Gtex Database

import requests

BASE_URL = "https://gtexportal.org/api/v2"

def gtex_get(endpoint, params=None):
    """Make a GET request to the GTEx API."""
    url = f"{BASE_URL}/{endpoint}"
    response = requests.get(url, params=params, headers={"Accept": "application/json"})
    response.raise_for_status()
    return response.json()

import requests
import pandas as pd

def get_gene_expression_by_tissue(gene_id_or_symbol, dataset_id="gtex_v10"):
    """Get median gene expression across all tissues."""
    url = "https://gtexportal.org/api/v2/expression/medianGeneExpression"
    params = {
        "gencodeId": gene_id_or_symbol,
        "datasetId": dataset_id,
        "itemsPerPage": 100
    }
    response = requests.get(url, params=params)
    data = response.json()

    records = data.get("data", [])
    df = pd.DataFrame(records)
    if not df.empty:
        df = df[["tissueSiteDetailId", "tissueSiteDetail", "median", "unit"]].sort_values(
            "median", ascending=False
        )
    return df

# Example: get expression of APOE across tissues
df = get_gene_expression_by_tissue("ENSG00000130203.10")  # APOE GENCODE ID
# Or use gene symbol (some endpoints accept both)
print(df.head(10))
# Output: tissue name, median TPM, sorted by highest expression

import requests
import pandas as pd

def query_eqtl(gene_id, tissue_id=None, dataset_id="gtex_v10"):
    """Query significant eQTLs for a gene, optionally filtered by tissue."""
    url = "https://gtexportal.org/api/v2/association/singleTissueEqtl"
    params = {
        "gencodeId": gene_id,
        "datasetId": dataset_id,
        "itemsPerPage": 250
    }
    if tissue_id:
        params["tissueSiteDetailId"] = tissue_id

    all_results = []
    page = 0
    while True:
        params["page"] = page
        response = requests.get(url, params=params)
        data = response.json()
        results = data.get("data", [])
        if not results:
            break
        all_results.extend(results)
        if len(results) < params["itemsPerPage"]:
            break
        page += 1

    df = pd.DataFrame(all_results)
    if not df.empty:
        df = df.sort_values("pval", ascending=True)
    return df

# Example: Find eQTLs for PCSK9
df = query_eqtl("ENSG00000169174.14")
print(df[["snpId", "tissueSiteDetailId", "slope", "pval", "gencodeId"]].head(20))

import requests

def query_variant_eqtl(variant_id, tissue_id=None, dataset_id="gtex_v10"):
    """Get all eQTL associations for a specific variant."""
    url = "https://gtexportal.org/api/v2/association/singleTissueEqtl"
    params = {
        "variantId": variant_id,  # e.g., "chr1_55516888_G_GA_b38"
        "datasetId": dataset_id,
        "itemsPerPage": 250
    }
    if tissue_id:
        params["tissueSiteDetailId"] = tissue_id

    response = requests.get(url, params=params)
    return response.json()

# GTEx variant ID format: chr{chrom}_{pos}_{ref}_{alt}_b38
# Example: "chr17_43094692_G_A_b38"

import requests

def get_egenes(tissue_id, dataset_id="gtex_v10"):
    """Get all eGenes (genes with at least one significant eQTL) in a tissue."""
    url = "https://gtexportal.org/api/v2/association/egene"
    params = {
        "tissueSiteDetailId": tissue_id,
        "datasetId": dataset_id,
        "itemsPerPage": 500
    }

    all_egenes = []
    page = 0
    while True:
        params["page"] = page
        response = requests.get(url, params=params)
        data = response.json()
        batch = data.get("data", [])
        if not batch:
            break
        all_egenes.extend(batch)
        if len(batch) < params["itemsPerPage"]:
            break
        page += 1
    return all_egenes

# Example: all eGenes in whole blood
egenes = get_egenes("Whole_Blood")
print(f"Found {len(egenes)} eGenes in Whole Blood")

import requests

def get_tissues(dataset_id="gtex_v10"):
    """Get all available tissues with metadata."""
    url = "https://gtexportal.org/api/v2/dataset/tissueSiteDetail"
    params = {"datasetId": dataset_id, "itemsPerPage": 100}
    response = requests.get(url, params=params)
    return response.json()["data"]

tissues = get_tissues()
# Key fields: tissueSiteDetailId, tissueSiteDetail, colorHex, samplingSite
# Common tissue IDs:
# Whole_Blood, Brain_Cortex, Liver, Kidney_Cortex, Heart_Left_Ventricle,
# Lung, Muscle_Skeletal, Adipose_Subcutaneous, Colon_Transverse, ...

import requests

def query_sqtl(gene_id, tissue_id=None, dataset_id="gtex_v10"):
    """Query significant sQTLs for a gene."""
    url = "https://gtexportal.org/api/v2/association/singleTissueSqtl"
    params = {
        "gencodeId": gene_id,
        "datasetId": dataset_id,
        "itemsPerPage": 250
    }
    if tissue_id:
        params["tissueSiteDetailId"] = tissue_id

    response = requests.get(url, params=params)
    return response.json()

import requests, pandas as pd

def interpret_gwas_variant(variant_id, dataset_id="gtex_v10"):
    """Find all genes regulated by a GWAS variant."""
    url = "https://gtexportal.org/api/v2/association/singleTissueEqtl"
    params = {"variantId": variant_id, "datasetId": dataset_id, "itemsPerPage": 500}
    response = requests.get(url, params=params)
    data = response.json()

    df = pd.DataFrame(data.get("data", []))
    if df.empty:
        return df
    return df[["geneSymbol", "tissueSiteDetailId", "slope", "pval", "maf"]].sort_values("pval")

# Example
results = interpret_gwas_variant("chr1_154453788_A_T_b38")
print(results.groupby("geneSymbol")["tissueSiteDetailId"].count().sort_values(ascending=False))