/bio-geo-data
<!--
$ npx -y skills add FreedomIntelligence/OpenClaw-Medical-Skills --skill bio-geo-data --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/bio-geo-data
Context preview
The summary Claude sees to decide when to auto-load this skill.
<!--
SKILL.md
bio-geo-data.SKILL.md<!--
COPYRIGHT NOTICE
This file is part of the "Universal Biomedical Skills" project.
Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
All Rights Reserved.
#
This code is proprietary and confidential.
Unauthorized copying of this file, via any medium is strictly prohibited.
#
Provenance: Authenticated by MD BABU MIA
-->
--- name: bio-geo-data description: Query NCBI Gene Expression Omnibus (GEO) for expression datasets using Biopython Bio.Entrez. Use when finding microarray/RNA-seq datasets, downloading expression data, or linking GEO series to SRA runs. tool_type: python primary_tool: Bio.Entrez measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools:
- read_file
- run_shell_command
---
GEO Data
Query and access Gene Expression Omnibus datasets using Biopython's Entrez module.
Required Setup
from Bio import Entrez
Entrez.email = 'your.email@example.com' # Required by NCBI
Entrez.api_key = 'your_api_key' # Optional
GEO Database Types
| Database | db value | Description | |----------|----------|-------------| | GEO DataSets | `gds` | Curated datasets (GDS*) | | GEO Profiles | `geoprofiles` | Individual gene profiles |
**GEO Record Types:** | Prefix | Type | Description | |--------|------|-------------| | GSE | Series | Complete study/experiment | | GSM | Sample | Individual sample | | GPL | Platform | Array/sequencing platform | | GDS | DataSet | Curated, normalized dataset |
Searching GEO
Search GEO DataSets (GDS)
from Bio import Entrez
Entrez.email = 'your.email@example.com'
# Search curated datasets
handle = Entrez.esearch(db='gds', term='breast cancer AND Homo sapiens[orgn]', retmax=10)
record = Entrez.read(handle)
handle.close()
print(f"Found {record['Count']} datasets")
print(f"IDs: {record['IdList']}")Search GEO Series (GSE)
# Search GEO Series via gds database
# Use entry_type filter
handle = Entrez.esearch(db='gds', term='RNA-seq[title] AND human[orgn] AND gse[entry_type]', retmax=10)
record = Entrez.read(handle)
handle.close()
Common Search Fields
| Field | Description | Example | |-------|-------------|---------| | `[orgn]` | Organism | `human[orgn]` | | `[title]` | Dataset title | `breast cancer[title]` | | `[description]` | Description text | `stem cell[description]` | | `[platform]` | Platform GPL | `GPL570[platform]` | | `[entry_type]` | Record type | `gse[entry_type]`, `gds[entry_type]` | | `[gdstype]` | Study type | `expression profiling[gdstype]` | | `[pubmed]` | PubMed ID | `35412348[pubmed]` | | `[pdat]` | Publication date | `2024[pdat]` |
GDS Types
# Expression profiling by array
term = 'expression profiling by array[gdstype] AND cancer'
# RNA-seq expression
term = 'expression profiling by high throughput sequencing[gdstype]'
# ChIP-seq
term = 'genome binding/occupancy profiling[gdstype]'
Fetching GEO Information
Get GEO DataSet Summary
# Fetch summary for GDS records
handle = Entrez.esummary(db='gds', id='200024320')
record = Entrez.read(handle)
handle.close()
summary = record[0]
print(f"Accession: {summary['Accession']}")
print(f"Title: {summary['title']}")
print(f"Summary: {summary['summary'][:200]}...")
