Archs4 Database

pip install requests pandas matplotlib seaborn

import requests

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def archs4_get(endpoint: str, params: dict = None) -> dict:
    """Send a GET request to the ARCHS4 API and return parsed JSON."""
    r = requests.get(f"{ARCHS4_BASE}/{endpoint}", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

# Quick check: top tissues expressing TP53
data = archs4_get("meta/genes/TP53/zscore")
tissues = data.get("values", [])
print(f"TP53 tissue expression entries: {len(tissues)}")
top5 = sorted(tissues, key=lambda x: x.get("zscore", 0), reverse=True)[:5]
for t in top5:
    print(f"  {t['tissue']:<40}  z={t['zscore']:.2f}")
# TP53 tissue expression entries: 200
#   thymus                                   z=2.81
#   testis                                   z=2.44

import requests
import pandas as pd

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def get_gene_tissue_zscore(gene_symbol: str, species: str = "human") -> pd.DataFrame:
    """Return tissue z-score expression profile for a gene.

    Parameters
    ----------
    gene_symbol : str
        HGNC gene symbol (e.g., 'TP53').
    species : str
        'human' or 'mouse' (default: 'human').
    """
    endpoint = f"meta/genes/{gene_symbol}/zscore"
    r = requests.get(
        f"{ARCHS4_BASE}/{endpoint}",
        params={"species": species},
        timeout=30
    )
    r.raise_for_status()
    data = r.json()
    records = data.get("values", [])
    df = pd.DataFrame(records)
    return df.sort_values("zscore", ascending=False).reset_index(drop=True)

df = get_gene_tissue_zscore("MYC")
print(f"MYC tissue z-scores: {len(df)} tissue types")
print(df[["tissue", "zscore"]].head(10).to_string(index=False))
# MYC tissue z-scores: 200
#                     tissue  zscore
#                      colon    3.12
#             small intestine    2.98
#                    placenta    2.74

# Query mouse tissues for a gene
df_mouse = get_gene_tissue_zscore("Myc", species="mouse")
print(f"Mouse Myc: top 5 tissues")
print(df_mouse[["tissue", "zscore"]].head(5).to_string(index=False))

import requests
import pandas as pd

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def get_coexpressed_genes(gene_symbol: str, top_n: int = 50,
                           species: str = "human") -> pd.DataFrame:
    """Return genes co-expressed with the query gene.

    Parameters
    ----------
    gene_symbol : str
        HGNC gene symbol.
    top_n : int
        Number of correlated genes to return (default: 50).
    species : str
        'human' or 'mouse' (default: 'human').
    """
    r = requests.get(
        f"{ARCHS4_BASE}/meta/genes/{gene_symbol}/correlations",
        params={"species": species, "limit": top_n},
        timeout=30
    )
    r.raise_for_status()
    data = r.json()
    records = data.get("values", [])
    df = pd.DataFrame(records)
    return df.sort_values("correlation", ascending=False).reset_index(drop=True)

coexp = get_coexpressed_genes("PCNA", top_n=20)
print(f"Top co-expressed genes with PCNA (n={len(coexp)}):")
print(coexp[["gene", "correlation"]].head(10).to_string(index=False))
# Top co-expressed genes with PCNA (n=20):
#   gene  correlation
#   RFC4         0.91
#   RFC2         0.89
#   MCM6         0.87

# Extract gene list for downstream enrichment
gene_list = coexp["gene"].tolist()
print(f"Co-expression gene list: {gene_list[:10]}")
# Pass gene_list to Enrichr or pathway analysis tools

import requests
import pandas as pd

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def search_samples(keyword: str, species: str = "human",
                   limit: int = 100) -> pd.DataFrame:
    """Search ARCHS4 samples by metadata keyword.

