Back to datasets
Dataset assetOpen Source CommunitySingle-Cell RNA SequencingEmbryonic Development
gastrulation_mmusculus
This dataset contains single‑cell RNA‑sequencing data from early mouse embryonic development stages (days 6.5 to 8.5), covering embryonic and extra‑embryonic tissues. Sequenced with 10X Genomics Chromium, it includes 139,331 cells and 29,452 genes. Detailed metadata are provided, including embryonic stage, sequencing batch, and Theiler stage.
Source
huggingface
Created
Aug 13, 2024
Updated
Aug 16, 2024
Signals
145 views
Availability
Linked source ready
Overview
Dataset description and usage context
Dataset Overview
Basic Information
- Name: Mouse Gastrulation scRNA‑seq data
- Tags: biology, rna, gene expression, mus musculus (mouse)
- Size Category: 100K < n < 1M
- License: cc0‑1.0
Project Information
- Source: scRNA‑seq of whole mouse embryos during gastrulation and organogenesis, spanning days 6.5 to 8.5 of development, including embryonic and extra‑embryonic tissues.
- Original Files: Array Express (E‑MTAB‑6967)
- Species: Mus musculus (Mouse)
Experimental Details
- Method: 10X Genomics Chromium system (version 1 chemistry)
- Cell Count: 139,331
- Gene Count: 29,452
Loading the Data
Use HuggingFace's optimized library to load the dataset and create an AnnData object:
from datasets import load_dataset
ds = load_dataset("helical-ai/gastrulation_mmusculus", trust_remote_code=True, split="train[:65%]", download_mode="reuse_cache_if_exists")
ds = ds.with_format("np")
observation_columns = [obs for obs in list(ds.features.keys()) if not obs == raw_counts]
obs_data = pd.DataFrame(ds.select_columns(observation_columns).data.to_pandas(), columns=observation_columns)
adata = ad.AnnData(ds[raw_counts], obs=obs_data)
adata.var_names = ds.features[raw_counts].id.split(",")
adata.var[gene_name] = adata.var_names.str.upper()
Key Metadata
| Category Name | Type |
|---|---|
stage | E6.5, E6.75, E7.0, E7.25, E7.5, E7.75, E8.0, E8.25, E8.5, mixed_gastrulation |
sequencing.batch | 1, 2, 3 |
theiler | TS10, TS11, TS12, TS9, TS9‑10 |
celltype | Allantois, Anterior Primitive Streak, Blood progenitors 1, Blood progenitors 2, Cardiomyocytes, Caudal Mesoderm, Caudal epiblast, Caudal neurectoderm, Def. endoderm, Endothelium, Epiblast, Erythroid1, Erythroid2, Erythroid3, ExE ectoderm, ExE endoderm, ExE mesoderm, Forebrain/Midbrain/Hindbrain, Gut, Haematoendothelial progenitors, Intermediate mesoderm, Mesenchyme, Mixed mesoderm, NMP, Nascent mesoderm, Neural crest, Notochord, PGC, Paraxial mesoderm, Parietal endoderm, Pharyngeal mesoderm, Primitive Streak, Rostral neurectoderm, Somitic mesoderm, Spinal cord, Surface ectoderm, Visceral endoderm, nan |
License Information
Data released via EMBL‑EBI (Array Express) under a CC0 license.
The dataset was used in Pijuan‑Sala et al., Nature 2019.
Need downstream help?
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.