Cancer intelligence, as an API.
Integrate the world’s biomedical databases and causal reasoning into what you’re building.
Building cancer-aware applications means stitching together fragmented databases with no causal structure and no provenance — just raw data with no way to trace where a claim came from or why it matters.
Provenance-traced knowledge graph
855K+ entities and 7.7M+ relationships — every one traced to its original data source with a Pearl Causal Hierarchy layer.
Formal causal inference
Do-calculus, counterfactual reasoning, and intervention simulation over a Structural Causal Model — not statistical correlations.
Integrated biomedical databases
ChEMBL, cBioPortal, STRING, PubMed, and more — all locally integrated through one unified API.
Patient interpretation
Multi-mutation tumor profiles with evidence-graded treatment options, resistance analysis, and clinical trial matching.
import requests
API_KEY = "your_api_key"
BASE = "https://research.usegalen.com/api/v1"
# Look up EGFR and its treatment relationships
entity = requests.get(
f"{BASE}/entities/EGFR",
headers={"X-API-Key": API_KEY}
).json()
print(f"{entity['name']}: {entity['entity_type']}")
print(f"Relationships: {entity['relationship_count']}")
# Simulate inhibiting EGFR — trace causal downstream effects
causal = requests.post(
f"{BASE}/causal/intervention",
headers={"X-API-Key": API_KEY},
json={"target": "EGFR", "intervention_type": "inhibit"}
).json()
for effect in causal["downstream_effects"]:
print(f" {effect['entity']}: {effect['effect_type']}")