Cancer3.AI › AI in Oncology › Datasets › IPD-IMGT/HLA Database
Registry / portal Open download CC BY-ND 4.0 (see site terms)

IPD-IMGT/HLA Database

The naming authority for HLA alleles: the catalogue whose size — thirty thousand names against roughly a hundred well-measured alleles — defines the central problem of this field.

Dataset site 📖 How it works { } JSON

At a glance

ProviderEMBL-EBI / Anthony Nolan Research Institute
AccessOpen download
LicenceCC BY-ND 4.0 (see site terms)
named class I alleles30 894
Size notesas of June 2026: 9,279 HLA-A, 11,258 HLA-B, 9,416 HLA-C — while one patient carries at most six
Formatstext, CSV
Data typeGenomics (DNA)Protein sequence
TaskAntigen presentation
CancerPan-cancer

Labels and annotations

Official allele names and nucleotide/protein sequences; the source of the 34-residue pseudosequences that pan-allele models use to describe a groove.

Details

Not yet documented on this card.

Models trained or evaluated on it

  • pretraining NetMHCpan-4.1 Health Tech, Technical University of Denmark (Nielsen lab) — allele sequences from which the 34-residue pseudosequences are cut

Sources

  1. IPD-IMGT/HLA statistics

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.