preserves returned predicates, qualifiers, primary/aggregator sources, and publication fields; a zero result is reported as "not returned under these constraints," never as absence of a relationship.
  • Deliberately excludes inference, ranking, link prediction, Pathfinder, ARS, batch, and NL-to-TRAPI surfaces.

Who it's for

  • Bioinformatics and translational researchers exploring drug–gene–disease links under the Biolink Model.
  • Data/literature curators who need reproducible query logs and explicit knowledge-source provenance.
  • Teams that want hard guardrails so an LLM does not overstate knowledge-graph output.

Example uses

  1. Drug–gene effect: query imatinib (CHEBI:31690) affecting ABL1 (NCBIGene:25) with object_direction_qualifier=decreased.
  2. Two-hop path: ivacaftor (CHEBI:66901) → Gene → cystic fibrosis (MONDO:0009061), both endpoints pinned, right-first expansion.
  3. Offline re-inspection: use summarize on a saved request/response pair to rebuild edge bindings and provenance for a write-up without hitting the network.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/ncats-arax/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/ncats-arax folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/ncats-arax/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/ncats-arax ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Prerequisites: Python 3.10+ and outbound HTTPS access to arax.transltr.io. No API key required (standard library only).
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Install the skill: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/ncats-arax ~/.claude/skills/
  4. Verify: run python ~/.claude/skills/ncats-arax/scripts/arax_client.py preflight to confirm the service identifies as ARAX with a supported TRAPI version.
  5. Restart Claude Code, then ask something like "use ARAX to look up how drug X affects gene Y."
  6. Caution: queries and caller metadata may be publicly visible — never submit patient data, confidential targets, or unpublished programs.
View source on GitHub ↗License: MIT