Query Reactome pathways via REST: pathway queries, entity lookup, keyword search, gene list enrichment, hierarchy, cross-refs. Content + Analysis services. Python wrapper: reactome2py. For KEGG use kegg-database; for PPIs use string-database-ppi.
SkillScore96Maintained
Automatic
◆Research pack
Last verified 8/24/2026
What it changes
Passed 22 of 23 test cases with the skill, and 15 of 23 without it.
Without skill65%
With skill96%
Checks it passed that the model alone missed
Requests path /data/pathways/top/9606.
Calls path /data/query/R-HSA-69620/xrefs.
Includes time.sleep(0.5) inside the loop.
and 6 more in the full report
7 fixed15 passed either way1 still failing0 broke
Pass-rate lift
+30 pp
Tokens
+256%
Agent turns
0%
Response time
-42%
Model gemini-3.6-flashMeasured 8/24/2026v122 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
Given an active analysis token 'TEST_TOKEN' and pathway ID 'R-HSA-69620', write a Python request that retrieves all input identifiers that mapped to that specific pathway.
Reactome is an open-source, curated database of biological pathways and reactions for 16+ species. It provides two REST APIs: the Content Service for querying pathway data, entities, and hierarchy, and the Analysis Service for gene/protein list enrichment and expression data overlay. All endpoints return JSON (default) or other formats and require no authentication.
When to Use
Querying pathway details by stable ID (e.g., R-HSA-69620 for Cell Cycle)
Searching for pathways, reactions, or entities by keyword
Running gene list enrichment analysis (over-representation) against Reactome pathways
Retrieving pathway hierarchy and containment relationships
Mapping identifiers across databases (UniProt, Ensembl, NCBI, ChEBI)
Getting species-specific pathway data (human, mouse, rat, and 13+ other organisms)
Retrieving analysis results by token for sharing or re-filtering
Building pathway context for multi-omics integration workflows
For KEGG metabolic pathways and cross-database ID conversion, use kegg-database instead
For protein-protein interaction networks, use string-database-ppi instead
For a Python wrapper with caching, consider reactome2py (pip install reactome2py)
Prerequisites
pip install requests
API constraints:
No authentication required — all endpoints are public
No documented hard rate limit — add time.sleep(0.5) between batch requests to be respectful
Content Service base URL: https://reactome.org/ContentService
Analysis Service base URL: https://reactome.org/AnalysisService