Cbioportal Database

pip install requests pandas matplotlib

import requests
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    """GET request to cBioPortal REST API, returns parsed JSON."""
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

# List available cancer types
cancer_types = cbio_get("cancer-types")
print(f"Total cancer types: {len(cancer_types)}")
# Total cancer types: 87

# Find TCGA breast cancer study
studies = cbio_get("studies", params={"keyword": "breast"})
brca = [s for s in studies if "tcga_brca" in s["studyId"]]
if brca:
    s = brca[0]
    print(f"Study: {s['name']}")
    print(f"  studyId: {s['studyId']}")
    print(f"  Samples: {s['allSampleCount']}")
# Study: Breast Invasive Carcinoma (TCGA, PanCancer Atlas)
#   studyId: brca_tcga_pan_can_atlas_2018
#   Samples: 1084

import requests
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

# Get all cancer types
cancer_types = cbio_get("cancer-types")
ct_df = pd.DataFrame(cancer_types)[["cancerTypeId", "name", "dedicatedColor"]]
print(f"Cancer types: {len(ct_df)}")
print(ct_df.head(5).to_string(index=False))

# Find all studies for a cancer type
lung_studies = cbio_get("studies", params={"keyword": "lung adenocarcinoma"})
print(f"\nLung adenocarcinoma studies: {len(lung_studies)}")
for s in lung_studies[:3]:
    print(f"  {s['studyId']:40s}  n={s['allSampleCount']}")

# Get detailed study metadata including available data types
study_id = "brca_tcga_pan_can_atlas_2018"
study = cbio_get(f"studies/{study_id}")
print(f"Study: {study['name']}")
print(f"  Reference genome: {study.get('referenceGenome', 'n/a')}")
print(f"  All sample count: {study['allSampleCount']}")

# List molecular profiles for the study
profiles = cbio_get("molecular-profiles", params={"studyId": study_id})
print(f"\nMolecular profiles ({len(profiles)} total):")
for p in profiles:
    print(f"  {p['molecularProfileId']:55s}  [{p['molecularAlterationType']}]")

import requests, json
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_post(endpoint, body):
    """POST request to cBioPortal REST API."""
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=60)
    r.raise_for_status()
    return r.json()

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

# Get all samples for a study
study_id = "brca_tcga_pan_can_atlas_2018"
samples = cbio_get(f"studies/{study_id}/samples", params={"projection": "ID"})
sample_ids = [s["sampleId"] for s in samples]
print(f"Total samples: {len(sample_ids)}")

# Mutation profile ID follows pattern: {studyId}_mutations
profile_id = f"{study_id}_mutations"

# Fetch mutations for TP53 (Entrez gene ID = 7157)
body = {
    "sampleIds": sample_ids[:200],   # first 200 samples
    "entrezGeneIds": [7157]           # TP53
}
mutations = cbio_post(f"molecular-profiles/{profile_id}/mutations/fetch", body)
print(f"TP53 mutations in first 200 samples: {len(mutations)}")

# Summarize by mutation type
mut_df = pd.DataFrame(mutations)
print("\nMutation type distribution:")
print(mut_df["mutationType"].value_counts().head(8).to_string())
# Missense_Mutation    102
# Nonsense_Mutation     28
# Splice_Site           14
# Frame_Shift_Del       12

import requests
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_post(endpoint, body):
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=60)
    r.raise_for_status()
    return r.json()

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

study_id = "brca_tcga_pan_can_atlas_2018"
# CNA profile: discrete copy number data
cna_profile_id = f"{study_id}_gistic"   # GISTIC-derived discrete CNA

samples = cbio_get(f"studies/{study_id}/samples", params={"projection": "ID"})
sample_ids = [s["sampleId"] for s in samples][:300]

# Fetch CNA for ERBB2 (Entrez 2064) and MYC (Entrez 4609)
body = {
    "sampleIds": sample_ids,
    "entrezGeneIds": [2064, 4609]   # ERBB2, MYC
}
cna_data = cbio_post(
    f"molecular-profiles/{cna_profile_id}/molecular-data/fetch", body
)
print(f"CNA records retrieved: {len(cna_data)}")

cna_df = pd.DataFrame(cna_data)
# CNA values: 2=amplification, 1=gain, 0=diploid, -1=loss, -2=deep deletion
cna_label = {2: "AMP", 1: "GAIN", 0: "DIPLOID", -1: "LOSS", -2: "HOMDEL"}

print("\nERBB2 CNA distribution:")
erbb2 = cna_df[cna_df["entrezGeneId"] == 2064]
erbb2_counts = erbb2["value"].map(lambda x: cna_label.get(int(x), str(x))).value_counts()
print(erbb2_counts.to_string())
# DIPLOID    210
# AMP         62
# GAIN        18
# LOSS        10

import requests
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

study_id = "brca_tcga_pan_can_atlas_2018"

