Geo Database

pip install GEOparse requests pandas

import GEOparse

# Download a GEO series (caches in current directory)
gse = GEOparse.get_GEO("GSE2553", destdir="./geo_data/")
print(f"Title: {gse.metadata['title'][0]}")
print(f"Samples: {len(gse.gsms)}")
print(f"Platform: {list(gse.gpls.keys())}")

# Sample metadata
meta = gse.phenotype_data
print(meta.head())

import requests

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

def geo_search(query, retmax=20):
    r = requests.get(f"{BASE}/esearch.fcgi",
                     params={"db": "gds", "term": query,
                             "retmax": retmax, "retmode": "json", "email": EMAIL})
    r.raise_for_status()
    return r.json()["esearchresult"]

# Search for human breast cancer RNA-seq datasets
result = geo_search(
    "breast cancer[title] AND Homo sapiens[organism] AND gse[entry type]",
    retmax=10
)
print(f"Found {result['count']} matching GEO datasets")
print(f"First accessions (UIDs): {result['idlist']}")

# Search for specific platform (e.g., Illumina HumanHT-12)
result = geo_search(
    "Illumina HumanHT-12[platform] AND Homo sapiens[organism] AND gse[entry type]",
    retmax=5
)
print(f"Illumina HumanHT-12 human datasets: {result['count']}")

import requests

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

def geo_summary(uids):
    r = requests.post(f"{BASE}/esummary.fcgi",
                      data={"db": "gds", "id": ",".join(uids),
                            "retmode": "json", "email": EMAIL})
    r.raise_for_status()
    return r.json()["result"]

# Get metadata for search results
result = geo_search_func = lambda q: requests.get(
    f"{BASE}/esearch.fcgi",
    params={"db": "gds", "term": q, "retmax": 3, "retmode": "json", "email": EMAIL}
).json()["esearchresult"]["idlist"]

uids = requests.get(
    f"{BASE}/esearch.fcgi",
    params={"db": "gds", "term": "lung cancer[title] AND gse[entry type]",
            "retmax": 3, "retmode": "json", "email": EMAIL}
).json()["esearchresult"]["idlist"]

summaries = geo_summary(uids)
for uid in summaries.get("uids", []):
    s = summaries[uid]
    print(f"\nAccession: {s.get('accession')} | {s.get('title')}")
    print(f"  Organism: {s.get('taxon')}")
    print(f"  Samples: {s.get('n_samples')}")
    print(f"  Type: {s.get('gdstype')}")

import GEOparse

# Download GSE (auto-caches; skip download if already present)
gse = GEOparse.get_GEO("GSE2553", destdir="./geo_data/", silent=True)

# Series metadata
print(f"Title   : {gse.metadata['title'][0]}")
print(f"Summary : {gse.metadata['summary'][0][:200]}...")
print(f"Samples : {len(gse.gsms)} GSMs")
print(f"Platforms: {list(gse.gpls.keys())}")

# Sample metadata table (phenotype data)
meta = gse.phenotype_data
print(f"Metadata columns: {list(meta.columns)}")
print(meta.head())

import GEOparse, pandas as pd

gse = GEOparse.get_GEO("GSE2553", destdir="./geo_data/", silent=True)

# Pivot to gene expression matrix (probes × samples)
gpl_id = list(gse.gpls.keys())[0]
pivot = gse.pivot_samples("VALUE", gpl_id)
print(f"Expression matrix shape: {pivot.shape}")  # (probes, samples)
print(pivot.iloc[:5, :3])

# Annotate probes with gene symbols from the GPL platform
gpl = gse.gpls[gpl_id]
annot = gpl.table[["ID", "Gene Symbol", "Gene Title"]].copy()
annot.columns = ["ID", "gene_symbol", "gene_title"]
annot = annot.dropna(subset=["gene_symbol"])
annot = annot[annot["gene_symbol"] != ""]

expr_annotated = pivot.join(annot.set_index("ID"), how="inner")
print(f"Annotated expression matrix: {expr_annotated.shape}")
print(expr_annotated[["gene_symbol", "gene_title"]].head())

import GEOparse

gsm = GEOparse.get_GEO("GSM45553", destdir="./geo_data/", silent=True)

