ncats-arax
Lets your agent query biomedical knowledge APIs to find relationships. It's useful for researching information about biological entities and their connections.
What it does
ARAX is a tool that searches for information within a large network of biomedical data. It finds connections between different elements, like genes and diseases, based on specific questions you ask.
When to use it
- ✓When you want to know if a drug affects a specific gene.
- ✓When you want to understand the relationship between a disease and a chemical substance.
- ✓When you need to check the source of information found in databases.
Example of what to ask your AI
“What genes are associated with cystic fibrosis disease?”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You provide information about what you are looking for (like a substance or disease name), and ARAX uses this to search its data network. It then returns the connections it finds.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add K-Dense-AI/scientific-agent-skills --skill ncats-araxOr download just the file:
curl -L https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/main/skills/ncats-arax/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
NCATS ARAX
Use ARAX as a constrained knowledge-graph lookup service. Submit reviewed CURIEs and explicit Biolink types, preserve the exact TRAPI exchange, inspect query-edge bindings and provenance, and treat every returned path as a candidate for subsequent verification.
Read query-contract.md before constructing a query. Read output-schema.md when interpreting saved artifacts, warnings, provenance, or partial results.
Safety boundary
- Use only public, nonsensitive research questions. ARAX status facilities may expose query and
caller metadata even when
store=falseis requested. - Do not submit patient information, confidential research questions, unpublished compound programs, or proprietary target hypotheses.
- Do not present a returned path as a validated mechanism or clinical recommendation.
- Report a zero as "not returned under these constraints," never as evidence that no relationship exists.
- Describe position as unscored response order, never rank.
- Verify important candidates with literature and authoritative databases separately.
Workflow
- Normalize free text separately, then review and report the proposed CURIE and category.
- Choose a typed one-hop query or an exactly two-hop query with both endpoints pinned.
- Use default RTX-KG2 lookup unless the user explicitly names two to five providers.
- Acknowledge that the biomedical query is public and choose a new or empty output directory.
- Run the client once. Do not silently change provider selection or expansion order after a failure or empty result.
- Inspect
summary.jsonfor bounded bindings and provenance andresponse.jsonfor the exact TRAPI payload. - Verify scientifically important paths outside ARAX.
Preflight
Check the production OpenAPI without making a biomedical query:
python skills/ncats-arax/scripts/arax_client.py preflight
The client verifies that the service identifies itself as ARAX, exposes POST /query and
GET /entity, and reports a supported TRAPI version. It reads info.x-trapi.version, falling back
to the title for older OpenAPI documents. A nonproduction endpoint or untested TRAPI series
requires an explicit override; neither override changes the fixed query shapes or operations.
Normalize an entity
Normalization is review-only and never triggers a graph query:
python skills/ncats-arax/scripts/arax_client.py normalize "ivacaftor" \
--expected-category biolink:SmallMolecule \
--max-synonyms 10 \
--acknowledge-public-query \
--output-dir outputs/normalize-ivacaftor
Review the canonical identifier, name, category, and synonym preview before using a CURIE. Report
all CURIEs and categories regardless of query outcome. A category warning or zero result is a
reason to curate the identifier, not to chain automatically to /query.
One-hop lookup
Pin at least one endpoint and type both nodes:
python skills/ncats-arax/scripts/arax_client.py one-hop \
--subject-id CHEBI:31690 \
--subject-category biolink:SmallMolecule \
--predicate biolink:affects \
--object-id NCBIGene:25 \
--object-category biolink:Gene \
--qualifier biolink:object_aspect_qualifier=activity_or_abundance \
--qualifier biolink:object_direction_qualifier=decreased \
--acknowledge-public-query \
--output-dir outputs/imatinib-abl1
Lookup mode is the default and fixes expansion to infores:rtx-kg2. It defaults to 20 results.
Use --result-limit N to request 1-50 results; 50 is the hard cap in either mode.
Endpoint-pinned two-hop lookup
Use exactly one typed, unpinned intermediate node:
python skills/ncats-arax/scripts/arax_client.py two-hop \
--subject-id CHEBI:66901 \
--subject-category biolink:SmallMolecule \
--predicate-1 biolink:affects \
--intermediate-category biolink:Gene \
--predicate-2 biolink:associated_with \
--object-id MONDO:0009061 \
--object-category biolink:Disease \
--qualifier-1 biolink:object_aspect_qualifier=activity_or_abundance \
--qualifier-1 biolink:object_direction_qualifier=increased \
--expand-order right-first \
--acknowledge-public-query \
--output-dir outputs/ivacaftor-cystic-fibrosis
Right-first expansion is the default. If an empty result merits another attempt, run a new query
explicitly with --expand-order left-first and keep the runs separate.
Selected-provider federation
…
FAQ
What is a CURIE?
A CURIE is a standardized way to identify entities (like genes or drugs) in scientific databases.
What are 'one-hop' and 'two-hop'?
These terms describe how direct the connection you are looking for is. 'One-hop' is a direct connection, while 'two-hop' involves an intermediate element.
Can I use confidential information?
No, ARAX should only be used for public, non-sensitive research questions. Do not submit patient information or proprietary data.
Details
Original description by the author
Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships. Use for Biolink-constrained RTX-KG2 lookup, explicit selected-provider ARAX federation, separate entity normalization, qualifier-aware graph traversal, and inspection of TRAPI edge bindings, publications, and knowledge-source provenance.
Popularity
- GitHub stars
- 51k
- Ranking position
- #1910
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
13c-metabolic-flux
Estimates metabolic fluxes using carbon-13 isotope tracing data. It is useful for analyzing cellular metabolism and biochemical pathways.
K-Dense-AI/scientific-agent-skills
adaptyv
Designs protein characterization experiments using the Adaptyv API. It helps estimate costs, submit sequences, and monitor lab results.
K-Dense-AI/scientific-agent-skills
aeon
Performs machine learning tasks on time series data. It is useful for classifying, forecasting, detecting anomalies, and finding patterns in sequential data.
K-Dense-AI/scientific-agent-skills
alphagenome
Looks up precomputed genomic effects for genetic variants. It provides scores and explanations to understand the impact of variants on the genome.
K-Dense-AI/scientific-agent-skills
Similar skills
data-throughput-accelerator
Makes your agent speed up the movement of large data volumes. It finds bottlenecks and ensures data is transferred quickly and correctly.
affaan-m/ECC
inventory-demand-planning
Helps your agent predict product demand in stores. It optimizes stock and plans when to run promotions to sell more.
affaan-m/ECC
market-research
Helps your agent conduct market research and competitive analysis. Provides summaries with source attribution.
affaan-m/ECC