# List available clinical attributes for this study
attrs = cbio_get(f"studies/{study_id}/clinical-attributes")
attr_df = pd.DataFrame(attrs)[["clinicalAttributeId", "displayName", "datatype", "patientAttribute"]]
print(f"Clinical attributes: {len(attr_df)}")
# Show survival-related attributes
survival_attrs = attr_df[attr_df["clinicalAttributeId"].str.contains("SURVIVAL|MONTHS|STATUS", na=False)]
print(survival_attrs[["clinicalAttributeId", "displayName"]].to_string(index=False))

# Fetch OS_STATUS and OS_MONTHS for all patients
clinical = cbio_get(f"studies/{study_id}/clinical-data",
                    params={"clinicalDataType": "PATIENT",
                            "projection": "DETAILED"})
clin_df = pd.DataFrame(clinical)
# Pivot to patient × attribute matrix
clin_pivot = clin_df.pivot_table(
    index="patientId", columns="clinicalAttributeId",
    values="value", aggfunc="first"
)
print(f"\nPatients: {len(clin_pivot)}")
if "OS_STATUS" in clin_pivot.columns:
    print("OS status counts:")
    print(clin_pivot["OS_STATUS"].value_counts().to_string())
# OS status counts:
# 0:LIVING    765
# 1:DECEASED  319

import requests
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_post(endpoint, body):
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=60)
    r.raise_for_status()
    return r.json()

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

study_id = "brca_tcga_pan_can_atlas_2018"
# RNA-seq profile (RSEM normalized values)
rna_profile_id = f"{study_id}_rna_seq_v2_mrna_median_normed_log2"

samples = cbio_get(f"studies/{study_id}/samples", params={"projection": "ID"})
sample_ids = [s["sampleId"] for s in samples][:100]

# Fetch expression for ESR1 (Entrez 2099), ERBB2 (2064), PGR (5241)
body = {
    "sampleIds": sample_ids,
    "entrezGeneIds": [2099, 2064, 5241]   # ESR1, ERBB2, PGR
}
expr_data = cbio_post(
    f"molecular-profiles/{rna_profile_id}/molecular-data/fetch", body
)
expr_df = pd.DataFrame(expr_data)
print(f"Expression records: {len(expr_df)}")

# Pivot to gene × sample matrix
expr_pivot = expr_df.pivot_table(
    index="sampleId", columns="entrezGeneId", values="value"
)
expr_pivot.columns = ["ERBB2", "ESR1", "PGR"]   # rename by gene symbol
print(f"\nExpression matrix: {expr_pivot.shape}")
print(expr_pivot.describe().round(2))

import requests
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

def cbio_post(endpoint, body):
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=30)
    r.raise_for_status()
    return r.json()

# Single gene lookup by Hugo symbol
gene = cbio_get("genes/TP53")
print(f"TP53: entrezGeneId={gene['entrezGeneId']}, type={gene['type']}")
# TP53: entrezGeneId=7157, type=protein-coding

# Batch gene lookup — convert Hugo symbols to Entrez IDs
gene_symbols = ["BRCA1", "BRCA2", "TP53", "PIK3CA", "PTEN", "KRAS", "EGFR"]
body = {"geneIds": gene_symbols, "geneIdType": "HUGO_GENE_SYMBOL"}
gene_list = cbio_post("genes/fetch", body)

gene_map = {g["hugoGeneSymbol"]: g["entrezGeneId"] for g in gene_list}
gene_df = pd.DataFrame(gene_list)[["hugoGeneSymbol", "entrezGeneId", "type"]]
print(f"\nResolved {len(gene_df)} genes:")
print(gene_df.to_string(index=False))
# hugoGeneSymbol  entrezGeneId            type
#          BRCA1         672   protein-coding
#          BRCA2         675   protein-coding
#           TP53        7157   protein-coding

import requests, time
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

def cbio_post(endpoint, body):
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=60)
    r.raise_for_status()
    return r.json()