print(f"Title   : {gsm.metadata['title'][0]}")
print(f"Source  : {gsm.metadata.get('source_name_ch1', ['n/a'])[0]}")
print(f"Organism: {gsm.metadata.get('organism_ch1', ['n/a'])[0]}")
print(f"Data rows: {len(gsm.table)}")
print(gsm.table.head())

import urllib.request, gzip, io, pandas as pd

# GEO series matrix file URL pattern
accession = "GSE2553"
series_num = accession[3:]  # strip "GSE"
folder = f"GSE{series_num[:-3]}nnn" if len(series_num) > 3 else f"GSE{series_num[:-2]}nn"

url = f"https://ftp.ncbi.nlm.nih.gov/geo/series/{folder}/{accession}/matrix/{accession}_series_matrix.txt.gz"

with urllib.request.urlopen(url) as resp:
    with gzip.open(resp, "rt", encoding="utf-8") as f:
        lines = f.readlines()

# Find metadata lines (start with !) and data table
meta_lines = [l for l in lines if l.startswith("!")]
data_start = next(i for i, l in enumerate(lines) if l.startswith('"ID_REF"'))
df = pd.read_csv(
    io.StringIO("".join(lines[data_start:])),
    sep="\t", index_col=0
)
print(f"Matrix shape: {df.shape}")
print(df.iloc[:3, :3])

import GEOparse

gse = GEOparse.get_GEO("GSE47966", destdir="./geo_data/", silent=True)  # a SuperSeries
relations = gse.metadata.get("relation", [])
subseries = [r.split(": ")[1] for r in relations if r.startswith("SuperSeries of")]
print(f"SubSeries to download: {subseries}")

for acc in subseries:
    sub = GEOparse.get_GEO(acc, destdir="./geo_data/", silent=True)
    print(f"  {acc}: {len(sub.gsms)} samples, platforms={list(sub.gpls.keys())}")

import GEOparse, pandas as pd

# Download series
gse = GEOparse.get_GEO("GSE2553", destdir="./geo_data/", silent=True)

# 1. Extract expression matrix
gpl_id = list(gse.gpls.keys())[0]
expr = gse.pivot_samples("VALUE", gpl_id)

# 2. Extract sample groups from characteristics
meta = gse.phenotype_data
print("Available metadata columns:", list(meta.columns))

# 3. Annotate probes with gene symbols
gpl = gse.gpls[gpl_id]
gene_col = "Gene Symbol" if "Gene Symbol" in gpl.table.columns else gpl.table.columns[1]
annot = gpl.table[["ID", gene_col]].dropna()
annot.columns = ["probe_id", "gene_symbol"]
annot = annot[annot["gene_symbol"].str.strip() != ""]

expr_genes = expr.join(annot.set_index("probe_id")[["gene_symbol"]], how="inner")
expr_genes = expr_genes.groupby("gene_symbol").mean()  # average duplicate probes

print(f"Genes × Samples: {expr_genes.shape}")
expr_genes.to_csv("expression_matrix.csv")
meta.to_csv("sample_metadata.csv")
print("Saved: expression_matrix.csv, sample_metadata.csv")

import requests, time, pandas as pd

EMAIL = "your@email.com"
BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

topic = "Alzheimer disease"
r = requests.get(f"{BASE}/esearch.fcgi",
                 params={"db": "gds", "email": EMAIL, "retmode": "json", "retmax": 50,
                         "term": f"{topic}[title] AND Homo sapiens[organism] AND gse[entry type]"})
uids = r.json()["esearchresult"]["idlist"]
print(f"Found {len(uids)} GSE datasets for '{topic}'")

rows = []
for i in range(0, len(uids), 20):
    batch = uids[i:i+20]
    r2 = requests.post(f"{BASE}/esummary.fcgi",
                       data={"db": "gds", "id": ",".join(batch),
                             "retmode": "json", "email": EMAIL})
    result = r2.json()["result"]
    for uid in result.get("uids", []):
        s = result[uid]
        rows.append({
            "accession": s.get("accession"),
            "title": s.get("title"),
            "n_samples": s.get("n_samples"),
            "organism": s.get("taxon"),
            "gds_type": s.get("gdstype"),
            "pub_date": s.get("pdat"),
        })
    time.sleep(0.4)

df = pd.DataFrame(rows).sort_values("n_samples", ascending=False)
df.to_csv(f"{topic.replace(' ', '_')}_geo_datasets.csv", index=False)
print(df[["accession", "title", "n_samples"]].head(10).to_string(index=False))