print(f"Organism: {summary['taxon']}")
print(f"Platform: {summary['GPL']}")
print(f"Samples: {summary['n_samples']}")Summary Fields
summary['Accession'] # GSE/GDS accession
summary['title'] # Dataset title
summary['summary'] # Description
summary['taxon'] # Organism
summary['GPL'] # Platform ID
summary['n_samples'] # Number of samples
summary['FTPLink'] # FTP download link
summary['PubMedIds'] # Associated publications
summary['gdsType'] # Dataset type
summary['ptechType'] # Platform technology
Code Patterns
Search and List GEO Series
from Bio import Entrez
Entrez.email = 'your.email@example.com'
def search_geo(term, entry_type='gse', max_results=20):
full_term = f'{term} AND {entry_type}[entry_type]'
handle = Entrez.esearch(db='gds', term=full_term, retmax=max_results)
search = Entrez.read(handle)
handle.close()
if not search['IdList']:
return []
handle = Entrez.esummary(db='gds', id=','.join(search['IdList']))
summaries = Entrez.read(handle)
handle.close()
results = []
for s in summaries:
results.append({
'accession': s['Accession'],
'title': s['title'],
'organism': s['taxon'],
'samples': s['n_samples'],
'platform': s['GPL']
})
return results
datasets = search_geo('breast cancer RNA-seq AND human[orgn]')
for ds in datasets:
print(f"{ds['accession']}: {ds['title'][:60]}... ({ds['samples']} samples)")Find RNA-Seq Datasets
def find_rnaseq_datasets(organism, keywords, max_results=20):
term = f'{keywords} AND {organism}[orgn] AND expression profiling by high throughput sequencing[gdstype] AND gse[entry_type]'
handle = Entrez.esearch(db='gds', term=term, retmax=max_results)
search = Entrez.read(handle)
handle.close()
if not search['IdList']:
return []
handle = Entrez.esummary(db='gds', id=','.join(search['IdList']))
summaries = Entrez.read(handle)
handle.close()
return summaries
datasets = find_rnaseq_datasets('Homo sapiens', 'COVID-19')
for ds in datasets:
print(f"{ds['Accession']}: {ds['n_samples']} samples - {ds['title'][:50]}...")Get GSE Download Link
def get_geo_ftp(gse_accession):
'''Get FTP download link for a GSE'''
handle = Entrez.esearch(db='gds', term=f'{gse_accession}[accn]')
search = Entrez.read(handle)
handle.close()
if not search['IdList']:
return None
handle = Entrez.esummary(db='gds', id=search['IdList'][0])
summary = Entrez.read(handle)[0]
handle.close()
returRead more
<!--
COPYRIGHT NOTICE
This file is part of the "Universal Biomedical Skills" project.
Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
All Rights Reserved.
#
This code is proprietary and confidential.
Unauthorized copying of this file, via any medium is strictly prohibited.
#
Provenance: Authenticated by MD BABU MIA
-->
--- name: bio-geo-data description: Query NCBI Gene Expression Omnibus (GEO) for expression datasets using Biopython Bio.Entrez. Use when finding microarray/RNA-seq datasets, downloading expression data, or linking GEO series to SRA runs. tool_type: python primary_tool: Bio.Entrez measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools:
- read_file
- run_shell_command
---
GEO Data
Query and access Gene Expression Omnibus datasets using Biopython's Entrez module.
Required Setup
from Bio import Entrez Entrez.email = 'your.email@example.com' # Required by NCBI Entrez.api_key = 'your_api_key' # Optional
GEO Database Types
| Database | db value | Description | |----------|----------|-------------| | GEO DataSets | `gds` | Curated datasets (GDS*) | | GEO Profiles | `geoprofiles` | Individual gene profiles |
**GEO Record Types:** | Prefix | Type | Description | |--------|------|-------------| | GSE | Series | Complete study/experiment | | GSM | Sample | Individual sample | | GPL | Platform | Array/sequencing platform | | GDS | DataSet | Curated, normalized dataset |
Searching GEO
Search GEO DataSets (GDS)
from Bio import Entrez
Entrez.email = 'your.email@example.com'
# Search curated datasets
handle = Entrez.esearch(db='gds', term='breast cancer AND Homo sapiens[orgn]', retmax=10)
record = Entrez.read(handle)
handle.close()
print(f"Found {record['Count']} datasets")
print(f"IDs: {record['IdList']}")Search GEO Series (GSE)
# Search GEO Series via gds database # Use entry_type filter handle = Entrez.esearch(db='gds', term='RNA-seq[title] AND human[orgn] AND gse[entry_type]', retmax=10) record = Entrez.read(handle) handle.close()
Common Search Fields
| Field | Description | Example | |-------|-------------|---------| | `[orgn]` | Organism | `human[orgn]` | | `[title]` | Dataset title | `breast cancer[title]` | | `[description]` | Description text | `stem cell[description]` | | `[platform]` | Platform GPL | `GPL570[platform]` | | `[entry_type]` | Record type | `gse[entry_type]`, `gds[entry_type]` | | `[gdstype]` | Study type | `expression profiling[gdstype]` | | `[pubmed]` | PubMed ID | `35412348[pubmed]` | | `[pdat]` | Publication date | `2024[pdat]` |
GDS Types
# Expression profiling by array term = 'expression profiling by array[gdstype] AND cancer' # RNA-seq expression term = 'expression profiling by high throughput sequencing[gdstype]' # ChIP-seq term = 'genome binding/occupancy profiling[gdstype]'
Fetching GEO Information
Get GEO DataSet Summary
# Fetch summary for GDS records
handle = Entrez.esummary(db='gds', id='200024320')
record = Entrez.read(handle)
handle.close()
summary = record[0]
print(f"Accession: {summary['Accession']}")
print(f"Title: {summary['title']}")
print(f"Summary: {summary['summary'][:200]}...")
