Cancer3.AI › AI in Oncology › Datasets › BD2013 — MHC binding affinity benchmark
Benchmark / challenge Open download public

BD2013 — MHC binding affinity benchmark

The reference affinity dataset behind fifteen years of binding predictors; its size and composition are why dataset composition, not architecture, drives reported performance.

Dataset site 📖 How it works { } JSON

At a glance

ProviderIEDB / Kim et al.
AccessOpen download
Licencepublic
affinity measurements176 161
Size notes114 alleles across six species — the historical training core for binding predictors, and a reminder of how small the measured world is
FormatsCSV
Data typeProtein sequence
TaskPeptide–MHC binding
CancerPan-cancer

Labels and annotations

Quantitative IC50 values from competitive binding assays with a radiolabelled reference peptide, or fluorescence-based equivalents.

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. Kim Y et al. Dataset size and composition impact the reliability of performance benchmarks. BMC Bioinformatics 2014

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.