Reactome Database

pip install requests

import requests
import time

CONTENT = "https://reactome.org/ContentService"
ANALYSIS = "https://reactome.org/AnalysisService"

def reactome_get(base, path, params=None):
    """Generic Reactome REST API caller. Returns JSON or raises."""
    resp = requests.get(f"{base}{path}", params=params)
    resp.raise_for_status()
    try:
        return resp.json()
    except ValueError:
        return resp.text

# Check database version
version = reactome_get(CONTENT, "/data/database/version")
print(f"Reactome version: {version}")

# Query a pathway
pathway = reactome_get(CONTENT, "/data/query/R-HSA-69620")
print(f"Pathway: {pathway['displayName']}")
print(f"Species: {pathway['speciesName']}")
time.sleep(0.5)

# Search for pathways
results = reactome_get(CONTENT, "/search/query", params={"query": "apoptosis", "types": "Pathway"})
print(f"Found {results['found']} results for 'apoptosis'")

# Query pathway by stable ID
pathway = reactome_get(CONTENT, "/data/query/R-HSA-69620")
print(f"Name: {pathway['displayName']}")
print(f"Stable ID: {pathway['stId']}, Species: {pathway['speciesName']}")
print(f"Schema class: {pathway['schemaClass']}")  # Pathway, TopLevelPathway, etc.
time.sleep(0.5)

# Get participating physical entities in a pathway
entities = reactome_get(CONTENT, f"/data/participants/{pathway['stId']}")
print(f"\nParticipating entities: {len(entities)}")
for e in entities[:3]:
    print(f"  {e['displayName']} ({e['schemaClass']})")
time.sleep(0.5)

# Get participating molecules with reference entities (UniProt, ChEBI, etc.)
refs = reactome_get(CONTENT, f"/data/participants/{pathway['stId']}/referenceEntities")
print(f"\nReference entities: {len(refs)}")
for r in refs[:3]:
    print(f"  {r['displayName']} — {r.get('databaseName', 'N/A')}:{r.get('identifier', 'N/A')}")

# Keyword search filtered to Pathways
results = reactome_get(CONTENT, "/search/query", params={
    "query": "cell cycle",
    "types": "Pathway",
    "species": "Homo sapiens",
    "cluster": "true"
})
print(f"Total found: {results['found']}")
for entry in results.get("results", [])[:1]:
    for e in entry.get("entries", [])[:5]:
        print(f"  {e['stId']}: {e['name']}")
time.sleep(0.5)

# Search for proteins/complexes
proteins = reactome_get(CONTENT, "/search/query", params={
    "query": "TP53", "types": "Protein", "species": "Homo sapiens"
})
print(f"\nTP53 protein entries: {proteins['found']}")
time.sleep(0.5)

# Suggest (autocomplete)
suggestions = reactome_get(CONTENT, "/search/suggest", params={"query": "apopt"})
print(f"Suggestions: {suggestions}")

import requests
import time

ANALYSIS = "https://reactome.org/AnalysisService"

# Gene list (newline-separated identifiers — UniProt, HGNC symbols, Ensembl, etc.)
gene_list = "TP53\nBRCA1\nBRCA2\nATM\nCHEK2\nCDK2\nRB1\nMDM2\nCDKN1A\nBAX"

# Submit for enrichment (POST with text body)
resp = requests.post(
    f"{ANALYSIS}/identifiers/",
    headers={"Content-Type": "text/plain"},
    data=gene_list,
    params={"pageSize": 10, "page": 1, "sortBy": "ENTITIES_FDR", "order": "ASC"}
)
resp.raise_for_status()
result = resp.json()

print(f"Analysis token: {result['summary']['token']}")
print(f"Pathways found: {result['pathwaysFound']}")
print(f"Identifiers found: {result['identifiersNotFound']}")
print(f"\nTop enriched pathways:")
for p in result["pathways"][:5]:
    print(f"  {p['stId']}: {p['name']}")
    print(f"    FDR: {p['entities']['fdr']:.2e}, "
          f"Found: {p['entities']['found']}/{p['entities']['total']}")
time.sleep(0.5)

import requests
import time

ANALYSIS = "https://reactome.org/AnalysisService"

# Re-fetch results by token (from a previous analysis)
token = "MjAyNTA2MTcxMDA3MzRfMQ%3D%3D"  # example — use token from Module 3

# Get results with filtering
results = requests.get(f"{ANALYSIS}/token/{token}", params={
    "pageSize": 20,
    "page": 1,
    "sortBy": "ENTITIES_FDR",
    "species": "Homo sapiens",
    "resource": "TOTAL"  # TOTAL, UNIPROT, ENSEMBL, CHEBI, etc.
})
results.raise_for_status()
data = results.json()
print(f"Token: {data['summary']['token']}")
print(f"Pathways: {data['pathwaysFound']}")
time.sleep(0.5)

# Get identifiers found in a specific pathway
pathway_detail = requests.get(
    f"{ANALYSIS}/token/{token}/found/all/{data['pathways'][0]['stId']}"
)
pathway_detail.raise_for_status()
found = pathway_detail.json()
print(f"\nIdentifiers found in {data['pathways'][0]['name']}:")
for entity in found.get("entities", [])[:5]:
    mapsTo = [m["identifier"] for m in entity.get("mapsTo", [])]
    print(f"  {entity['id']} -> {mapsTo}")