print(f"Organism: {summary['taxon']}")
print(f"Platform: {summary['GPL']}")
print(f"Samples: {summary['n_samples']}")Summary Fields
summary['Accession'] # GSE/GDS accession summary['title'] # Dataset title summary['summary'] # Description summary['taxon'] # Organism summary['GPL'] # Platform ID summary['n_samples'] # Number of samples summary['FTPLink'] # FTP download link summary['PubMedIds'] # Associated publications summary['gdsType'] # Dataset type summary['ptechType'] # Platform technology
Code Patterns
Search and List GEO Series
from Bio import Entrez
Entrez.email = 'your.email@example.com'
def search_geo(term, entry_type='gse', max_results=20):
full_term = f'{term} AND {entry_type}[entry_type]'
handle = Entrez.esearch(db='gds', term=full_term, retmax=max_results)
search = Entrez.read(handle)
handle.close()
if not search['IdList']:
return []
handle = Entrez.esummary(db='gds', id=','.join(search['IdList']))
summaries = Entrez.read(handle)
handle.close()
results = []
for s in summaries:
results.append({
'accession': s['Accession'],
'title': s['title'],
'organism': s['taxon'],
'samples': s['n_samples'],
'platform': s['GPL']
})
return results
datasets = search_geo('breast cancer RNA-seq AND human[orgn]')
for ds in datasets:
print(f"{ds['accession']}: {ds['title'][:60]}... ({ds['samples']} samples)")Find RNA-Seq Datasets
def find_rnaseq_datasets(organism, keywords, max_results=20):
term = f'{keywords} AND {organism}[orgn] AND expression profiling by high throughput sequencing[gdstype] AND gse[entry_type]'
handle = Entrez.esearch(db='gds', term=term, retmax=max_results)
search = Entrez.read(handle)
handle.close()
if not search['IdList']:
return []
handle = Entrez.esummary(db='gds', id=','.join(search['IdList']))
summaries = Entrez.read(handle)
handle.close()
return summaries
datasets = find_rnaseq_datasets('Homo sapiens', 'COVID-19')
for ds in datasets:
print(f"{ds['Accession']}: {ds['n_samples']} samples - {ds['title'][:50]}...")Get GSE Download Link
def get_geo_ftp(gse_accession):
'''Get FTP download link for a GSE'''
handle = Entrez.esearch(db='gds', term=f'{gse_accession}[accn]')
search = Entrez.read(handle)
handle.close()
if not search['IdList']:
return None
handle = Entrez.esummary(db='gds', id=search['IdList'][0])
summary = Entrez.read(handle)[0]
handle.close()
returThe largest open-source medical AI skill library for OpenClaw.
Other skills on openclaw-medical-skills.
- /aav-vector-design-agent
<!--
Open skill - /adaptyv
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use
Open skill - /adhd-daily-planner
Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that
Open skill - /aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations
Open skill - /agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.
Open skill - /agentd-drug-discovery
<!--
Open skill

