Cellfm-datasets: A Unified Data Infrastructure for Single-Cell and Spatial Transcriptomics Foundation Model Pretraining (opens in new tab)
Large-scale cell foundation models are increasingly limited not only by model architecture, but also by the data infrastructure required to repeatedly sample sparse transcriptomic profiles from out-of-core cohorts. AnnData/H5AD has become a standard exchange format for single-cell and spatial omics analysis, yet its HDF5-backed layout is not designed for high-frequency random mini-batch loading under multi-worker and distributed pretraining. We present Cellfm-datasets, a data infrastructure a...
Read the original article