Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.
The English summary is being prepared. Showing the original description.
Query NCBI GEO for gene expression datasets. Use when user asks about RNA-seq datasets, microarray data, expression data, GEO accessions, or finding public datasets. Triggers on "geo", "gene expression omnibus", "expression dataset", "RNA-seq dataset", "microarray dataset", "GSE", "GDS".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Query Gene Expression Omnibus for public expression datasets.
from Bio import Entrez
import json
Entrez.email = "bioclaw@example.com"
# 1. Search GEO datasets
def search_geo(query, max_results=10, db="gds"):
handle = Entrez.esearch(db=db, term=query, retmax=max_results, sort="relevance")
record = Entrez.read(handle)
handle.close()
return record
# 2. Get dataset summaries
def geo_summary(id_list, db="gds"):
ids = ",".join(str(i) for i in id_list)
handle = Entrez.esummary(db=db, id=ids, retmode="json")
result = json.loads(handle.read())
handle.close()
return result
# 3. Search for Series (GSE)
def search_gse(keyword, organism="Homo sapiens", max_results=10):
query = f'"{keyword}" AND "{organism}"[Organism] AND gse[ETYP]'
return search_geo(query, max_results)
# Example: Find breast cancer RNA-seq datasets
search = search_gse("breast cancer RNA-seq", max_results=5)
print(f"Found {search['Count']} datasets")
if search['IdList']:
summaries = geo_summary(search['IdList'])
for uid in search['IdList']:
info = summaries['result'].get(str(uid), {})
title = info.get('title', 'N/A')
gse = info.get('accession', 'N/A')
gpl = info.get('gpl', 'N/A')
n_samples = info.get('n_samples', 'N/A')
summary = info.get('summary', 'N/A')[:200]
print(f"\n{gse}: {title}")
print(f" Platform: {gpl}, Samples: {n_samples}")
print(f" Summary: {summary}...")
print(f" URL: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc={gse}")
"CRISPR" AND gse[ETYP]"Homo sapiens"[Organism]"Illumina"[Platform]"2024/01:2026/12"[PDAT]"breast cancer" AND "RNA-seq" AND "Homo sapiens"[Organism] AND gse[ETYP]No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.
The English summary is being prepared. Showing the original description.
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm. For QC thresholds, use protein-qc.
The English summary is being prepared. Showing the original description.
AlphaFold2 / AlphaFold-Multimer structure prediction for validation and confidence scoring. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm2-sequence-scoring. For QC thresholds, use protein-design-qc.
The English summary is being prepared. Showing the original description.
Workflow for event-level and isoform-level splicing analysis with sashimi-ready outputs and splice QC.
The English summary is being prepared. Showing the original description.
ATAC-seq processing with assay QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up.
The English summary is being prepared. Showing the original description.
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.
The English summary is being prepared. Showing the original description.