scDiffEq datasets: LARRY in vitro, human hematopoiesis, and pancreatic endocrinogenesis

Single-cell datasets used by the scDiffEq package, which models single-cell dynamics with neural differential equations. These files are mirrored here so that scdiffeq.datasets can fetch them without authentication. The previous host sits behind a web application firewall that rejects programmatic downloads, which left users unable to obtain the data at all. Contents LARRY in vitro (Weinreb et al.) — larry.h5ad (130,887 × 2,492, with precomputed PCA/UMAP), larry_unprocessed.h5ad (130,887 × 25,289, unfiltered), a prebuilt preprocessed form of the latter, precomputed CytoTRACE annotations, and KEGG-derived growth weights. Human hematopoiesis — raw and processed objects plus the fitted scaler/PCA/UMAP models. Pancreatic endocrinogenesis — raw and processed objects plus the fitted scaler/PCA/UMAP models. Provenance. These are redistributed and derived copies of data published by their original authors. Please cite the original publications alongside this record: LARRY in vitro — Weinreb C, Rodriguez-Fraticelli A, Camargo FD, Klein AM. Lineage tracing on transcriptional landscapes links state to fate during differentiation. Science (2020). 10.1126/science.aaw3381 Human hematopoiesis — Qiu X, Zhang Y, Martin-Rufino JD, et al. Mapping transcriptomic vector fields of single cells. Cell (2022). 10.1016/j.cell.2021.12.045 Pancreatic endocrinogenesis — Bastidas-Ponce A, Tritschler S, Dony L, et al. Comprehensive single cell mRNA profiling reveals a detailed roadmap for pancreatic endocrinogenesis. Development (2019). 10.1242/dev.173849 The .h5ad objects carry preprocessing applied by scDiffEq (gene filtering, standardization, and a 50-component PCA with a fixed random seed). Note that the seeded PCA is reproducible going forward but does not reproduce the basis distributed with the original publications, which was computed with an unseeded randomized SVD.