    Parameters
    ----------
    keyword : str
        Search term (e.g., 'breast cancer', 'liver', 'HeLa').
    species : str
        'human' or 'mouse'.
    limit : int
        Maximum number of samples to return.
    """
    r = requests.get(
        f"{ARCHS4_BASE}/samples/search",
        params={"query": keyword, "species": species, "limit": limit},
        timeout=30
    )
    r.raise_for_status()
    data = r.json()
    records = data.get("samples", [])
    return pd.DataFrame(records)

samples = search_samples("pancreatic cancer", limit=50)
print(f"Samples matching 'pancreatic cancer': {len(samples)}")
if len(samples) > 0:
    print(samples[["sample_id", "series_id", "title"]].head(5).to_string(index=False))
# Samples matching 'pancreatic cancer': 50
#   sample_id  series_id  title
#   GSM2345678  GSE123456  Pancreatic ductal adenocarcinoma - sample 1

import requests

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def get_gene_metadata(gene_symbol: str, species: str = "human") -> dict:
    """Return metadata and expression summary for a gene."""
    r = requests.get(
        f"{ARCHS4_BASE}/meta/genes/{gene_symbol}",
        params={"species": species},
        timeout=30
    )
    r.raise_for_status()
    return r.json()

meta = get_gene_metadata("GAPDH")
print(f"Gene: {meta.get('gene_symbol', 'N/A')}")
print(f"Species: {meta.get('species', 'N/A')}")
print(f"Ensembl ID: {meta.get('ensembl_gene_id', 'N/A')}")
print(f"Description: {meta.get('description', 'N/A')[:80]}")

# Compare metadata for a panel of housekeeping genes
import time

housekeeping = ["GAPDH", "ACTB", "B2M", "HPRT1", "RPLP0"]
for gene in housekeeping:
    meta = get_gene_metadata(gene)
    print(f"  {gene:<8}  {meta.get('ensembl_gene_id', 'N/A')}")
    time.sleep(0.1)

import requests
import pandas as pd

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def tissue_zscores(gene_symbol: str, top_n: int = 20, species: str = "human") -> pd.DataFrame:
    """Fetch top tissue z-scores for a gene and save for plotting."""
    r = requests.get(
        f"{ARCHS4_BASE}/meta/genes/{gene_symbol}/zscore",
        params={"species": species},
        timeout=30,
    )
    r.raise_for_status()
    df = pd.DataFrame(r.json().get("values", [])).sort_values("zscore", ascending=False).head(top_n)
    df.to_csv(f"{gene_symbol}_tissue_zscores.csv", index=False)
    return df

df = tissue_zscores("BRCA1", top_n=15)
print(f"Top tissues for BRCA1: {len(df)} -> BRCA1_tissue_zscores.csv")
# Render with the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Box / Violin / Bar" recipe (horizontal bar of zscore by tissue).

import requests

# HDF5 files are available for bulk download from the ARCHS4 data portal
# URL pattern: https://maayanlab.cloud/archs4/download#expression
# Human gene-level: human_gene_v2.6.h5
# Mouse gene-level: mouse_gene_v2.6.h5

def get_h5_download_urls() -> dict:
    """Return download URLs for ARCHS4 HDF5 expression matrices."""
    base = "https://maayanlab.cloud/archs4"
    return {
        "human_gene": f"{base}/files/human_gene_v2.6.h5",
        "mouse_gene": f"{base}/files/mouse_gene_v2.6.h5",
        "human_transcript": f"{base}/files/human_transcript_v2.6.h5",
        "mouse_transcript": f"{base}/files/mouse_transcript_v2.6.h5",
    }

urls = get_h5_download_urls()
for key, url in urls.items():
    print(f"  {key:<22}  {url}")

# To work with a downloaded HDF5 file:
try:
    import h5py
    import numpy as np

    h5_path = "human_gene_v2.6.h5"   # after download

    def extract_gene_from_h5(h5_path: str, gene_symbol: str,
                              n_samples: int = 1000) -> dict:
        """Extract expression values for a gene from the HDF5 matrix."""
        with h5py.File(h5_path, "r") as f:
            genes = [g.decode() for g in f["meta"]["genes"]["gene_symbol"][:]]
            if gene_symbol not in genes:
                raise ValueError(f"{gene_symbol} not found in HDF5")
            idx = genes.index(gene_symbol)
            expr = f["data"]["expression"][idx, :n_samples]
            sample_ids = [s.decode() for s in f["meta"]["samples"]["geo_accession"][:n_samples]]
        return {"gene": gene_symbol, "expression": expr, "sample_ids": sample_ids}

    result = extract_gene_from_h5(h5_path, "TP53", n_samples=500)
    print(f"TP53 expression: mean={result['expression'].mean():.2f},"
          f" max={result['expression'].max():.2f} (n={len(result['expression'])} samples)")
except ImportError:
    print("h5py not installed. Install with: pip install h5py")
except FileNotFoundError:
    print("HDF5 file not downloaded yet. Use the URLs above to download first.")