# Top-level pathways for human (9606 = NCBI taxonomy ID)
top = reactome_get(CONTENT, "/data/pathways/top/9606")
print(f"Top-level human pathways: {len(top)}")
for p in top[:5]:
    print(f"  {p['stId']}: {p['displayName']}")
time.sleep(0.5)

# Get contained events (sub-pathways and reactions)
events = reactome_get(CONTENT, "/data/pathway/R-HSA-69620/containedEvents")
print(f"\nContained events in Cell Cycle: {len(events)}")
for e in events[:5]:
    print(f"  {e['stId']}: {e['displayName']} ({e['schemaClass']})")
time.sleep(0.5)

# Get the full ancestor chain for a pathway
ancestors = reactome_get(CONTENT, "/data/event/R-HSA-69620/ancestors")
print(f"\nAncestors of Cell Cycle:")
for chain in ancestors:
    names = [a["displayName"] for a in chain]
    print(f"  {' > '.join(names)}")

# List all species in Reactome
species = reactome_get(CONTENT, "/data/species/all")
print(f"Species in Reactome: {len(species)}")
for s in species[:5]:
    print(f"  {s['displayName']} (taxId: {s['taxId']})")
time.sleep(0.5)

# Map a Reactome entity to external references
xrefs = reactome_get(CONTENT, "/data/query/R-HSA-69620/xrefs")
if isinstance(xrefs, list):
    print(f"\nCross-references for R-HSA-69620: {len(xrefs)}")
    for x in xrefs[:5]:
        print(f"  {x}")
time.sleep(0.5)

# Get orthologous pathway in another species (human → mouse)
mouse_ortho = reactome_get(CONTENT, "/data/orthology/R-HSA-69620/species/10090")
if mouse_ortho:
    for o in mouse_ortho[:3]:
        print(f"Mouse ortholog: {o['stId']}: {o['displayName']}")

import requests
import time

CONTENT = "https://reactome.org/ContentService"
ANALYSIS = "https://reactome.org/AnalysisService"

# Step 1: Submit gene list
genes = "TP53\nBRCA1\nBRCA2\nATM\nCHEK2\nCDK2\nRB1\nMDM2\nCDKN1A\nBAX"
resp = requests.post(
    f"{ANALYSIS}/identifiers/",
    headers={"Content-Type": "text/plain"},
    data=genes,
    params={"pageSize": 5, "sortBy": "ENTITIES_FDR", "order": "ASC"}
)
resp.raise_for_status()
result = resp.json()
token = result["summary"]["token"]
print(f"Token: {token} | Pathways found: {result['pathwaysFound']}")

# Step 2: Show top pathways with FDR
for p in result["pathways"][:5]:
    fdr = p["entities"]["fdr"]
    ratio = f"{p['entities']['found']}/{p['entities']['total']}"
    print(f"  {p['stId']}: {p['name']} (FDR={fdr:.2e}, {ratio})")
time.sleep(0.5)

# Step 3: Get details on top pathway
top_id = result["pathways"][0]["stId"]
detail = requests.get(f"{CONTENT}/data/query/{top_id}").json()
print(f"\nTop pathway: {detail['displayName']}")
print(f"Compartments: {[c['displayName'] for c in detail.get('compartment', [])]}")

# Uses reactome_get helper and CONTENT base URL from Quick Start

# Step 1: Find pathway by search
results = reactome_get(CONTENT, "/search/query",
                       params={"query": "DNA repair", "types": "Pathway", "species": "Homo sapiens"})
top_hit = results["results"][0]["entries"][0]
pid = top_hit["stId"]
print(f"Found: {pid} — {top_hit['name']}")
time.sleep(0.5)

# Step 2: Get sub-events
events = reactome_get(CONTENT, f"/data/pathway/{pid}/containedEvents")
reactions = [e for e in events if e["schemaClass"] == "Reaction"]
subpaths = [e for e in events if "Pathway" in e["schemaClass"]]
print(f"Sub-pathways: {len(subpaths)}, Reactions: {len(reactions)}")
time.sleep(0.5)

# Step 3: Get participating molecules for a reaction
if reactions:
    rxn = reactions[0]
    refs = reactome_get(CONTENT, f"/data/participants/{rxn['stId']}/referenceEntities")
    print(f"\n{rxn['displayName']} participants:")
    for r in refs[:5]:
        print(f"  {r.get('databaseName', '?')}:{r.get('identifier', '?')} — {r['displayName']}")

import requests

ANALYSIS = "https://reactome.org/AnalysisService"

# Tab-separated: identifier \t expression_value1 \t expression_value2 ...
# First line can be a header (auto-detected)
expression_data = """#id\tcontrol\ttreated
TP53\t1.2\t3.5
BRCA1\t2.1\t1.8
CDK2\t0.9\t4.2
RB1\t1.5\t0.6
MDM2\t1.0\t2.8
CDKN1A\t0.8\t5.1
BAX\t1.1\t3.9"""

resp = requests.post(
    f"{ANALYSIS}/identifiers/",
    headers={"Content-Type": "text/plain"},
    data=expression_data,
    params={"pageSize": 10, "sortBy": "ENTITIES_FDR"}
)
resp.raise_for_status()
result = resp.json()

print(f"Expression columns: {result['summary'].get('sampleName', 'N/A')}")
print(f"Token: {result['summary']['token']}")
for p in result["pathways"][:3]:
    exp = p["entities"].get("exp", [])
    print(f"  {p['name']}: FDR={p['entities']['fdr']:.2e}, expr={exp}")