Skip to content

Datasets & Benchmarks

Source note: this page is educational and was last checked against official portal landing pages on 2026-06-04. Dataset sizes, releases, access levels, and schemas change; verify the source portal before quoting numbers or building a benchmark.

Cancer datasets are not interchangeable. A useful dataset entry should say what was measured, how samples were selected, whether data are open or controlled-access, which version was used, and what the dataset is not suitable for.

High-value starting points

ResourceUse it forCautions
NCI Genomic Data Commons / TCGACohort discovery, harmonized genomic files, clinical metadata, TCGA/TARGET-style learningCounts and file availability change by project and release; controlled data require authorization
cBioPortal / MSK-IMPACT studiesExploratory clinico-genomic queries and mutation/copy-number summariesStudy versions and sample filters matter; not every cohort is a benchmarking truth set
AACR Project GENIEReal-world clinico-genomic registry dataUse the specific public release and data guide; clinical completeness varies by contributing center
TCIACancer imaging collections, radiology/pathology imaging researchImaging protocols, segmentations, labels, and linked clinical data vary by collection
Human Cell AtlasSingle-cell and spatial reference contextNot oncology-specific by default; use tissue, donor, assay, and disease metadata carefully

Sources: [1], [2], [3], [4], [5]


What to record before using a dataset

  • Source URL, portal release, download date, and accession/study ID.
  • Open vs controlled-access status and data-use restrictions.
  • Sample inclusion/exclusion rules and duplicate handling.
  • Assay type, platform, reference genome, pipeline, and normalization.
  • Endpoint definitions, censoring rules, and missing-data handling.
  • Whether labels are diagnostic, prognostic, predictive, synthetic, weakly supervised, or manually curated.

Benchmark rules

A dataset becomes a benchmark only after the task is locked:

TaskMinimum benchmark definition
Variant callingReference genome, truth set, region mask, variant classes, caller versions, scoring metric
Expression analysisCount matrix provenance, batch design, normalization, contrast, multiple-testing policy
Survival modelingStart time, event, censoring, follow-up, train/test split, calibration metric
Imaging AIDICOM metadata, segmentation source, preprocessing, scanner/site split, external validation
Trial matchingSource trial registry date, patient fact schema, criterion-level labels, human review policy

Do not treat a large public dataset as automatically fair, representative, or clinically validated. Public availability is not the same as benchmark readiness.


Local sample data

The file data/samples/sample_cancer_data.csv is synthetic demonstration data. It is not an incidence cohort, survival cohort, treatment-response cohort, or clinical benchmark. See data/samples/README.md in the repository before using it in examples.


See also


References

  1. NCI Genomic Data Commons. GDC Data Portal. https://portal.gdc.cancer.gov/
  2. National Cancer Institute. The Cancer Genome Atlas Program (TCGA). https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga
  3. AACR Project GENIE. AACR Project GENIE Data. https://www.aacr.org/professionals/research/aacr-project-genie/aacr-project-genie-data/
  4. The Cancer Imaging Archive. TCIA collections. https://www.cancerimagingarchive.net/
  5. Human Cell Atlas. HCA Data Portal. https://data.humancellatlas.org/

Early public release. Content evolves through continuous review. Questions: [email protected] · CC BY 4.0 where applicable.