Search for gene expression DataSets and Profiles in the NCBI GEO database. Use this skill when the user wants to find microarray, RNA-seq, or other genomic data by keywords, organism, author, or specific fields.
This skill allows searching the NCBI Gene Expression Omnibus (GEO) database.
scripts/search_geo.py.references/ for task-specific guidance.Python: 3.10+. Repository baseline for current packaged skills.Third-party packages: not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.See ## Usage above for related details.
cd "20260316/scientific-skills/Evidence Insight/geo-search-api"
python -m py_compile scripts/search_geo.py
python scripts/search_geo.py --help
Example run plan:
CONFIG block or documented parameters if the script uses fixed settings.python scripts/search_geo.py with the validated inputs.scripts/search_geo.py.references/ contains supporting rules, prompts, or checklists.The skill provides a Python script to execute searches against the NCBI Entrez API.
scripts/search_geo.pyUse this script to perform searches.
Arguments:
query: (Required) The main search terms (e.g., "breast cancer", "GSE12345").--filters: (Optional) JSON string of field-specific filters.
'{"Organism": "Homo sapiens", "Author": "Smith"}'references/query_fields.json for supported fields.--db: (Optional) Target database. gds (DataSets/Series) or geoprofiles. Default: gds.--limit: (Optional) Maximum number of results. Default: 10.--email: (Optional) User email (recommended for NCBI E-utilities).--api_key: (Optional) NCBI API Key (recommended for higher rate limits).Example:
python scripts/search_geo.py "diabetes" --filters '{"Organism": "Mus musculus", "DataSet Type": "expression profiling by array"}' --limit 5
Queries are constructed by combining the main query term with any provided filters using the AND operator.
Field aliases (e.g., ORGN for Organism) are handled automatically by the NCBI API, but using full names from references/query_fields.json is recommended for clarity.
geo_search_api_result.md unless the skill documentation defines a better convention.Run this minimal verification path before full execution when possible:
python scripts/search_geo.py --help
Expected output format:
Result file: geo_search_api_result.md
Validation summary: PASS/FAIL with brief notes
Assumptions: explicit list if any