Cancer3.AI › AI in Oncology › Datasets › AACR Project GENIE
Registry / portal Free registration AACR GENIE data-use terms (Synapse registration)

AACR Project GENIE

The largest real-world clinical sequencing registry in oncology — the place to test whether a variant-effect or biomarker model generalises beyond TCGA.

Dataset site { } JSON

At a glance

ProviderAmerican Association for Cancer Research; hosted on Synapse / cBioPortal
AccessFree registration
LicenceAACR GENIE data-use terms (Synapse registration)
patients200 000
Size notesclinical-grade tumour sequencing from 19+ institutions with limited clinical data; releases twice a year
FormatsMAF, TSV
Data typeGenomics (DNA)Electronic health records
TaskVariant effectPrognosisSurvival analysis
CancerPan-cancer

Labels and annotations

Somatic mutations, copy number and fusions from targeted panels; cancer type (OncoTree), age, sex, sample type; biopharma-collaborative subsets add treatment and outcome data.

Details

Not yet documented on this card.

Models trained or evaluated on it

No model in this catalog is linked to this dataset yet.

Sources

  1. AACR Project GENIE
  2. GENIE on cBioPortal

This page is educational — it is not medical advice and does not replace consultation with an oncologist. Diagnostic and treatment decisions are made solely by specialist physicians.