# Focus on a curated set of TCGA PanCancer Atlas studies
STUDIES = {
    "brca_tcga_pan_can_atlas_2018": "BRCA",
    "luad_tcga_pan_can_atlas_2018": "LUAD",
    "coad_tcga_pan_can_atlas_2018": "COAD",
    "prad_tcga_pan_can_atlas_2018": "PRAD",
    "gbm_tcga_pan_can_atlas_2018": "GBM",
}

GENE_ENTREZ = 7157   # TP53
GENE_SYMBOL = "TP53"

rows = []
for study_id, label in STUDIES.items():
    try:
        samples = cbio_get(f"studies/{study_id}/samples", params={"projection": "ID"})
        sample_ids = [s["sampleId"] for s in samples]
        n_total = len(sample_ids)
        profile_id = f"{study_id}_mutations"
        body = {"sampleIds": sample_ids, "entrezGeneIds": [GENE_ENTREZ]}
        muts = cbio_post(f"molecular-profiles/{profile_id}/mutations/fetch", body)
        mutated_samples = len({m["sampleId"] for m in muts})
        rows.append({"study": label, "n_mutated": mutated_samples,
                     "n_total": n_total,
                     "freq": mutated_samples / n_total * 100})
        time.sleep(0.2)
    except Exception as e:
        print(f"  Skipping {study_id}: {e}")

df = pd.DataFrame(rows).sort_values("freq", ascending=True)
df.to_csv(f"{GENE_SYMBOL}_mutation_frequency.csv", index=False)
print(df[["study", "n_mutated", "n_total", "freq"]].to_string(index=False))
# Render with the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Box / Violin / Bar" recipe (horizontal bar of freq by study).

import requests, time
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

def cbio_post(endpoint, body):
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=120)
    r.raise_for_status()
    return r.json()

study_id = "luad_tcga_pan_can_atlas_2018"
profile_id = f"{study_id}_mutations"

# Resolve gene symbols to Entrez IDs
gene_symbols = ["KRAS", "EGFR", "TP53", "BRAF", "STK11", "KEAP1", "RB1"]
gene_list = cbio_post("genes/fetch",
                       {"geneIds": gene_symbols, "geneIdType": "HUGO_GENE_SYMBOL"})
gene_map = {g["entrezGeneId"]: g["hugoGeneSymbol"] for g in gene_list}
entrez_ids = list(gene_map.keys())

# Fetch all samples
samples = cbio_get(f"studies/{study_id}/samples", params={"projection": "ID"})
sample_ids = [s["sampleId"] for s in samples]
print(f"Study: {study_id} — {len(sample_ids)} samples")

# Batch mutations in chunks of 500 samples to avoid timeouts
chunk_size = 500
all_muts = []
for i in range(0, len(sample_ids), chunk_size):
    chunk = sample_ids[i:i + chunk_size]
    body = {"sampleIds": chunk, "entrezGeneIds": entrez_ids}
    muts = cbio_post(f"molecular-profiles/{profile_id}/mutations/fetch", body)
    all_muts.extend(muts)
    time.sleep(0.1)

mut_df = pd.DataFrame(all_muts)
mut_df["hugoSymbol"] = mut_df["entrezGeneId"].map(gene_map)
print(f"Total mutations: {len(mut_df)}")
print("\nMutation counts per gene:")
print(mut_df.groupby("hugoSymbol")["sampleId"].nunique()
      .sort_values(ascending=False).to_string())

mut_df.to_csv(f"{study_id}_driver_mutations.csv", index=False)
print(f"\nSaved: {study_id}_driver_mutations.csv")

import requests
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

def cbio_post(endpoint, body):
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=60)
    r.raise_for_status()
    return r.json()

study_id = "brca_tcga_pan_can_atlas_2018"
cna_profile_id = f"{study_id}_gistic"

# Get all samples
samples = cbio_get(f"studies/{study_id}/samples", params={"projection": "ID"})
sample_ids = [s["sampleId"] for s in samples]

# Fetch ERBB2 CNA (Entrez 2064)
cna_data = cbio_post(
    f"molecular-profiles/{cna_profile_id}/molecular-data/fetch",
    {"sampleIds": sample_ids, "entrezGeneIds": [2064]}
)
cna_df = pd.DataFrame(cna_data)[["sampleId", "value"]].rename(columns={"value": "erbb2_cna"})
cna_df["erbb2_cna"] = cna_df["erbb2_cna"].astype(int)
cna_df["erbb2_status"] = cna_df["erbb2_cna"].map(
    {2: "Amplified", 1: "Gain", 0: "Diploid", -1: "Loss", -2: "Deep Deletion"})

