pbm
Datasets
All datasets matching “pbm”PBMC_ATLAS10M_PBMCsplatter-cube-pbmc3k
Splatter cube: controlled scRNA-seq variants with known cluster structure
180 simulated datasets: 60 parameter points x 3 seeds, each 2,000 cells x 16,085 genes with a known number of clusters.
Generated with splatter, with baseline
parameters estimated from real reference data rather than chosen by hand.
Files
data/pP_sS.h5ad -- counts (CSR). obs["Group"] holds the ground-truth cluster label.
metrics.csv -- one row per simulation: parameters, realised sparsity… See the full description on the dataset page: https://huggingface.co/datasets/btraven/splatter-cube-pbmc3k.aida-asian-pbmc-cell-sentence-top2000
AIDA Asian PBMC Cell Sentences (Top 2000 Genes)
Dataset Description
This dataset contains 1,265,624 single cells from peripheral blood mononuclear cells (PBMCs) of 619 healthy donors across 5 Asian countries, transformed into "cell sentences" - space-separated gene symbols ordered by expression level.
Each cell is represented as a sequence of the top 2,000 most highly expressed genes, enabling language model-style analysis of single-cell transcriptomics data.… See the full description on the dataset page: https://huggingface.co/datasets/transhumanist-already-exists/aida-asian-pbmc-cell-sentence-top2000.10x-pbmc-5kParse_100K_PBMC_cytokines
Parse 100K PBMC Cytokines (IFN-γ vs PBS)
Balanced 100,000-cell subsample of the ~10 million cell cytokine stimulation
dataset from Parse Biosciences.
In the original experiment, peripheral blood mononuclear cells (PBMCs) from
twelve healthy donors were treated with either one of 90 different cytokines or
a phosphate-buffered saline (PBS) control for 24 hours, yielding
(90 + 1) × 12 = 1,092 experimental conditions.
For the brisc tutorials, the data is restricted to the… See the full description on the dataset page: https://huggingface.co/datasets/dashingcell/Parse_100K_PBMC_cytokines.