# Example: Positive z-score = above-average expression for that gene
# z > 2.0 → top ~2.5% of samples for that gene
# z < -2.0 → bottom ~2.5% of samples for that gene
# Use absolute z-score thresholds consistently when comparing across genes

import requests, time
import pandas as pd

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

gene_panel = ["MYC", "TP53", "BRCA1", "EGFR", "KRAS", "CDK4"]
top_n_tissues = 25

def get_tissue_zscores(gene: str) -> pd.Series:
    r = requests.get(
        f"{ARCHS4_BASE}/meta/genes/{gene}/zscore",
        params={"species": "human"},
        timeout=30
    )
    r.raise_for_status()
    records = r.json().get("values", [])
    df = pd.DataFrame(records).set_index("tissue")["zscore"]
    return df

# Build expression matrix (genes × tissues)
all_data = {}
for gene in gene_panel:
    try:
        all_data[gene] = get_tissue_zscores(gene)
        print(f"  Fetched {gene}")
    except Exception as e:
        print(f"  Warning: {gene} failed — {e}")
    time.sleep(0.1)

matrix = pd.DataFrame(all_data).T   # genes × tissues
# Select top tissues by max absolute z-score
tissue_importance = matrix.abs().max(axis=0).sort_values(ascending=False)
top_tissues = tissue_importance.head(top_n_tissues).index
matrix_subset = matrix[top_tissues]

# Save the gene × tissue matrix; render with the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Expression heatmap"
# recipe (RdBu_r, center=0) -> figures/archs4_panel_heatmap.png
matrix_subset.to_csv("archs4_panel_matrix.csv")
print(f"Panel matrix ready: {matrix_subset.shape} -> archs4_panel_matrix.csv")

import requests, time
import pandas as pd

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def get_coexp(gene: str, top_n: int = 20, species: str = "human") -> list:
    r = requests.get(
        f"{ARCHS4_BASE}/meta/genes/{gene}/correlations",
        params={"species": species, "limit": top_n},
        timeout=30
    )
    r.raise_for_status()
    return [rec["gene"] for rec in r.json().get("values", [])]

seed_gene = "PCNA"
min_correlation = 0.80

# Hop 1: direct co-expressed partners
hop1_genes = get_coexp(seed_gene, top_n=30)
print(f"Hop 1 partners of {seed_gene}: {len(hop1_genes)}")
time.sleep(0.1)

# Hop 2: co-expressed genes of each partner
edges = set()
for gene in hop1_genes[:10]:   # limit for demonstration
    partners = get_coexp(gene, top_n=20)
    for partner in partners:
        if partner != seed_gene:
            edges.add((gene, partner))
    time.sleep(0.1)

# Summarize the network
network_df = pd.DataFrame(list(edges), columns=["source", "target"])
hub_counts = network_df["source"].value_counts()
print(f"\nTwo-hop network: {len(edges)} edges")
print(f"Top hub genes:")
print(hub_counts.head(5))

network_df.to_csv(f"{seed_gene}_coexp_network.csv", index=False)
print(f"\nSaved {seed_gene}_coexp_network.csv")

import requests, time
import pandas as pd

ARCHS4_BASE = "https://maayanlab.cloud/archs4/api/v1"

def search_and_summarize(keyword: str, species: str = "human",
                          limit: int = 200) -> pd.DataFrame:
    """Search samples and return a tidy metadata DataFrame."""
    r = requests.get(
        f"{ARCHS4_BASE}/samples/search",
        params={"query": keyword, "species": species, "limit": limit},
        timeout=30
    )
    r.raise_for_status()
    records = r.json().get("samples", [])
    return pd.DataFrame(records)

keyword = "colorectal cancer"
df = search_and_summarize(keyword, limit=150)
print(f"Samples matching '{keyword}': {len(df)}")

if len(df) > 0:
    # Summarize by GEO series
    series_counts = df["series_id"].value_counts()
    print(f"\nTop GEO series (by sample count):")
    print(series_counts.head(8).to_string())

    # Export sample list
    df.to_csv(f"{keyword.replace(' ', '_')}_samples.csv", index=False)
    print(f"\nSaved {keyword.replace(' ', '_')}_samples.csv ({len(df)} samples)")
    print(f"Unique GEO series: {df['series_id'].nunique()}")