# Fetch clinical data (OS_STATUS, OS_MONTHS)
clinical = cbio_get(f"studies/{study_id}/clinical-data",
                    params={"clinicalDataType": "PATIENT", "projection": "DETAILED"})
clin_df = pd.DataFrame(clinical)
clin_pivot = clin_df.pivot_table(
    index="patientId", columns="clinicalAttributeId", values="value", aggfunc="first"
).reset_index()

# Map samples to patients
sample_patient = cbio_get(f"studies/{study_id}/samples", params={"projection": "DETAILED"})
sp_df = pd.DataFrame(sample_patient)[["sampleId", "patientId"]]

# Merge CNA + clinical via patient ID
merged = (cna_df
          .merge(sp_df, on="sampleId")
          .merge(clin_pivot[["patientId", "OS_STATUS", "OS_MONTHS"]],
                 on="patientId", how="inner"))
merged = merged.dropna(subset=["OS_STATUS", "OS_MONTHS"])
merged["OS_MONTHS"] = pd.to_numeric(merged["OS_MONTHS"], errors="coerce")
merged["event"] = (merged["OS_STATUS"] == "1:DECEASED").astype(int)

# Survival table for the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Kaplan–Meier" recipe (columns: time, event, group)
km_input = (merged.loc[merged["erbb2_status"].isin(["Amplified", "Diploid"]),
                       ["OS_MONTHS", "event", "erbb2_status"]]
            .rename(columns={"OS_MONTHS": "time", "erbb2_status": "group"}))
km_input.to_csv("erbb2_survival.csv", index=False)
print(f"Survival table: {len(km_input)} patients -> erbb2_survival.csv")
print(km_input["group"].value_counts().to_string())
# Render with the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Kaplan–Meier" recipe -> figures/erbb2_survival.png

import requests, time
import pandas as pd

BASE_URL = "https://www.cbioportal.org/api"

def cbio_get(endpoint, params=None):
    r = requests.get(f"{BASE_URL}/{endpoint}", params=params,
                     headers={"Accept": "application/json"}, timeout=30)
    r.raise_for_status()
    return r.json()

def cbio_post(endpoint, body):
    r = requests.post(f"{BASE_URL}/{endpoint}", json=body,
                      headers={"Accept": "application/json",
                               "Content-Type": "application/json"},
                      timeout=90)
    r.raise_for_status()
    return r.json()

STUDIES = {
    "brca_tcga_pan_can_atlas_2018": "BRCA",
    "luad_tcga_pan_can_atlas_2018": "LUAD",
    "coad_tcga_pan_can_atlas_2018": "COAD",
    "gbm_tcga_pan_can_atlas_2018":  "GBM",
}
GENE_SYMBOLS = ["TP53", "KRAS", "PIK3CA", "EGFR", "PTEN"]

# Resolve genes
gene_list = cbio_post("genes/fetch",
                       {"geneIds": GENE_SYMBOLS, "geneIdType": "HUGO_GENE_SYMBOL"})
gene_map = {g["entrezGeneId"]: g["hugoGeneSymbol"] for g in gene_list}
entrez_ids = list(gene_map.keys())

freq_matrix = pd.DataFrame(index=GENE_SYMBOLS, columns=list(STUDIES.values()), dtype=float)

for study_id, label in STUDIES.items():
    try:
        samples = cbio_get(f"studies/{study_id}/samples", params={"projection": "ID"})
        sample_ids = [s["sampleId"] for s in samples]
        n_total = len(sample_ids)
        profile_id = f"{study_id}_mutations"
        body = {"sampleIds": sample_ids, "entrezGeneIds": entrez_ids}
        muts = cbio_post(f"molecular-profiles/{profile_id}/mutations/fetch", body)
        mut_df = pd.DataFrame(muts) if muts else pd.DataFrame()
        for eid, symbol in gene_map.items():
            if mut_df.empty:
                freq_matrix.loc[symbol, label] = 0.0
            else:
                n_mut = mut_df[mut_df["entrezGeneId"] == eid]["sampleId"].nunique()
                freq_matrix.loc[symbol, label] = n_mut / n_total * 100
        time.sleep(0.2)
    except Exception as e:
        print(f"  {label}: {e}")

freq_matrix = freq_matrix.fillna(0).astype(float)
freq_matrix.to_csv("mutation_frequency_matrix.csv")
print(freq_matrix.to_string())
# Render with the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Expression heatmap" recipe (gene x cancer-type, YlOrRd,
# annotated) -> figures/mutation_frequency_heatmap.png