Catalogue
Genomics & Multi-omics Datasets
Synthetic, multi-ancestry datasets built from a common playbook and hosted on the Hugging Face Hub. All datasets are configuration-driven, literature-grounded, and released as CSV + Parquet.
Breast Cancer
Core Genomics & Omics
DNA Methylation — SSA Breast Cancer
electricsheepafrica/ssa-breast-dna-methylationCpG methylation beta values, promoter methylation of tumour suppressors (BRCA1, RASSF1A, CDH1), global methylation indices, epigenetic age metrics.
Multi-omicsRNA Expression — SSA Breast Cancer
electricsheepafrica/ssa-breast-rna-expressionSynthetic log2(TPM+1) expression values for housekeeping genes, ER/luminal pathway, HER2 pathway, basal-like markers, immune signatures.
Multi-omicsTumour Gene Expression Panels
electricsheepafrica/tumor-gene-expression-africanPanel-style gene expression (50–100 genes) reflecting clinical expression assays, African ancestry distributions and subtype frequencies.
Multi-omicsImmune Profiles & TME
electricsheepafrica/ssa-breast-immune-profilesImmune cell fractions, tumour-infiltrating lymphocytes (TILs), tumour microenvironment metrics for breast cancer samples.
Multi-omicsSystemic Immune Markers
electricsheepafrica/ssa-breast-systemic-immune-markersNLR, PLR, lymphocyte counts, CRP/ESR and related systemic inflammatory markers.
Multi-omicsImmunohistochemistry (IHC) Profiles
electricsheepafrica/ssa-breast-ihc-profilesER/PR/HER2 scores, Ki-67, and other IHC markers with derived molecular subtype calls.
Breast Cancer
Longitudinal & Integrated ML Datasets
Integrated Genomic–Clinical ML Dataset
electricsheepafrica/ssa-breast-integrated-mlBaseline genomics, clinical variables, social determinants, longitudinal visits, treatments, and outcomes for ML pipelines.
LongitudinalTumour Evolution & Disease Progression
electricsheepafrica/ssa-breast-disease-progressionMatched primary/metastatic tumour pairs, mutation burden, clonal time series with resistance mechanisms.
LongitudinalBiomarker Trajectories
electricsheepafrica/ssa-breast-biomarker-trajectoriesCA15-3, CA27-29, and ctDNA levels over 0–24 months, stratified by response class.
TechnicalData Quality Benchmarks
electricsheepafrica/ssa-breast-data-quality-benchmarksRNA/DNA QC metrics, batch effects, sequencing centre and platform patterns.
TechnicalMissing Data Patterns
electricsheepafrica/ssa-breast-missing-data-patternsLongitudinal visits with non-random missingness, loss to follow-up, test availability patterns.
Population Genomics
Genome-wide Variation & Structural Genomics
Genome-wide SNP Array (SSA AIMs)
electricsheepafrica/ssa-snp-array-aimsSample-level metadata for thousands of individuals, variant-level data for hundreds of thousands of SNPs with ancestry-informative markers.
PopulationStructural Variation Catalogue (SSA)
electricsheepafrica/ssa-structural-variation-catalogDeletions, duplications, inversions, and complex SVs across SSA ancestry groups with frequency tables.
GermlineBRCA African Germline Mutations
electricsheepafrica/brca-african-mutationsBRCA1/2 variants in African populations, founder variants and penetrance tables for risk model calibration.
Beyond Breast Cancer
Cross-cancer Genomics for SSA
Colorectal Genomic (SSA)
electricsheepafrica/colorectal-genomic-ssaSomatic mutations, copy-number patterns, key pathways in synthetic colorectal tumours with SSA-specific profiles.
Cross-cancerOvarian Somatic Mutations
electricsheepafrica/ovarian-somatic-mutationsSomatic mutation profiles for ovarian cancer including high-grade serous and other subtypes.
Cross-cancerCervical HPV Genotyping (SSA)
electricsheepafrica/cervical-hpv-genotyping-ssaHigh-risk and low-risk HPV genotypes in synthetic cervical screening cohorts with SSA prevalence patterns.
Browse the Full Collection
All datasets are available on Hugging Face with detailed README cards, validation reports, and code links.
Open Hugging Face Collection ↗